% % This file was created by the Typo3 extension % sevenpack version 0.7.14 % % --- Timezone: CEST % Creation date: 2013-05-24 % Creation time: 18-31-29 % --- Number of references % 1182 % @Book { 5772, title = {Dynamic Faces: Insights from Experiments and Computation}, year = {2010}, month = {10}, pages = {288}, abstract = {The recognition of faces is a fundamental visual function with importance for social interaction and communication. Scientific interest in facial recognition has increased dramatically over the last decade. Researchers in such fields as psychology, neurophysiology, and functional imaging have published more than 10,000 studies on face processing. Almost all of these studies focus on the processing of static pictures of faces, however, with little attention paid to the recognition of dynamic faces, faces as they change over time—a topic in neuroscience that is also relevant for a variety of technical applications, including robotics, animation, and human-computer interfaces. This volume offers a state-of-the-art, interdisciplinary overview of recent work on dynamic faces from both biological and computational perspectives. The chapters cover a broad range of topics, including the psychophysics of dynamic face perception, results from electrophysiology and imaging, clinical deficits in patients with impairments of dynamic face processing, and computational models that provide insights about the brain mechanisms for the processing of dynamic faces. The book offers neuroscientists and biologists an essential reference for designing new experiments, and provides computer scientists with knowledge that will help them improve technical systems for the recognition, processing, synthesizing, and animating of dynamic faces.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/BookMITPressDraft_5772[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://mitpress.mit.edu/catalog/item/default.asp?ttype=2\&tid=12290}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {978-0-262-01453-3}, author = {Curio, C and B{\"u}lthoff, HH and Giese, MA} } @Book { 188, title = {Perception and Action in Virtual Environments: selected papers from the Cognitive and Computational Psychophysics Department, 1997 - 2000}, year = {2000}, pages = {416}, abstract = {At the Max-Planck-Institute for Biological Cybernetics in T{\"u}bingen we pursue a behavioral approach to human action and perception that proves especially well suited for studying more complex cognitive functions, such as object recognition and spatial cognition. The recent availability of high-fidelity `Virtual Reality‘ environments enables us to provide observers a level of sensory realism and dynamic sensory feedback that approaches their experiences in the real world. At the same time, we can keep the ultimate control over most stimulus aspects that are required by the rules of psychophysics. In this book, we take a closer look at these developments in spatial cognition research and present results from different experimental studies that we have conducted using this approach.}, department = {Department B{\"u}lthoff}, publisher = {Max Planck Institute for Biological Cybernetics}, address = {T{\"u}bingen, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, author = {von der Heyde, M and B{\"u}lthoff, HH} } @Book { 459, title = {Object Recognition in Man, Monkey, and Machine}, year = {1999}, month = {3}, pages = {217}, abstract = {These interconnected essays on three-dimensional visual object recognition present cutting-edge research by some of the most creative neuroscientific, cognitive, and computational scientists in the field. Cassandra Moore and Patrick Cavanagh take a classic demonstration, the perception of ''two-tone'' images, and turn it into a method for understanding the nature of object representations in terms of surfaces and the interaction between bottom-up and top-down processes. Michael J. Tarr and Isabel Gauthier use computer graphics to study whether viewpoint-dependent recognition mechanisms can generalize between exemplars of perceptually defined classes. Melvyn A. Goodale and G. Keith Humphrey use innovative psychophysical techniques to investigate dissociable aspects of visual and spatial processing in brain-injured subjects. D. I. Perrett, M. W. Oram, and E. Ashbridge combine neurophysiological single-cell data from monkeys with computational analyses for a new way of thinking about the mechanisms that mediate viewpoint-dependent object recognition and mental rotation. Shimon Ullman also addresses possible mechanisms to account for viewpoint-dependent behavior, but from the perspective of machine vision. Finally, Philippe G. Schyns synthesizes work from many areas, to provide a coherent account of how stimulus class and recognition task interact. The contributors bring a wide range of methodologies to bear on the common problem of image-based object recognition.}, department = {Department B{\"u}lthoff}, web_url = {http://mitpress.mit.edu/catalog/item/default.asp?tid=3885\&ttype=2}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, series = {Cognition Special Issues}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {978-0-262-70070-2}, author = {Tarr, MJ and B{\"u}lthoff, HH} } @Proceedings { 4925, title = {10th T{\"u}bingen Perception Conference: TWK 2007}, journal = {Proceedings of the 10th T{\"u}binger Wahrnehmungskonferenz (TWK 2007)}, year = {2007}, month = {7}, pages = {163}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/TWK-2007.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk07/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {10th T{\"u}binger Wahrnehmungskonferenz}, language = {en}, ISBN = {978-3-927091-77-1}, author = {B{\"u}lthoff, HH and Chatziastros, A and Mallot, HA and Ulrich, R} } @Proceedings { 4032, title = {9th T{\"u}bingen Perception Conference: TWK 2006}, journal = {9. T{\"u}binger Wahrnehmungskonferenz (TWK 2006)}, year = {2006}, month = {3}, pages = {177}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk06}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {9th T{\"u}binger Wahrnehmungskonferenz}, language = {en}, ISBN = {3-927091-73-1}, author = {B{\"u}lthoff, HH and Gillner, S and Mallot, HA and Ulrich, R} } @Proceedings { 3250, title = {8th T{\"u}bingen Perception Conference: TWK 2005}, journal = {Proceedings of the 8. T{\"u}binger Wahrnehmungskonferenz (TWK 2005)}, year = {2005}, month = {2}, pages = {202}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3250.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk05}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {8th T{\"u}binger Wahrnehmungskonferenz}, language = {en}, ISBN = {3-927091-70-7}, author = {B{\"u}lthoff, HH and Mallot, HA and Ulrich, R and Wichmann, FA} } @Proceedings { 3299, title = {Dynamic Perception: Workshop of the GI Section ''Computer Vision''}, journal = {Workshop on Dynamic Perception 2004}, year = {2004}, month = {11}, pages = {253}, department = {Department B{\"u}lthoff}, publisher = {Akademische Verlagsgesellschaft}, address = {Berlin, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {5th Workshop on Dynamic Perception 2004}, language = {en}, ISBN = {3-89838-059-9}, author = {Ilg, UJ and B{\"u}lthoff, HH and Mallot, HA} } @Proceedings { 2882, title = {Pattern Recognition: 26th DAGM Symposium}, journal = {Proceedings of the 26th Pattern Recognition Symposium (DAGM‘04)}, year = {2004}, month = {8}, pages = {581}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, web_url = {http://springerlink.com/content/wawqdma0pb8m/?p=a29656720fd44989ae2f4e363e37a15c\&pi=2191}, publisher = {Springer}, address = {Berlin, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {26th Pattern Recognition Symposium}, language = {en}, ISBN = {978-3-540-22945-2}, DOI = {10.1007/b99676}, author = {Rasmussen, CE and B{\"u}lthoff, HH and Giese, MA and Sch{\"o}lkopf, B} } @Proceedings { 2575, title = {7th T{\"u}bingen Perception Conference: TWK 2004}, journal = {Proceedings of the 7. T{\"u}binger Wahrnehmungskonferenz (TWK 2004)}, year = {2004}, month = {2}, pages = {198}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2575.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk04/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen}, event_name = {TWK 2004}, language = {en}, ISBN = {3-927091-68-5}, author = {B{\"u}lthoff, HH and Mallot, HA and Ulrich, R and Wichmann, FA} } @Proceedings { 2358, title = {6. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 6. T{\"u}binger Wahrnehmungskonferenz (TWK 2003)}, year = {2003}, month = {2}, pages = {183}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2358.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk03/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {Sixth Perception Conference at T{\"u}bingen (TWK 2003)}, language = {en}, ISBN = {3-927091-62-6}, author = {B{\"u}lthoff, HH and Gegenfurtner, K and Mallot, HA and Ulrich, R and Wichmann, FA} } @Proceedings { 1943, title = {Biologically Motivated Computer Vision: Second International Workshop}, journal = {Proceedings of the 2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002)}, year = {2002}, month = {11}, pages = {662}, abstract = {This book constitutes the refereed proceedings of the Second International Workshop on Biologically Motivated Computer Vision, BMCV 2002, held in T{\"u}bingen, Germany, in November 2002. The 22 revised full papers and 37 revised short papers presented together with 6 invited papers were carefully reviewed and selected from 97 submissions. The papers are organized in topical sections on neurons and features, motion, mid-level vision, recognition - from scenes to neurons, attention, robotics, and cognitive vision.}, department = {Department B{\"u}lthoff}, web_url = {http://www.bmcv.tuebingen.mpg.de}, publisher = {Springer}, address = {Berlin, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002)}, language = {en}, ISBN = {3-540-00174-3}, DOI = {10.1007/3-540-36181-2}, author = {B{\"u}lthoff, HH and Lee, S-W and Poggio, TA and Wallraven, C} } @Proceedings { 1209, title = {TWK 2002 : Beitr{\"a}ge zur 5. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 5. T{\"u}binger Wahrnehmungskonferenz (TWK 2002)}, year = {2002}, month = {2}, pages = {222}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1209.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk02/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {5. T{\"u}binger Wahrnehmungskonferenz (TWK 2002)}, language = {en}, ISBN = {3-927091-56-1}, author = {B{\"u}lthoff, HH and Gegenfurtner, K and Mallot, HA and Ulrich, R} } @Proceedings { 666, title = {TWK 2001: Beitr{\"a}ge zur 4. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 4. T{\"u}binger Wahrnehmungskonferenz (TWK 2001)}, year = {2001}, month = {3}, pages = {184}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf666.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk01/TWK.pdf}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen}, event_name = {4. T{\"u}binger Wahrnehmungskonferenz (TWK 2001)}, language = {en}, ISBN = {3-927091-54-5}, author = {B{\"u}lthoff, HH and Gegenfurtner, K and Mallot, HA and Ulrich, R} } @Proceedings { 174, title = {Biologically Motivated Computer Vision: First IEEE International Workshop on Biologically Motivated Computer Vision (BMCV 2000)}, journal = {Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision}, year = {2000}, month = {5}, pages = {656}, abstract = {This book constitutes the refereed proceedings of the First IEEE/CS International Workshops on Biologically Motivated Computer Vision, BMCV 2000, held in Seoul Korea in May 2000. The 56 revised papers presented together with eight invited papers were carefully reviewed and selected from 90 full paper submissions. The book is divided in topical sections on segmentation, detection, and object recognition; computational models; active and attentive vision; ICA and space-variant imaging; and neural networks and applications.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springer.com/computer/computer+imaging/book/978-3-540-67560-0}, publisher = {Springer}, address = {Berlin, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Seoul, South Korea}, event_name = {First IEEE International Workshop on Biologically Motivated Computer Vision (BMCV 2000)}, language = {en}, ISBN = {978-3-540-67560-0}, DOI = {10.1007/3-540-45482-9}, author = {Lee, S-W and B{\"u}lthoff, HH and Poggio, T} } @Proceedings { 173, title = {TWK 2000: Beitr{\"a}ge zur 3. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 3. T{\"u}binger Wahrnehmungskonferenz (TWK 2000)}, year = {2000}, month = {2}, pages = {169}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf173.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk00/TWK.pdf}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {3. T{\"u}binger Wahrnehmungskonferenz (TWK 2000)}, language = {en}, ISBN = {3-927091-49-9}, author = {B{\"u}lthoff, HH and Fahle, M and Gegenfurtner, K and Mallot, HA} } @Proceedings { 455, title = {Beitr{\"a}ge zur 2. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 2. T{\"u}binger Wahrnehmungskonferenz (TWK 1999)}, year = {1999}, month = {2}, pages = {134}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf455.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk99/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {2. T{\"u}binger Wahrnehmungskonferenz (TWK 99)}, language = {en}, ISBN = {3-927091-45-6}, author = {B{\"u}lthoff, HH and Fahle, M and Gegenfurtner, K and Mallot, HA} } @Proceedings { 665, title = {Visuelle Wahrnehmung: Beitr{\"a}ge zur 1. T{\"u}binger Wahrnehmungskonferenz}, journal = {Proceedings of the 1. T{\"u}binger Wahrnehmungskonferenz (TWK 1998)}, year = {1998}, month = {2}, pages = {170}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf665.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.twk.tuebingen.mpg.de/twk98/}, publisher = {Knirsch}, address = {Kirchentellinsfurt, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {1. T{\"u}binger Wahrnehmungskonferenz (TWK 1998)}, language = {en}, ISBN = {3-927091-40-5}, author = {B{\"u}lthoff, HH and Fahle, M and Gegenfurtner, K and Mallot, HA} } @Article { NieuwenhuizenMvB2013, title = {Influences of Simulator Motion System Characteristics on Pilot Control Behavior}, journal = {Journal of Guidance, Control, and Dynamics}, year = {2013}, month = {5}, volume = {36}, number = {3}, pages = {667-676}, abstract = {Low-cost motion systems have been proposed for certain training tasks that would otherwise be performed on highperformance full-flight simulators. These systems usually have lower bandwidth and lower smoothness. The influence of these characteristics on pilot perception and control behavior is unknown and needs to be investigated. In this paper, this is done by simulating a model of a simulator with limited capabilities on a high-end simulator. The platform limitations, which consist of a platform filter, time delay, and noise characteristics, can then be removed one by one, and their effect on control behavior is studied in isolation. An experiment was conducted to identify pilot perception and control behavior in a closed-loop control task. The time delay and noise characteristics of the simulators did not have an effect. However, it was found that the bandwidth of the motion system had a significant effect on performance and control behavior. Results indicate that the motion cues were barely used at all in conditions with a low bandwidth, and that participants relied on the visual cues to generate lead to perform the control task.}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/1.59257}, DOI = {10.2514/1.59257}, author = {Nieuwenhuizen, FM and Mulder, M and van Paassen, MM and B{\"u}lthoff, HH} } @Article { WallravenWB2013, title = {Learning to recognize face shapes through serial exploration}, journal = {Experimental Brain Research}, year = {2013}, month = {5}, volume = {226}, number = {4}, pages = {513-523}, abstract = {Human observers are experts at visual face recognition due to specialized visual mechanisms for face processing that evolve with perceptual expertize. Such expertize has long been attributed to the use of configural processing, enabled by fast, parallel information encoding of the visual information in the face. Here we tested whether participants can learn to efficiently recognize faces that are serially encoded—that is, when only partial visual information about the face is available at any given time. For this, ten participants were trained in gaze-restricted face recognition in which face masks were viewed through a small aperture controlled by the participant. Tests comparing trained with untrained performance revealed (1) a marked improvement in terms of speed and accuracy, (2) a gradual development of configural processing strategies, and (3) participants’ ability to rapidly learn and accurately recognize novel exemplars. This performance pattern demonstrates that participants were able to learn new strategies to compensate for the serial nature of information encoding. The results are discussed in terms of expertize acquisition and relevance for other sensory modalities relying on serial encoding.}, department = {Department B{\"u}lthoff}, web_url = {http://link.springer.com/content/pdf/10.1007\%2Fs00221-013-3463-y.pdf}, DOI = {10.1007/s00221-013-3463-y}, author = {Wallraven, C and Whittingstall, L and B{\"u}lthoff, HH} } @Article { BerthozBBCFFHKMMNPRSSTVvVW2013, title = {Motion Scaling for High-Performance Driving Simulators}, journal = {IEEE Transactions on Human-Machine Systems}, year = {2013}, month = {5}, volume = {43}, number = {3}, pages = {265-276}, abstract = {Advanced driving simulators aim at rendering the motion of a vehicle with maximum fidelity, which requires increased mechanical travel, size, and cost of the system. Motion cueing algorithms reduce the motion envelope by taking advantage of limitations in human motion perception, and the most commonly employed method is just to scale down the physical motion. However, little is known on the effects of motion scaling on motion perception and on actual driving performance. This paper presents the results of a European collaborative project, which explored different motion scale factors in a slalom driving task. Three state-of-the-art simulator systems were used, which were capable of generating displacements of several meters. The results of four comparable driving experiments, which were obtained with a total of 65 participants, indicate a preference for motion scale factors below 1, within a wide range of acceptable values (0.4–0.75). Very reduced or absent motion cues significantly degrade driving performance. Applications of this research are discussed for the design of motion systems and cueing algorithms for driving simulation.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=6502304}, DOI = {10.1109/TSMC.2013.2242885}, author = {Berthoz, A and Bles, W and B{\"u}lthoff, HH and Correia Gracio, BJ and Feenstra, P and Filliard, N and Huhne, R and Kemeny, A and Mayrhofer, M and Mulder, M and Nusseck, HG and Pretto, P and Reymond, G and Schl{\"u}sselberger, R and Schwandtner, J and Teufel, H and Vailleau, B and van Paassen, MM and Vidal, M and Wentink, M} } @Article { SoykaBB2013, title = {Temporal processing of self-motion: modeling reaction times for rotations and translations}, journal = {Experimental Brain Research}, year = {2013}, month = {5}, volume = {Epub ahead}, abstract = {In this paper, we show that differences in reaction times (RT) to self-motion depend not only on the duration of the profile, but also on the actual time course of the acceleration. We previously proposed models that described direction discrimination thresholds for rotational and translational motions based on the dynamics of the vestibular sensory organs (otoliths and semi-circular canals). As these models have the potential to describe RT for different motion profiles (e.g., trapezoidal versus triangular acceleration profiles or varying profile durations), we validated these models by measuring RTs in human observers for a direction discrimination task using both translational and rotational motions varying in amplitude, duration and acceleration profile shape in a within-subjects design. In agreement with previous studies, amplitude and duration were found to affect RT, and importantly, we found an influence of the profile shape on RT. The models are able to fit the measured RTs with an accuracy of around 5 ms, and the best-fitting parameters are similar to those found from identifying the models based on threshold measurements. This confirms the validity of the modeling approach and links perceptual thresholds to RT. By establishing a link between vestibular thresholds for self-motion and RT, we show for the first time that RTs to purely inertial motion stimuli can be used as an alternative to threshold measurements for identifying self-motion perception models. This is advantageous, since RT tasks are less challenging for participants and make assessment of vestibular function less fatiguing. Further, our results provide strong evidence that the perceived timing of self-motion stimulation is largely influenced by the response dynamics of the vestibular sensory organs.}, department = {Department B{\"u}lthoff}, web_url = {http://link.springer.com/content/pdf/10.1007\%2Fs00221-013-3536-y.pdf}, DOI = {10.1007/s00221-013-3536-y}, author = {Soyka, F and B{\"u}lthoff, HH and Barnett-Cowan, M} } @Article { SchultzBBP2012, title = {What the Human Brain Likes About Facial Motion}, journal = {Cerebral Cortex}, year = {2013}, month = {5}, volume = {23}, number = {5}, pages = {1167-1178}, abstract = {Facial motion carries essential information about other people's emotions and intentions. Most previous studies have suggested that facial motion is mainly processed in the superior temporal sulcus (STS), but several recent studies have also shown involvement of ventral temporal face-sensitive regions. Up to now, it is not known whether the increased response to facial motion is due to an increased amount of static information in the stimulus, to the deformation of the face over time, or to increased attentional demands. We presented nonrigidly moving faces and control stimuli to participants performing a demanding task unrelated to the face stimuli. We manipulated the amount of static information by using movies with different frame rates. The fluidity of the motion was manipulated by presenting movies with frames either in the order in which they were recorded or in scrambled order. Results confirm higher activation for moving compared with static faces in STS and under certain conditions in ventral temporal face-sensitive regions. Activation was maximal at a frame rate of 12.5 Hz and smaller for scrambled movies. These results indicate that both the amount of static information and the fluid facial motion per se are important factors for the processing of dynamic faces.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/Cerebral-Cortex-2012-Schultz.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://cercor.oxfordjournals.org/content/23/5/1167.full.pdf+html}, DOI = {10.1093/cercor/bhs106}, author = {Schultz, J and Brockhaus, M and B{\"u}lthoff, HH and Pilz, K} } @Article { delaRosaB2013, title = {Motor-visual neurons and action recognition in social interactions. Commentary on Mirror neurons: From origin to function}, journal = {Behavioral and Brain Sciences}, year = {2013}, month = {5}, department = {Department B{\"u}lthoff}, state = {accepted}, author = {de la Rosa, S and B{\"u}lthoff, HH} } @Article { LeeFSBR2013, title = {Semi-Autonomous Haptic Teleoperation Control Architecture of Multiple Unmanned Aerial Vehicles}, journal = {IEEE/ASME Transaction on Mechatronics}, year = {2013}, month = {5}, abstract = {Abstract—We propose a novel semi-autonomous haptic teleoperation control architecture for multiple unmanned aerial vehicles (UAVs), consisting of three control layers: 1) UAV control layer, where each UAV is abstracted by, and is controlled to follow the trajectory of, its own kinematic Cartesian virtual point (VP); 2) VP control layer, which modulates each VP’s motion according to the teleoperation commands and local artificial potentials (for VP-VP/VP-obstacle collision avoidance and VP-VP connectivity preservation); and 3) teleoperation layer, through which a single remote human user can command all (or some) of the VPs’ velocity while haptically perceiving the state of all (or some) of the UAVs and obstacles. Master-passivity/slave-stability and some asymptotic performance measures are proved. Experimental results using four custom-built quadrotor-type UAVs are also presented to illustrate the theory.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/2013b-LeeFraSonBueRob.pdf}, department = {Department B{\"u}lthoff}, state = {}, author = {Lee, D and Franchi, A and Son, HI and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Article { PiryankovadKBM2013, title = {Egocentric distance perception in large screen immersive displays}, journal = {Displays}, year = {2013}, month = {4}, volume = {34}, number = {2}, pages = {153–164}, abstract = {Many scientists have demonstrated that compared to the real world egocentric distances in head-mounted display virtual environments are underestimated. However, distance perception in large screen immersive displays has received less attention. We investigate egocentric distance perception in a virtual office room projected using a semi-spherical, a Max Planck Institute CyberMotion Simulator cabin and a flat large screen immersive display. The goal of our research is to systematically investigate distance perception in large screen immersive displays with commonly used technical specifications. We specifically investigate the role of distance to the target, stereoscopic projection and motion parallax on distance perception. We use verbal reports and blind walking as response measures for the real world experiment. Due to the limited space in the three large screen immersive displays we use only verbal reports as the response measure for the experiments in the virtual environment. Our results show an overall underestimation of distance perception in the large screen immersive displays, while verbal estimates of distances are nearly veridical in the real world. We find that even when providing motion parallax and stereoscopic depth cues to the observer in the flat large screen immersive display, participants estimate the distances to be smaller than intended. Although stereo cues in the flat large screen immersive display do increase distance estimates for the nearest distance, the impact of the stereoscopic depth cues is not enough to result in veridical distance perception. Further, we demonstrate that the distance to the target significantly influences the percent error of verbal estimates in both the real and virtual world. The impact of the distance to the target on the distance judgments is the same in the real world and in two of the used large screen displays, namely, the MPI CyberMotion Simulator cabin and the flat displays. However, in the semi-spherical display we observe a significantly different influence of distance to the target on verbal estimates of egocentric distances. Finally, we discuss potential reasons for our results. Based on the findings from our research we give general suggestions that could serve as methods for improving the LSIDs in terms of the accuracy of depth perception and suggest methods to compensate for the underestimation of verbal distance estimates in large screen immersive displays.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science/article/pii/S0141938213000036}, DOI = {10.1016/j.displa.2013.01.001}, author = {Piryankova, IV and de la Rosa, S and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Article { SonFLKBR2012, title = {Human-Centered Design and Evaluation of Haptic Cueing for Teleoperation of Multiple Mobile Robots}, journal = {IEEE Transactions on Cybernetics}, year = {2013}, month = {4}, volume = {43}, number = {2}, pages = {597-609}, abstract = {In this paper, we investigate the effect of haptic cueing on a human operator's performance in the field of bilateral teleoperation of multiple mobile robots, particularly multiple unmanned aerial vehicles (UAVs). Two aspects of human performance are deemed important in this area, namely, the maneuverability of mobile robots and the perceptual sensitivity of the remote environment. We introduce metrics that allow us to address these aspects in two psychophysical studies, which are reported here. Three fundamental haptic cue types were evaluated. The Force cue conveys information on the proximity of the commanded trajectory to obstacles in the remote environment. The Velocity cue represents the mismatch between the commanded and actual velocities of the UAVs and can implicitly provide a rich amount of information regarding the actual behavior of the UAVs. Finally, the Velocity+Force cue is a linear combination of the two. Our experimental results show that, while maneuverability is best supported by the Force cue feedback, perceptual sensitivity is best served by the Velocity cue feedback. In addition, we show that large gains in the haptic feedbacks do not always guarantee an enhancement in the teleoperator's performance.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2013a-SonFraChuKimBueRob.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=6294459}, DOI = {10.1109/TSMCB.2012.2212884}, author = {Son, HI and Franchi, A and Chuang, LL and Kim, J and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Article { RobuffoGiordanoFSB2012, title = {A Passivity-Based Decentralized Strategy for Generalized Connectivity Maintenance}, journal = {International Journal of Robotics Research}, year = {2013}, month = {3}, volume = {32}, number = {3}, pages = {299-323}, abstract = {The design of decentralized controllers coping with the typical constraints on the inter-robot sensing/communication capabilities represents a promising direction in multi-robot research thanks to the inherent scalability and fault tolerance of these approaches. In these cases, connectivity of the underlying interaction graph plays a fundamental role: it represents a necessary condition for allowing a group or robots to achieve a common task by resorting to only local information. The goal of this paper is to present a novel decentralized strategy able to enforce connectivity maintenance for a group of robots in a flexible way, that is, by granting large freedom to the group internal configuration so as to allow establishment/deletion of interaction links at anytime as long as global connectivity is preserved. A peculiar feature of our approach is that we are able to embed into a unique connectivity preserving action a large number of constraints and requirements for the group: (i) the presence of specific inter-robot sensing/communication models; (ii) group requirements such as formation control; and (iii) individual requirements such as collision avoidance. This is achieved by defining a suitable global potential function of the second smallest eigenvalue \(\lambda\)2 of the graph Laplacian, and by computing, in a decentralized way, a gradient-like controller built on top of this potential. Simulation results obtained with a group of quadrotor unmanned aerial vehicles (UAVs) and unmanned ground vehicles, and experimental results obtained with four quadrotor UAVs, are finally presented to thoroughly illustrate the features of our approach on a concrete case study.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/2013l-RobFraSecBue-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ijr.sagepub.com/content/32/3/299.full.pdf+html}, DOI = {10.1177/0278364912469671}, author = {Robuffo Giordano, P and Franchi, A and Secchi, C and B{\"u}lthoff, HH} } @Article { RuddleVB2013, title = {Learning to Walk in Virtual Reality}, journal = {ACM Transactions on Applied Perception}, year = {2013}, month = {3}, abstract = {This article provides longitudinal data for when participants learned to travel with a walking metaphor through virtual reality (VR) worlds, using interfaces that ranged from joystick-only, to linear and omnidirectional treadmills, and actual walking in VR. Three metrics were used: travel time, collisions (a measure of accuracy), and the speed profile. The time that participants required to reach asymptotic performance for traveling, and what that asymptote was, varied considerably between interfaces. In particular, when a world had tight turns (0.75 m corridors), participants who walked were more proficient than those who used a joystick to locomote and turned either physically or with a joystick, even after 10 minutes of training. The speed profile showed that this was caused by participants spending a notable percentage of the time stationary, irrespective of whether or not they frequently played computer games. The study shows how speed profiles can be used to help evaluate participants‟ proficiency with travel interfaces, highlights the need for training to be structured to addresses specific weaknesses in proficiency (e.g., start-stop movement), and for studies to measure and report that proficiency.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/ruddle-acm-tap.pdf}, department = {Department B{\"u}lthoff}, state = {}, author = {Ruddle, RA and Volkova, E and B{\"u}lthoff, HH} } @Article { VenrooijMAvvB2012, title = {A New View on Biodynamic Feedthrough Analysis: Unifying the Effects on Forces and Positions}, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics}, year = {2013}, month = {2}, volume = {43}, number = {1}, pages = {129-142}, abstract = {When performing a manual control task, vehicle accelerations can cause involuntary limb motions, which can result in unintentional control inputs. This phenomenon is called biodynamic feedthrough (BDFT). In the past decades, many studies into BDFT have been performed, but its fundamentals are still only poorly understood. What has become clear, though, is that BDFT is a highly complex process, and its occurrence is influenced by many different factors. A particularly challenging topic in BDFT research is the role of the human operator, which is not only a very complex but also a highly adaptive system. In literature, two different ways of measuring and analyzing BDFT are reported. One considers the transfer of accelerations to involuntary forces applied to the control device (CD); the other considers the transfer of accelerations to involuntary CD deflections or positions. The goal of this paper is to describe an approach to unify these two methods. It will be shown how the results of the two methods relate and how this knowledge may aid in understanding BDFT better as a whole. The approach presented is based on the notion that BDFT dynamics can be described by the combination of two transfer dynamics: 1) the transfer dynamics from body accelerations to involuntary forces and 2) the transfer dynamics from forces to CD deflections. The approach was validated using experimental results.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=6225447}, DOI = {10.1109/TSMCB.2012.2200972}, author = {Venrooij, J and Mulder, M and Abbink, DA and van Paassen, MM and van der Helm, FCT and B{\"u}lthoff, HH} } @Article { NieuwenhuizenvSMB2012, title = {Cross-platform Validation for a Model of a Low-cost Stewart Platform}, journal = {Journal of Modeling, Simulation, Identification, and Control}, year = {2013}, month = {1}, volume = {1}, number = {1}, pages = {1-23}, abstract = {actuators, lower bandwidth, and higher motion noise. The influence of these characteristics on pilot perception and control behavior is unknown, and needs to be investigated. A possible approach to this would be to simulate a platform with limited capabilities with a high-end platform, and then remove the platform limitations one by one. The effects of these platform limitations on pilot behavior can then be investigated in isolation. In this paper, a model of a low-cost simulator was validated for simulation on a high-performance simulator. A dynamic model of the MPI Stewart platform was analyzed and compared with measurements of the baseline simulator response. Measurements for validation of the implementation of the model on the SIMONA Research Simulator showed that the dynamics of the MPI Stewart platform could be represented well in terms of dynamic range, time}, department = {Department B{\"u}lthoff}, web_url = {http://uscip.org/JournalsDetail.aspx?journalID=21}, DOI = {10.7726/jmsic.2013.1001}, author = {Nieuwenhuizen, FM and van Paassen, MM and Stroosma, O and Mulder, M and B{\"u}lthoff, HH} } @Article { delaRosaGBC2012, title = {The contribution of different cues of facial movement to the emotional facial expression adaptation aftereffect}, journal = {Journal of Vision}, year = {2013}, month = {1}, volume = {13}, number = {1:23}, pages = {1-15}, abstract = {Probing emotional facial expression recognition with the adaptation paradigm is one way to investigate the processes underlying emotional face recognition. Previous research suggests that these processes are tuned to dynamic facial information (facial movement). Here we examined the tuning of processes involved in the recognition of emotional facial expressions to different sources of facial movement information. Specifically we investigated the effect of the availability of rigid head movement and intrinsic facial movements (e.g., movement of facial features) on the size of the emotional facial expression adaptation effect. Using a three-dimensional (3D) morphable model that allowed the manipulation of the availability of each of the two factors (intrinsic facial movement, head movement) individually, we examined emotional facial expression adaptation with happy and disgusted faces. Our results show that intrinsic facial movement is necessary for the emergence of an emotional facial expression adaptation effect with dynamic adaptors. The presence of rigid head motion modulates the emotional facial expression adaptation effect only in the presence of intrinsic facial motion. In a second experiment we show these adaptation effects are difficult to explain by merely the perceived intensity and clarity (uniqueness) of the adaptor expressions. Together these results suggest that processes encoding facial expressions are differently tuned to different sources of facial movements.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/13/1/23.full.pdf+html}, DOI = {10.1167/13.1.23}, author = {de la Rosa, S and Giese, MA and B{\"u}lthoff, HH and Curio, C} } @Article { KrimmelKBBMDBR2013, title = {Three-Dimensional Assessment of Facial Development in Children With Unilateral Cleft Lip With and Without Alveolar Cleft}, journal = {Journal of Craniofacial Surgery}, year = {2013}, month = {1}, volume = {24}, number = {1}, pages = {313–316}, abstract = {Children with cleft lip or cleft lip and alveolus represent a minor group in the cleft population. The aim of this study was to analyze the faces of these children. In a prospective, cross-sectional study, 344 healthy children and 30 children with cleft lip or cleft lip and alveolus were scanned three-dimensionally at the age of 0 to 6 years. Twenty-one standard anthropometric landmarks were identified, and the images were superimposed. Growth curves for normal facial development were calculated. The facial morphology of cleft children was compared with that of unaffected children. Facial morphology and growth in the transverse direction of the examined patients appeared broadened in all levels. Especially the nasal landmarks indicated a widening of the nose. The landmarks ac l, sbal l, sbal r, c l, sn l, and ls l differed significantly from unaffected children. In the sagittal and vertical dimensions, there was no significant difference compared with unaffected children. Our study demonstrates that surgical and orthodontic treatment can restore the vertical and sagittal dimensions of the face in children with cleft lip with and without alveolar clefts; however, the transverse dimension—especially the nose—remains too broad.}, department = {Department B{\"u}lthoff}, web_url = {http://journals.lww.com/jcraniofacialsurgery/pages/articleviewer.aspx?year=2013\&issue=01000\&article=00069\&type=abstract}, DOI = {10.1097/SCS.0b013e318275ed60}, author = {Krimmel, M and Kluba, S and Breidt, M and Bacher, M and M{\"u}ller-Hagedorn, S and Dietz, K and B{\"u}lthoff, HH and Reinert, s} } @Article { HeydrichDAHBMB2013, title = {Visual capture and the experience of having two bodies: Direct comparison of two virtual reality techniques}, journal = {-}, year = {2013}, month = {1}, department = {Department B{\"u}lthoff}, author = {Heydrich, L and Dodds, T and Aspell, JE and Herbelin, B and B{\"u}lthoff, HH and Mohler, B and Blanke, O} } @Article { YuilleB2012, title = {Action as an innate bias for visual learning}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, year = {2012}, month = {10}, volume = {109}, number = {44}, pages = {17736-17737}, abstract = {Babies are faced at birth with a buzzing blooming confusion of visual stimuli (1). The set of all possible images is truly enormous (2), and simple calculations suggest that only a small fraction of all possible images have ever been seen over the entire history and prehistory of mankind. Moreover, the world consists of an estimated number of 30,000 objects (3), which occur in more than 1,000 different types of scenes. How can an infant start making sense of the visual world? Detailed models of how infants learn to understand images and the balance between nature and nurture are currently lacking. Studies suggest that visual abilities develop in a stereotyped order (4). In particular, infants appear to be able to perceive motion and detect faces at an early stage of development. They can probably exploit the regularities that motion tends to be smooth in space and time, which also enables them to track image patches. Vision researchers have also demonstrated that many vertebrates and insects rely heavily on motion perception for surviving in this complex visual world, e.g., for camouflage breaking or figure ground separation (5, 6), and there are computational models that relate to neural circuitry (7).}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/109/44/17736.full.pdf+html}, DOI = {10.1073/pnas.1215851109}, author = {Yuille, AL and B{\"u}lthoff, HH} } @Article { FranchiSSBR2012, title = {Bilateral Teleoperation of Groups of Mobile Robots with Time-Varying Topology}, journal = {IEEE Transaction on Robotics}, year = {2012}, month = {10}, volume = {28}, number = {5}, pages = {1019-1033}, abstract = {In this paper, a novel decentralized control strategy for bilaterally teleoperating heterogeneous groups of mobile robots from different domains (aerial, ground, marine, and underwater) is proposed. By using a decentralized control architecture, the group of robots, which is treated as the slave side, is made able to navigate in a cluttered environment while avoiding obstacles, interrobot collisions, and following the human motion commands. Simultaneously, the human operator acting on the master side is provided with a suitable force feedback informative of the group response and of the interaction with the surrounding environment. Using passivity-based techniques, we allow the behavior of the group to be as flexible as possible with arbitrary split and join events (e.g., due to interrobot visibility/packet losses or specific task requirements) while guaranteeing the stability of the system. We provide a rigorous analysis of the system stability and steady-state characteristics and validate performance through human/hardware-in-the-loop simulations by considering a heterogeneous fleet of unmanned aerial vehicles (UAVs) and unmanned ground vehicles as a case study. Finally, we also provide an experimental validation with four quadrotor UAVs.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012e-FraSecSonBueRob.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6199993}, DOI = {10.1109/TRO.2012.2196304}, author = {Franchi, A and Secchi, C and Son, HI and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Article { PrettoBRB2012, title = {Foggy perception slows us down}, journal = {eLife}, year = {2012}, month = {10}, volume = {1}, pages = {1-12}, abstract = {Visual speed is believed to be underestimated at low contrast, which has been proposed as an explanation of excessive driving speed in fog. Combining psychophysics measurements and driving simulation, we confirm that speed is underestimated when contrast is reduced uniformly for all objects of the visual scene independently of their distance from the viewer. However, we show that when contrast is reduced more for distant objects, as is the case in real fog, visual speed is actually overestimated, prompting drivers to decelerate. Using an artificial anti-fog—that is, fog characterized by better visibility for distant than for close objects, we demonstrate for the first time that perceived speed depends on the spatial distribution of contrast over the visual scene rather than the global level of contrast per se. Our results cast new light on how reduced visibility conditions affect perceived speed, providing important insight into the human visual system.}, department = {Department B{\"u}lthoff}, web_url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3479833/}, DOI = {10.7554/eLife.00031}, EPUB = {e00281}, author = {Pretto, P and Bresciani, J-P and Rainer, G and B{\"u}lthoff, HH} } @Article { FranchiMGRBR2012, title = {Modeling and Control of UAV Bearing-Formations with Bilateral High-Level Steering}, journal = {International Journal of Robotics Research}, year = {2012}, month = {10}, volume = {31}, number = {12}, pages = {1504-1525}, abstract = {In this paper we address the problem of controlling the motion of a group of unmanned aerial vehicles (UAVs) bound to keep a formation defined in terms of only relative angles (i.e. a bearing formation). This problem can naturally arise within the context of several multi-robot applications such as, e.g. exploration, coverage, and surveillance. First, we introduce and thoroughly analyze the concept and properties of bearing formations, and provide a class of minimally linear sets of bearings sufficient to uniquely define such formations. We then propose a bearing-only formation controller requiring only bearing measurements, converging almost globally, and maintaining bounded inter-agent distances despite the lack of direct metric information. The controller still leaves the possibility of imposing group motions tangent to the current bearing formation. These can be either autonomously chosen by the robots because of any additional task (e.g. exploration), or exploited by an assisting human co-operator. For this latter ‘human-in-the-loop’ case, we propose a multi-master/multi-slave bilateral shared control system providing the co-operator with some suitable force cues informative of the UAV performance. The proposed theoretical framework is extensively validated by means of simulations and experiments with quadrotor UAVs equipped with onboard cameras. Practical limitations, e.g. limited field-of-view, are also considered.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012q-FraMasGraRylBueRob-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ijr.sagepub.com/content/early/2012/10/05/0278364912462493.full.pdf+html}, DOI = {10.1177/0278364912462493}, author = {Franchi, A and Masone, C and Grabe, V and Ryll, M and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Article { BiegBBC2012, title = {Looking for Discriminating Is Different from Looking for Looking's Sake}, journal = {PLoS ONE}, year = {2012}, month = {9}, volume = {7}, number = {9}, pages = {1-9}, abstract = {Recent studies provide evidence for task-specific influences on saccadic eye movements. For instance, saccades exhibit higher peak velocity when the task requires coordinating eye and hand movements. The current study shows that the need to process task-relevant visual information at the saccade endpoint can be, in itself, sufficient to cause such effects. In this study, participants performed a visual discrimination task which required a saccade for successful completion. We compared the characteristics of these task-related saccades to those of classical target-elicited saccades, which required participants to fixate a visual target without performing a discrimination task. The results show that task-related saccades are faster and initiated earlier than target-elicited saccades. Differences between both saccade types are also noted in their saccade reaction time distributions and their main sequences, i.e., the relationship between saccade velocity, duration, and amplitude.}, department = {Department B{\"u}lthoff}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=409E420397B230BE376365245B458D2A?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pone.0045445\&representation=PDF}, DOI = {10.1371/journal.pone.0045445}, EPUB = {e45445}, author = {Bieg, H-J and Bresciani, J-P and B{\"u}lthoff, HH and Chuang, LL} } @Article { FranchiSRBR2012, title = {Shared Control: Balancing Autonomy and Human Assistance with a Group of Quadrotor UAVs}, journal = {IEEE Robotics \& Automation Magazine}, year = {2012}, month = {9}, volume = {19}, number = {3}, pages = {57-68}, abstract = {Robustness and flexibility constitute the main advantages of multiple-robot systems with respect to single-robot ones as per the recent literature. The use of multiple unmanned aerial vehicles (UAVs) combines these benefits with the agility and pervasiveness of aerial platforms [1], [2]. The degree of autonomy of the multi-UAV system should be tuned according to the specificities of the situation under consideration. For regular missions, fully autonomous UAV systems are often appropriate, but, in general, the use of semiautonomous groups of UAVs, supervised or partially controlled by one or more human operators, is the only viable solution to deal with the complexity and unpredictability of real-world scenarios as in, e.g., the case of search and rescue missions or exploration of large/cluttered environments [3]. In addition, the human presence is also mandatory for taking the responsibility of critical decisions in high-risk situations [4].}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012f-FraSecRylBueRob-preprint_01.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=\&arnumber=6290692\&contentType=Journals+\%26+Magazines\&sortType\%3Dasc_p_Sequence\%26filter\%3DAND\%28p_IS_Number\%3A6299141\%29}, DOI = {10.1109/MRA.2012.2205625}, author = {Franchi, A and Secchi, C and Ryll, M and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Article { StreuberMBd2012, title = {The Influence of Visual Information on the Motor Control of Table Tennis Strokes}, journal = {Presence}, year = {2012}, month = {9}, volume = {21}, number = {3}, pages = {281-294}, abstract = {Theories of social interaction (i.e., common coding theory) suggest that visual information about the interaction partner is critical for successful interpersonal action coordination. Seeing the interaction partner allows an observer to understand and predict the interaction partner's behavior. However, it is unknown which of the many sources of visual information about an interaction partner (e.g., body, end effectors, and/or interaction objects) are used for action understanding and thus for the control of movements in response to observed actions. We used a novel immersive virtual environment to investigate this further. Specifically, we asked participants to perform table tennis strokes in response to table tennis balls stroked by a virtual table tennis player. We tested the effect of the visibility of the ball, the paddle, and the body of the virtual player on task performance and movement kinematics. Task performance was measured as the minimum distance between the center of the paddle and the center of the ball (radial error). Movement kinematics was measured as variability in the paddle speed of repeatedly executed table tennis strokes (stroke speed variability). We found that radial error was reduced when the ball was visible compared to invisible. However, seeing the body and/or the racket of the virtual players only reduced radial error when the ball was invisible. There was no influence of seeing the ball on stroke speed variability. However, we found that stroke speed variability was reduced when either the body or the paddle of the virtual player was visible. Importantly, the differences in stroke speed variability were largest in the moment when the virtual player hit the ball. This suggests that seeing the virtual player's body or paddle was important for preparing the stroke response. These results demonstrate for the first time that the online control of arm movements is coupled with visual body information about an opponent.}, department = {Department B{\"u}lthoff}, web_url = {http://www.mitpressjournals.org/doi/abs/10.1162/PRES_a_00113}, DOI = {10.1162/PRES_a_00113}, author = {Streuber, S and Mohler, BJ and B{\"u}lthoff, HH and de la Rosa, S} } @Article { SoykaRBB2011, title = {Modeling direction discrimination thresholds for yaw rotations around an earth-vertical axis for arbitrary motion profiles}, journal = {Experimental Brain Research}, year = {2012}, month = {7}, volume = {220}, number = {1}, pages = {89-99}, abstract = {Understanding the dynamics of vestibular perception is important, for example, for improving the realism of motion simulation and virtual reality environments or for diagnosing patients suffering from vestibular problems. Previous research has found a dependence of direction discrimination thresholds for rotational motions on the period length (inverse frequency) of a transient (single cycle) sinusoidal acceleration stimulus. However, self-motion is seldom purely sinusoidal, and up to now, no models have been proposed that take into account non-sinusoidal stimuli for rotational motions. In this work, the influence of both the period length and the specific time course of an inertial stimulus is investigated. Thresholds for three acceleration profile shapes (triangular, sinusoidal, and trapezoidal) were measured for three period lengths (0.3, 1.4, and 6.7 s) in ten participants. A two-alternative forced-choice discrimination task was used where participants had to judge if a yaw rotation around an earth-vertical axis was leftward or rightward. The peak velocity of the stimulus was varied, and the threshold was defined as the stimulus yielding 75 \% correct answers. In accordance with previous research, thresholds decreased with shortening period length (from \verb=~=2 deg/s for 6.7 s to \verb=~=0.8 deg/s for 0.3 s). The peak velocity was the determining factor for discrimination: Different profiles with the same period length have similar velocity thresholds. These measurements were used to fit a novel model based on a description of the firing rate of semi-circular canal neurons. In accordance with previous research, the estimates of the model parameters suggest that velocity storage does not influence perceptual thresholds.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/h72677r65r8p3g0u/fulltext.pdf}, DOI = {10.1007/s00221-012-3120-x}, author = {Soyka, F and Robuffo Giordano, P and Barnett-Cowan, M and B{\"u}lthoff, HH} } @Article { BarnettCowanRB2012, title = {Persistent perceptual delay for head movement onset relative to auditory stimuli of different durations and rise times}, journal = {Experimental Brain Research}, year = {2012}, month = {7}, volume = {220}, number = {1}, pages = {41-50}, abstract = {The perception of simultaneity between auditory and vestibular information is crucially important for maintaining a coherent representation of the acoustic environment whenever the head moves. It has been recently reported, however, that despite having similar transduction latencies, vestibular stimuli are perceived significantly later than auditory stimuli when simultaneously generated. This suggests that perceptual latency of a head movement is longer than a co-occurring sound. However, these studies paired a vestibular stimulation of long duration (\verb=~=1 s) and of a continuously changing temporal envelope with a brief (10–50 ms) sound pulse. In the present study, the stimuli were matched for temporal envelope duration and shape. Participants judged the temporal order of the two stimuli, the onset of an active head movement and the onset of brief (50 ms) or long (1,400 ms) sounds with a square- or raised-cosine-shaped envelope. Consistent with previous reports, head movement onset had to precede the onset of a brief sound by about 73 ms in order for the stimuli to be perceived as simultaneous. Head movements paired with long square sounds (\verb=~=100 ms) were not significantly different than brief sounds. Surprisingly, head movements paired with long raised-cosine sound (\verb=~=115 ms) had to be presented even earlier than brief stimuli. This additional lead time could not be accounted for by differences in the comparison stimulus characteristics (temporal envelope duration and shape). Rather, differences between sound conditions were found to be attributable to variability in the time for head movement to reach peak velocity: the head moved faster when paired with a brief sound. The persistent lead time required for vestibular stimulation provides further evidence that the perceptual latency of vestibular stimulation is greater than the other senses.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/2q0453017814jm13/fulltext.pdf}, DOI = {10.1007/s00221-012-3112-x}, author = {Barnett-Cowan, M and Raeder, SM and B{\"u}lthoff, HH} } @Article { McDonnellBB2012, title = {Render me Real? Investigating the Effect of Render Style on the Perception of Animated Virtual Humans}, journal = {ACM Transactions on Graphics}, year = {2012}, month = {7}, volume = {31}, number = {4: SIGGRAPH 2012 Conference Proceedings}, pages = {91: 1-11}, abstract = {The realistic depiction of lifelike virtual humans has been the goal of many movie makers in the last decade. Recently, films such as Tron: Legacy and The Curious Case of Benjamin Button have produced highly realistic characters. In the real-time domain, there is also a need to deliver realistic virtual characters, with the increase in popularity of interactive drama video games (such as L.A. Noire™ or Heavy Rain™). There have been mixed reactions from audiences to lifelike characters used in movies and games, with some saying that the increased realism highlights subtle imperfections, which can be disturbing. Some developers opt for a stylized rendering (such as cartoon-shading) to avoid a negative reaction [Thompson 2004]. In this paper, we investigate some of the consequences of choosing realistic or stylized rendering in order to provide guidelines for developers for creating appealing virtual characters. We conducted a series of psychophysical experiments to determine whether render style affects how virtual humans are perceived. Motion capture with synchronized eye-tracked data was used throughout to animate custom-made virtual model replicas of the captured actors.}, department = {Department B{\"u}lthoff}, web_url = {http://s2012.siggraph.org/attendees/sessions/100-71}, DOI = {10.1145/2185520.2185587}, author = {McDonnell, R and Breidt, M and B{\"u}lthoff, HH} } @Article { NethSEKBM2011_2, title = {Velocity-Dependent Dynamic Curvature Gain for Redirected Walking}, journal = {IEEE Transactions on Visualization and Computer Graphics}, year = {2012}, month = {7}, volume = {18}, number = {7}, pages = {1041-1052}, abstract = {Redirected walking techniques allow people to walk in a larger virtual space than the physical extents of the laboratory. We describe two experiments conducted to investigate human sensitivity to walking on a curved path and to validate a new redirected walking technique. In a psychophysical experiment, we found that sensitivity to walking on a curved path was significantly lower for slower walking speeds (radius of 10 m versus 22 m). In an applied study, we investigated the influence of a velocity-dependent dynamic gain controller and an avatar controller on the average distance that participants were able to freely walk before needing to be reoriented. The mean walked distance was significantly greater in the dynamic gain controller condition, as compared to the static controller (22 m versus 15 m). Our results demonstrate that perceptually motivated dynamic redirected walking techniques, in combination with reorientation techniques, allow for unaided exploration of a large virtual city model.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/TVCG_Neth_Manuscript_revised.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.computer.org/portal/web/csdl/doi/10.1109/TVCG.2011.275}, DOI = {10.1109/TVCG.2011.275}, author = {Neth, CT and Souman, JL and Engel, D and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Article { ChuangVB2012_2, title = {Learned non-rigid object motion is a view-invariant cue to recognizing novel objects}, journal = {Frontiers in Computational Neuroscience}, year = {2012}, month = {5}, volume = {6}, number = {26}, pages = {1-8}, abstract = {There is evidence that observers use learned object motion to recognize objects. For instance, studies have shown that reversing the learned direction in which a rigid object rotated in depth impaired recognition accuracy. This motion reversal can be achieved by playing animation sequences of moving objects in reverse frame order. In the current study, we used this sequence-reversal manipulation to investigate whether observers encode the motion of dynamic objects in visual memory, and whether such dynamic representations are encoded in a way that is dependent on the viewing conditions. Participants first learned dynamic novel objects, presented as animation sequences. Following learning, they were then tested on their ability to recognize these learned objects when their animation sequence was shown in the same sequence order as during learning or in the reverse sequence order. In Experiment 1, we found that non-rigid motion contributed to recognition performance; that is, sequence-reversal decreased sensitivity across different tasks. In subsequent experiments, we tested the recognition of non-rigidly deforming (Experiment 2) and rigidly rotating (Experiment 3) objects across novel viewpoints. Recognition performance was affected by viewpoint changes for both experiments. Learned non-rigid motion continued to contribute to recognition performance and this benefit was the same across all viewpoint changes. By comparison, learned rigid motion did not contribute to recognition performance. These results suggest that non-rigid motion provides a source of information for recognizing dynamic objects, which is not affected by changes to viewpoint.}, department = {Department B{\"u}lthoff}, web_url = {http://www.frontiersin.org/Journal/DownloadFile.ashx?pdf=1\&FileId=\%2062343\&articleId=\%2022441\&Version=\%201\&ContentTypeId=21\&FileName=\%20fncom-06-00026.pdf}, DOI = {10.3389/fncom.2012.00026}, author = {Chuang, LL and Vuong, QC and B{\"u}lthoff, HH} } @Article { BarnettCowanMVTB2011, title = {MPI CyberMotion Simulator: Implementation of a Novel Motion Simulator to Investigate Multisensory Path Integration in Three Dimensions}, journal = {Journal of Visualized Experiments}, year = {2012}, month = {5}, volume = {63}, number = {5}, pages = {1-6}, abstract = {Path integration is a process in which self-motion is integrated over time to obtain an estimate of one's current position relative to a starting point 1. Humans can do path integration based exclusively on visual 2-3, auditory 4, or inertial cues 5. However, with multiple cues present, inertial cues - particularly kinaesthetic - seem to dominate 6-7. In the absence of vision, humans tend to overestimate short distances (<5 m) and turning angles (<30\(^{\circ}\)), but underestimate longer ones 5. Movement through physical space therefore does not seem to be accurately represented by the brain. Extensive work has been done on evaluating path integration in the horizontal plane, but little is known about vertical movement (see 3 for virtual movement from vision alone). One reason for this is that traditional motion simulators have a small range of motion restricted mainly to the horizontal plane. Here we take advantage of a motion simulator 8-9 with a large range of motion to assess whether path integration is similar between horizontal and vertical planes. The relative contributions of inertial and visual cues for path navigation were also assessed. 16 observers sat upright in a seat mounted to the flange of a modified KUKA anthropomorphic robot arm. Sensory information was manipulated by providing visual (optic flow, limited lifetime star field), vestibular-kinaesthetic (passive self motion with eyes closed), or visual and vestibular-kinaesthetic motion cues. Movement trajectories in the horizontal, sagittal and frontal planes consisted of two segment lengths (1st: 0.4 m, 2nd: 1 m; ±0.24 m/s2 peak acceleration). The angle of the two segments was either 45\(^{\circ}\) or 90\(^{\circ}\). Observers pointed back to their origin by moving an arrow that was superimposed on an avatar presented on the screen. Observers were more likely to underestimate angle size for movement in the horizontal plane compared to the vertical planes. In the frontal plane observers were more likely to overestimate angle size while there was no such bias in the sagittal plane. Finally, observers responded slower when answering based on vestibular-kinaesthetic information alone. Human path integration based on vestibular-kinaesthetic information alone thus takes longer than when visual information is present. That pointing is consistent with underestimating and overestimating the angle one has moved through in the horizontal and vertical planes respectively, suggests that the neural representation of self-motion through space is non-symmetrical which may relate to the fact that humans experience movement mostly within the horizontal plane.}, department = {Department B{\"u}lthoff}, web_url = {http://www.jove.com/pdf/default.aspx?PDF=\&ID=3436}, DOI = {10.3791/3436}, EPUB = {e3436}, author = {Barnett-Cowan, M and Meilinger, T and Vidal, M and Teufel, H and B{\"u}lthoff, HH} } @Article { CamposBB2012, title = {Multisensory integration in the estimation of walked distances}, journal = {Experimental Brain Research}, year = {2012}, month = {5}, volume = {218}, number = {4}, pages = {551-565}, abstract = {When walking through space, both dynamic visual information (optic flow) and body-based information (proprioceptive and vestibular) jointly specify the magnitude of distance travelled. While recent evidence has demonstrated the extent to which each of these cues can be used independently, less is known about how they are integrated when simultaneously present. Many studies have shown that sensory information is integrated using a weighted linear sum, yet little is known about whether this holds true for the integration of visual and body-based cues for travelled distance perception. In this study using Virtual Reality technologies, participants first travelled a predefined distance and subsequently matched this distance by adjusting an egocentric, in-depth target. The visual stimulus consisted of a long hallway and was presented in stereo via a head-mounted display. Body-based cues were provided either by walking in a fully tracked free-walking space (Exp. 1) or by being passively moved in a wheelchair (Exp. 2). Travelled distances were provided either through optic flow alone, body-based cues alone or through both cues combined. In the combined condition, visually specified distances were either congruent (1.0\(\times\)) or incongruent (0.7\(\times\) or 1.4\(\times\)) with distances specified by body-based cues. Responses reflect a consistent combined effect of both visual and body-based information, with an overall higher influence of body-based cues when walking and a higher influence of visual cues during passive movement. When comparing the results of Experiments 1 and 2, it is clear that both proprioceptive and vestibular cues contribute to travelled distance estimates during walking. These observed results were effectively described using a basic linear weighting model.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/t37011l884450186/fulltext.pdf}, DOI = {10.1007/s00221-012-3048-1}, author = {Campos, JL and Butler, JS and B{\"u}lthoff, HH} } @Article { NolanBWFBR2011, title = {Neural correlates of oddball detection in self-motion heading: A high-density event-related potential study of vestibular integration}, journal = {Experimental Brain Research}, year = {2012}, month = {5}, volume = {219}, number = {1}, pages = {1-11}, abstract = {The perception of self-motion is a product of the integration of information from both visual and non-visual cues, to which the vestibular system is a central contributor. It is well documented that vestibular dysfunction leads to impaired movement and balance, dizziness and falls, and yet our knowledge of the neuronal processing of vestibular signals remains relatively sparse. In this study, high-density electroencephalographic recordings were deployed to investigate the neural processes associated with vestibular detection of changes in heading. To this end, a self-motion oddball paradigm was designed. Participants were translated linearly 7.8 cm on a motion platform using a one second motion profile, at a 45\(^{\circ}\) angle leftward or rightward of straight ahead. These headings were presented with a stimulus probability of 80–20 \%. Participants responded when they detected the infrequent direction change via button-press. Event-related potentials (ERPs) were calculated in response to the standard (80 \%) and target (20 \%) movement directions. Statistical parametric mapping showed that ERPs to standard and target movements differed significantly from 490 to 950 ms post-stimulus. Topographic analysis showed that this difference had a typical P3 topography. Individual participant bootstrap analysis revealed that 93.3 \% of participants exhibited a clear P3 component. These results indicate that a perceived change in vestibular heading can readily elicit a P3 response, wholly similar to that evoked by oddball stimuli presented in other sensory modalities. This vestibular-evoked P3 response may provide a readily and robustly detectable objective measure for the evaluation of vestibular integrity in various disease models.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/a574525416v829w4/fulltext.pdf}, DOI = {10.1007/s00221-012-3059-y}, author = {Nolan, H and Butler, JS and Whelan, R and Foxe, JJ and B{\"u}lthoff, HH and Reilly, RB} } @Article { FischerLBB2011, title = {Visual Motion Responses in the Posterior Cingulate Sulcus: A Comparison to V5/MT and MST}, journal = {Cerebral Cortex}, year = {2012}, month = {4}, volume = {22}, number = {4}, pages = {865-876}, abstract = {Motion processing regions apart from V5+/MT+ are still relatively poorly understood. Here, we used functional magnetic resonance imaging to perform a detailed functional analysis of the recently described cingulate sulcus visual area (CSv) in the dorsal posterior cingulate cortex. We used distinct types of visual motion stimuli to compare CSv with V5/MT and MST, including a visual pursuit paradigm. Both V5/MT and MST preferred 3D flow over 2D planar motion, responded less yet substantially to random motion, had a strong preference for contralateral versus ipsilateral stimulation, and responded nearly equally to contralateral and to full-field stimuli. In contrast, CSv had a pronounced preference to 2D planar motion over 3D flow, did not respond to random motion, had a weak and nonsignificant lateralization that was significantly smaller than that of MST, and strongly preferred full-field over contralateral stimuli. In addition, CSv had a better capability to integrate eye movements with retinal motion compared with V5/MT and MST. CSv thus differs from V5+/MT+ by its unique preference to full-field, coherent, and planar motion cues. These results place CSv in a good position to process visual cues related to self-induced motion, in particular those associated to eye or lateral head movements.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://cercor.oxfordjournals.org/content/22/4/865.full.pdf+html}, DOI = {10.1093/cercor/bhr154}, author = {Fischer, E and Logothetis, NK and B{\"u}lthoff, HH and Bartels, A} } @Article { FischerBLB2012, title = {Human Areas V3A and V6 Compensate for Self-Induced Planar Visual Motion}, journal = {Neuron}, year = {2012}, month = {3}, volume = {73}, number = {6}, pages = {1228-1240}, abstract = {Little is known about mechanisms mediating a stable perception of the world during pursuit eye movements. Here, we used fMRI to determine to what extent human motion-responsive areas integrate planar retinal motion with nonretinal eye movement signals in order to discard self-induced planar retinal motion and to respond to objective (“real”) motion. In contrast to other areas, V3A lacked responses to self-induced planar retinal motion but responded strongly to head-centered motion, even when retinally canceled by pursuit. This indicates a near-complete multimodal integration of visual with nonvisual planar motion signals in V3A. V3A could be mapped selectively and robustly in every single subject on this basis. V6 also reported head-centered planar motion, even when 3D flow was added to it, but was suppressed by retinal planar motion. These findings suggest a dominant contribution of human areas V3A and V6 to head-centered motion perception and to perceptual stability during eye movements.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.sciencedirect.com/science/article/pii/S0896627312001407}, DOI = {10.1016/j.neuron.2012.01.022}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Article { KaulardCBW2012, title = {The MPI Facial Expression Database: A Validated Database of Emotional and Conversational Facial Expressions}, journal = {PLoS One}, year = {2012}, month = {3}, volume = {7}, number = {3}, pages = {1-18}, abstract = {The ability to communicate is one of the core aspects of human life. For this, we use not only verbal but also nonverbal signals of remarkable complexity. Among the latter, facial expressions belong to the most important information channels. Despite the large variety of facial expressions we use in daily life, research on facial expressions has so far mostly focused on the emotional aspect. Consequently, most databases of facial expressions available to the research community also include only emotional expressions, neglecting the largely unexplored aspect of conversational expressions. To fill this gap, we present the MPI facial expression database, which contains a large variety of natural emotional and conversational expressions. The database contains 55 different facial expressions performed by 19 German participants. Expressions were elicited with the help of a method-acting protocol, which guarantees both well-defined and natural facial expressions. The method-acting protocol was based on every-day scenarios, which are used to define the necessary context information for each expression. All facial expressions are available in three repetitions, in two intensities, as well as from three different camera angles. A detailed frame annotation is provided, from which a dynamic and a static version of the database have been created. In addition to describing the database in detail, we also present the results of an experiment with two conditions that serve to validate the context scenarios as well as the naturalness and recognizability of the video sequences. Our results provide clear evidence that conversational expressions can be recognized surprisingly well from visual information alone. The MPI facial expression database will enable researchers from different research fields (including the perceptual and cognitive sciences, but also affective computing, as well as computer vision) to investigate the processing of a wider range of natural facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.plosone.org/article/info\%3Adoi\%2F10.1371\%2Fjournal.pone.0032321}, DOI = {10.1371/journal.pone.0032321}, EPUB = {e32321}, author = {Kaulard, K and Cunningham, DW and B{\"u}lthoff, HH and Wallraven, C} } @Article { FrankensteinMBM2011, title = {Is the Map in Our Head Oriented North?}, journal = {Psychological Science}, year = {2012}, month = {2}, volume = {23}, number = {2}, pages = {120-125}, abstract = {We examined how a highly familiar environmental space—one’s city of residence—is represented in memory. Twenty-six participants faced a photo-realistic virtual model of their hometown and completed a task in which they pointed to familiar target locations from various orientations. Each participant’s performance was most accurate when he or she was facing north, and errors increased as participants’ deviation from a north-facing orientation increased. Pointing errors and latencies were not related to the distance between participants’ initial locations and the target locations. Our results are inconsistent with accounts of orientation-free memory and with theories assuming that the storage of spatial knowledge depends on local reference frames. Although participants recognized familiar local views in their initial locations, their strategy for pointing relied on a single, north-oriented reference frame that was likely acquired from maps rather than experience from daily exploration. Even though participants had spent significantly more time navigating the city than looking at maps, their pointing behavior seemed to rely on a north-oriented mental map.}, department = {Department B{\"u}lthoff}, web_url = {http://pss.sagepub.com/content/23/2/120.full.pdf+html}, DOI = {10.1177/0956797611429467}, author = {Frankenstein, J and Mohler, BJ and B{\"u}lthoff, HH and Meilinger, T} } @Article { 4958, title = {From Isovists via Mental Representations to Behaviour: First Steps Toward Closing the Causal Chain}, journal = {Environment and Planning B: Planning and Design}, year = {2012}, month = {1}, volume = {39}, number = {1}, pages = {48-62}, abstract = {This paper addresses the interactions between human wayfinding performance, the mental representation of routes, and the geometrical layout of path intersections. The conclusions of this paper are based on the results of a virtual reality empirical experiment. The study consisted of a route-learning and reproduction task and two choice reaction tasks measuring the acquired knowledge of route decision points. In order to relate the recorded behaviour to the geometry of the environment, a specific adaptation of an isovist-based spatial analysis that accounts for directional bias in human spatial perception and representation was developed. The analyses applied provided conclusive evidence of correspondences between the geometrical properties of environments as captured by isovists and their mental representations.}, department = {Department B{\"u}lthoff}, web_url = {http://www.envplan.com/epb/fulltext/b39/b34048t.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1068/b34048t}, author = {Meilinger, T and Franz, G and B{\"u}lthoff, HH} } @Article { DopjansBW2012, title = {Serial exploration of faces: Comparing vision and touch}, journal = {Journal of Vision}, year = {2012}, month = {1}, volume = {12}, number = {1:6}, pages = {1-14}, abstract = {Even though we can recognize faces by touch surprisingly well, haptic face recognition performance is still worse than for visual exploration. One possibility for this performance difference might be due to different encoding strategies in the two modalities, namely, holistic encoding in vision versus serial encoding in haptics. Here, we tested this hypothesis by promoting serial encoding in vision, using a novel, gaze-restricted display that limited the effective field of view in vision to resemble that of haptic exploration. First, we compared haptic with gaze-restricted and unrestricted visual face recognition. Second, we used the face inversion paradigm to assess how encoding differences might affect processing strategies (featural vs. holistic). By promoting serial encoding in vision, we found equal face recognition performance in vision and haptics with a clear switch from holistic to featural processing, suggesting that performance differences in visual and haptic face recognition are due to modality-specific encoding strategies.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/12/1/6.full.pdf+html}, DOI = {10.1167/12.1.6}, author = {Dopjans, L and B{\"u}lthoff, HH and Wallraven, C} } @Article { FlemingHB2011, title = {Estimation of 3D shape from image orientations}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, year = {2011}, month = {12}, volume = {108}, number = {51}, pages = {20438-20443}, abstract = {One of the main functions of vision is to estimate the 3D shape of objects in our environment. Many different visual cues, such as stereopsis, motion parallax, and shading, are thought to be involved. One important cue that remains poorly understood comes from surface texture markings. When a textured surface is slanted in 3D relative to the observer, the surface patterns appear compressed in the retinal image, providing potentially important information about 3D shape. What is not known, however, is how the brain actually measures this information from the retinal image. Here, we explain how the key information could be extracted by populations of cells tuned to different orientations and spatial frequencies, like those found in the primary visual cortex. To test this theory, we created stimuli that selectively stimulate such cell populations, by “smearing” (filtering) images of 2D random noise into specific oriented patterns. We find that the resulting patterns appear vividly 3D, and that increasing the strength of the orientation signals progressively increases the sense of 3D shape, even though the filtering we apply is physically inconsistent with what would occur with a real object. This finding suggests we have isolated key mechanisms used by the brain to estimate shape from texture. Crucially, we also find that adapting the visual system's orientation detectors to orthogonal patterns causes unoriented random noise to look like a specific 3D shape. Together these findings demonstrate a crucial role of orientation detectors in the perception of 3D shape.}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/108/51/20438.full.pdf+html}, DOI = {10.1073/pnas.1114619109}, author = {Fleming, RW and Holtmann-Rice, D and B{\"u}lthoff, HH} } @Article { SoumanRSFTUDBE2011, title = {CyberWalk: Enabling unconstrained omnidirectional walking through virtual environments}, journal = {ACM Transactions on Applied Perception}, year = {2011}, month = {11}, volume = {8}, number = {4:25}, pages = {1-22}, abstract = {Despite many recent developments in Virtual Reality, an effective locomotion interface which allows for normal walking through large virtual environments was still lacking until recently. Here, we describe the new CyberWalk omnidirectional treadmill system, which makes it possible for users to walk endlessly in any direction, while never leaving the confines of the limited walking surface. The treadmill system improves on previous designs, both in its mechanical features and in the control system employed to keep users close to the centre of the treadmill. As a result, users are able to start walking, vary their walking speed and direction, and stop walking like they would on a normal, stationary surface. The treadmill system was validated in two experiments, in which both the walking behaviour and the performance in a basic spatial updating task were compared to that during normal overground walking. The results suggest that walking on the CyberWalk treadmill is very close to normal walking, especially after some initial familiarization. Moreover, we did not find a detrimental effect of treadmill walking in the spatial updating task. The CyberWalk system constitutes a significant step forward to bringing the real world into the laboratory or workplace.}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://dl.acm.org/citation.cfm?id=2043607\&dl=ACM\&coll=DL\&CFID=62552168\&CFTOKEN=60220994}, DOI = {10.1145/2043603.2043607}, author = {Souman, JL and Robuffo Giordano, P and Schwaiger, M and Frissen, I and Th{\"u}mmel, T and Ulbrich, H and De Luca, A and B{\"u}lthoff, HH and Ernst, M} } @Article { DahlLBW2011, title = {Second-Order Relational Manipulations Affect Both Humans and Monkeys}, journal = {PLoS One}, year = {2011}, month = {10}, volume = {6}, number = {10}, pages = {1-7}, abstract = {Recognition and individuation of conspecifics by their face is essential for primate social cognition. This ability is driven by a mechanism that integrates the appearance of facial features with subtle variations in their configuration (i.e., second-order relational properties) into a holistic representation. So far, there is little evidence of whether our evolutionary ancestors show sensitivity to featural spatial relations and hence holistic processing of faces as shown in humans. Here, we directly compared macaques with humans in their sensitivity to configurally altered faces in upright and inverted orientations using a habituation paradigm and eye tracking technologies. In addition, we tested for differences in processing of conspecific faces (human faces for humans, macaque faces for macaques) and non-conspecific faces, addressing aspects of perceptual expertise. In both species, we found sensitivity to second-order relational properties for conspecific (expert) faces, when presented in upright, not in inverted, orientation. This shows that macaques possess the requirements for holistic processing, and thus show similar face processing to that of humans.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=479810543A9D0DDB1F0DBC45F84CA66C.ambra02?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pone.0025793\&representation=PDF}, DOI = {10.1371/journal.pone.0025793}, EPUB = {e25793}, author = {Dahl, CD and Logothetis, NK and B{\"u}lthoff, HH and Wallraven, C} } @Article { DoddsMB2011, title = {Talk to the Virtual Hands: Self-Animated Avatars Improve Communication in Head-Mounted Display Virtual Environments}, journal = {PLoS One}, year = {2011}, month = {10}, volume = {6}, number = {10}, pages = {1-12}, abstract = {Background When we talk to one another face-to-face, body gestures accompany our speech. Motion tracking technology enables us to include body gestures in avatar-mediated communication, by mapping one's movements onto one's own 3D avatar in real time, so the avatar is self-animated. We conducted two experiments to investigate (a) whether head-mounted display virtual reality is useful for researching the influence of body gestures in communication; and (b) whether body gestures are used to help in communicating the meaning of a word. Participants worked in pairs and played a communication game, where one person had to describe the meanings of words to the other. Principal Findings In experiment 1, participants used significantly more hand gestures and successfully described significantly more words when nonverbal communication was available to both participants (i.e. both describing and guessing avatars were self-animated, compared with both avatars in a static neutral pose). Participants ‘passed’ (gave up describing) significantly more words when they were talking to a static avatar (no nonverbal feedback available). In experiment 2, participants' performance was significantly worse when they were talking to an avatar with a prerecorded listening animation, compared with an avatar animated by their partners' real movements. In both experiments participants used significantly more hand gestures when they played the game in the real world. Conclusions Taken together, the studies show how (a) virtual reality can be used to systematically study the influence of body gestures; (b) it is important that nonverbal communication is bidirectional (real nonverbal feedback in addition to nonverbal communication from the describing participant); and (c) there are differences in the amount of body gestures that participants use with and without the head-mounted display, and we discuss possible explanations for this and ideas for future investigation.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/Dodds-TalktotheVirtualHands-PLoSOne-2011.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=BB8DF7295C39A064E5FFC9839EC935BD.ambra01?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pone.0025759\&representation=PDF}, DOI = {10.1371/journal.pone.0025759}, EPUB = {e25759}, author = {Dodds, TJ and Mohler, BJ and B{\"u}lthoff, HH} } @Article { StreuberKSBd2011, title = {The effect of social context on the use of visual information}, journal = {Experimental Brain Research}, year = {2011}, month = {10}, volume = {214}, number = {2}, pages = {273-284}, abstract = {Social context modulates action kinematics. Less is known about whether social context also affects the use of task relevant visual information. We tested this hypothesis by examining whether the instruction to play table tennis competitively or cooperatively affected the kind of visual cues necessary for successful table tennis performance. In two experiments, participants played table tennis in a dark room with only the ball, net, and table visible. Visual information about both players’ actions was manipulated by means of self-glowing markers. We recorded the number of successful passes for each player individually. The results showed that participants’ performance increased when their own body was rendered visible in both the cooperative and the competitive condition. However, social context modulated the importance of different sources of visual information about the other player. In the cooperative condition, seeing the other player’s racket had the largest effects on performance increase, whereas in the competitive condition, seeing the other player’s body resulted in the largest performance increase. These results suggest that social context selectively modulates the use of visual information about others’ actions in social interactions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/b014430023h47417/fulltext.pdf}, DOI = {10.1007/s00221-011-2830-9}, author = {Streuber, S and Knoblich, G and Sebanz, N and B{\"u}lthoff, HH and de la Rosa, S} } @Article { SchomakerTBB2011, title = {It is all me: the effect of viewpoint on visual–vestibular recalibration}, journal = {Experimental Brain Research}, year = {2011}, month = {9}, volume = {243}, number = {2-3}, pages = {245-256}, abstract = {Participants performed a visual–vestibular motor recalibration task in virtual reality. The task consisted of keeping the extended arm and hand stable in space during a whole-body rotation induced by a robotic wheelchair. Performance was first quantified in a pre-test in which no visual feedback was available during the rotation. During the subsequent adaptation phase, optical flow resulting from body rotation was provided. This visual feedback was manipulated to create the illusion of a smaller rotational movement than actually occurred, hereby altering the visual–vestibular mapping. The effects of the adaptation phase on hand stabilization performance were measured during a post-test that was identical to the pre-test. Three different groups of subjects were exposed to different perspectives on the visual scene, i.e., first-person, top view, or mirror view. Sensorimotor adaptation occurred for all three viewpoint conditions, performance in the post-test session showing a marked under-compensation relative to the pre-test performance. In other words, all viewpoints gave rise to a remapping between vestibular input and the motor output required to stabilize the arm. Furthermore, the first-person and mirror view adaptation induced a significant decrease in variability of the stabilization performance. Such variability reduction was not observed for the top view adaptation. These results suggest that even if all three viewpoints can evoke substantial adaptation aftereffects, the more naturalistic first-person view and the richer mirror view should be preferred when reducing motor variability constitutes an important issue.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/d195u587t5141836/fulltext.pdf}, DOI = {10.1007/s00221-011-2723-y}, author = {Schomaker, J and Tesch, J and B{\"u}lthoff, HH and Bresciani, JP} } @Article { GaissertBW2011, title = {Similarity and categorization: From vision to touch}, journal = {Acta Psychologica}, year = {2011}, month = {9}, volume = {138}, number = {1}, pages = {219-230}, abstract = {Even though human perceptual development relies on combining multiple modalities, most categorization studies so far have focused on the visual modality. To better understand the mechanisms underlying multisensory categorization, we analyzed visual and haptic perceptual spaces and compared them with human categorization behavior. As stimuli we used a three-dimensional object space of complex, parametrically-defined objects. First, we gathered similarity ratings for all objects and analyzed the perceptual spaces of both modalities using multidimensional scaling analysis. Next, we performed three different categorization tasks which are representative of every-day learning scenarios: in a fully unconstrained task, objects were freely categorized, in a semi-constrained task, exactly three groups had to be created, whereas in a constrained task, participants received three prototype objects and had to assign all other objects accordingly. We found that the haptic modality was on par with the visual modality both in recovering the topology of the physical space and in solving the categorization tasks. We also found that within-category similarity was consistently higher than across-category similarity for all categorization tasks and thus show how perceptual spaces based on similarity can explain visual and haptic object categorization. Our results suggest that both modalities employ similar processes in forming categories of complex objects.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MiamiImageURL\&_cid=272045\&_user=29041\&_pii=S0001691811001302\&_check=y\&_origin=\&_coverDate=30-Sep-2011\&view=c\&wchp=dGLbVBA-zSkzk\&md5=8320348e946ed057a766d4d041954797/1-s2.0-S0001691811001302-main.pdf}, DOI = {10.1016/j.actpsy.2011.06.007}, author = {Gaissert, N and B{\"u}lthoff, HH and Wallraven, C} } @Article { ButlerCBS2011, title = {The Role of Stereo Vision in Visual-Vestibular Integration}, journal = {Seeing and Perceiving}, year = {2011}, month = {9}, volume = {24}, number = {5}, pages = {453-470}, abstract = {Self-motion through an environment stimulates several sensory systems, including the visual system and the vestibular system. Recent work in heading estimation has demonstrated that visual and vestibular cues are typically integrated in a statistically optimal manner, consistent with Maximum Likelihood Estimation predictions. However, there has been some indication that cue integration may be affected by characteristics of the visual stimulus. Therefore, the current experiment evaluated whether presenting optic flow stimuli stereoscopically, or presenting both eyes with the same image (binocularly) affects combined visual-vestibular heading estimates. Participants performed a two-interval forced-choice task in which they were asked which of two presented movements was more rightward. They were presented with either visual cues alone, vestibular cues alone or both cues combined. Measures of reliability were obtained for both binocular and stereoscopic conditions. Group level analyses demonstrated that when stereoscopic information was available there was clear evidence of optimal integration, yet when only binocular information was available weaker evidence of cue integration was observed. Exploratory individual analyses demonstrated that for the stereoscopic condition 90\% of participants exhibited optimal integration, whereas for the binocular condition only 60\% of participants exhibited results consistent with optimal integration. Overall, these findings suggest that stereo vision may be important for self-motion perception, particularly under combined visual-vestibular conditions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.ingentaconnect.com/content/brill/sp/2011/00000024/00000005/art00002}, DOI = {10.1163/187847511X588070}, author = {Butler, JS and Campos, JL and B{\"u}lthoff, HH and Smith, ST} } @Article { 6789, title = {Contributions of the PPC to online control of visually guided reaching movements assessed with fMRI-guided TMS}, journal = {Cerebral Cortex}, year = {2011}, month = {7}, volume = {21}, number = {7}, pages = {1602-1612}, abstract = {The posterior parietal cortex (PPC) plays an important role in controlling voluntary movements by continuously integrating sensory information about body state and the environment. We tested which subregions of the PPC contribute to the processing of target- and body-related visual information while reaching for an object, using a reaching paradigm with 2 types of visual perturbation: displacement of the visual target and displacement of the visual feedback about the hand position. Initially, functional magnetic resonance imaging (fMRI) was used to localize putative target areas involved in online corrections of movements in response to perturbations. The causal contribution of these areas to online correction was tested in subsequent neuronavigated transcranial magnetic stimulation (TMS) experiments. Robust TMS effects occurred at distinct anatomical sites along the anterior intraparietal sulcus (aIPS) and the anterior part of the supramarginal gyrus for both perturbations. TMS over neighboring sites did not affect online control. Our results support the hypothesis that the aIPS is more generally involved in visually guided control of movements, independent of body effectors and nature of the visual information. Furthermore, they suggest that the human network of PPC subregions controlling goal-directed visuomotor processes extends more inferiorly than previously thought. Our results also point toward a good spatial specificity of the TMS effects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Cerebral-Cortex-2010-Reichenbach_6789[0].pdf}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, web_url = {http://cercor.oxfordjournals.org/content/21/7/1602.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1093/cercor/bhq225}, author = {Reichenbach, A and Bresciani, J-P and Peer, A and B{\"u}lthoff, HH and Thielscher, A} } @Article { RuddleVB2011, title = {Walking improves your cognitive map in environments that are large-scale and large in extent}, journal = {ACM Transactions on Computer-Human Interaction}, year = {2011}, month = {6}, volume = {18}, number = {2:10}, pages = {1-22}, abstract = {This study investigated the effect of body-based information (proprioception, etc.) when participants navigated large-scale virtual marketplaces that were either small (Experiment 1) or large in extent (Experiment 2). Extent refers to the size of an environment, whereas scale refers to whether people have to travel through an environment to see the detail necessary for navigation. Each participant was provided with full body-based information (walking through the virtual marketplaces in a large tracking hall or on an omnidirectional treadmill), just the translational component of body-based information (walking on a linear treadmill, but turning with a joystick), just the rotational component (physically turning but using a joystick to translate) or no body-based information (joysticks to translate and rotate). In large and small environments translational body-based information significantly improved the accuracy of participants' cognitive maps, measured using estimates of direction and relative straight line distance but, on its own, rotational body-based information had no effect. In environments of small extent, full body-based information also improved participants' navigational performance. The experiments show that locomotion devices such as linear treadmills would bring substantial benefits to virtual environment applications where large spaces are navigated, and theories of human navigation need to reconsider the contribution made by body-based information, and distinguish between environmental scale and extent.}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?doid=1970378.1970384}, DOI = {10.1145/1970378.1970384}, author = {Ruddle, RA and Volkova, E and B{\"u}lthoff, HH} } @Article { RuddleVMB2011, title = {The effect of landmark and body-based sensory information on route knowledge}, journal = {Memory \& Cognition}, year = {2011}, month = {5}, volume = {39}, number = {4}, pages = {686-699}, abstract = {Two experiments investigated the effects of landmarks and body-based information on route knowledge. Participants made four out-and-back journeys along a route, guided only on the first outward trip and with feedback every time an error was made. Experiment 1 used 3-D virtual environments (VEs) with a desktop monitor display, and participants were provided with no supplementary landmarks, only global landmarks, only local landmarks, or both global and local landmarks. Local landmarks significantly reduced the number of errors that participants made, but global landmarks did not. Experiment 2 used a head-mounted display; here, participants who physically walked through the VE (translational and rotational body-based information) made 36\% fewer errors than did participants who traveled by physically turning but changing position using a joystick. Overall, the experiments showed that participants were less sure of where to turn than which way, and journey direction interacted with sensory information to affect the number and types of errors participants made.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/12771128x0716033/fulltext.pdf}, DOI = {10.3758/s13421-010-0054-z}, author = {Ruddle, RA and Volkova, E and Mohler, B and B{\"u}lthoff, HH} } @Article { 6849, title = {Perceived Object Stability Depends on Multisensory Estimates of Gravity}, journal = {PLoS ONE}, year = {2011}, month = {4}, volume = {6}, number = {4}, pages = {1-5}, abstract = {Background How does the brain estimate object stability? Objects fall over when the gravity-projected centre-of-mass lies outside the point or area of support. To estimate an object's stability visually, the brain must integrate information across the shape and compare its orientation to gravity. When observers lie on their sides, gravity is perceived as tilted toward body orientation, consistent with a representation of gravity derived from multisensory information. We exploited this to test whether vestibular and kinesthetic information affect this visual task or whether the brain estimates object stability solely from visual information. Methodology/Principal Findings In three body orientations, participants viewed images of objects close to a table edge. We measured the critical angle at which each object appeared equally likely to fall over or right itself. Perceived gravity was measured using the subjective visual vertical. The results show that the perceived critical angle was significantly biased in the same direction as the subjective visual vertical (i.e., towards the multisensory estimate of gravity). Conclusions/Significance Our results rule out a general explanation that the brain depends solely on visual heuristics and assumptions about object stability. Instead, they suggest that multisensory estimates of gravity govern the perceived stability of objects, resulting in objects appearing more stable than they are when the head is tilted in the same direction in which they fall.}, department = {Department B{\"u}lthoff}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=C1AE6461C55EF186CAA1AB710C6E0EAA.ambra02?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pone.0019289\&representation=PDF}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1371/journal.pone.0019289}, EPUB = {e19289}, author = {Barnett-Cowan, M and Fleming, RW and Singh, M and B{\"u}lthoff, HH} } @Article { 6950, title = {Predicting direction detection thresholds for arbitrary translational acceleration profiles in the horizontal plane}, journal = {Experimental Brain Research}, year = {2011}, month = {3}, volume = {209}, number = {1}, pages = {95-107}, abstract = {In previous research, direction detection thresholds have been measured and successfully modeled by exposing participants to sinusoidal acceleration profiles of different durations. In this paper, we present measurements that reveal differences in thresholds depending not only on the duration of the profile, but also on the actual time course of the acceleration. The measurements are further explained by a model based on a transfer function, which is able to predict direction detection thresholds for all types of acceleration profiles. In order to quantify a participant’s ability to detect the direction of motion in the horizontal plane, a four-alternative forced-choice task was implemented. Three types of acceleration profiles (sinusoidal, trapezoidal and triangular) were tested for three different durations (1.5, 2.36 and 5.86 s). To the best of our knowledge, this is the first study which varies both quantities (profile and duration) in a systematic way within a single experiment. The lowest thresholds were found for trapezoidal profiles and the highest for triangular profiles. Simulations for frequencies lower than the ones actually measured predict a change from this behavior: Sinusoidal profiles are predicted to yield the highest thresholds at low frequencies. This qualitative prediction is only possible with a model that is able to predict thresholds for different types of acceleration profiles. Our modeling approach represents an important advancement, because it allows for a more general and accurate description of perceptual thresholds for simple and complex translational motions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/l2086212j6121842/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-010-2523-9}, author = {Soyka, F and Robuffo Giordano, P and Beykirch, K and B{\"u}lthoff, HH} } @Article { 6442, title = {Visual influences on path integration in darkness indicates a multimodal representation of large-scale space}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, year = {2011}, month = {1}, volume = {108}, number = {3}, pages = {1152-1157}, abstract = {Our ability to return to the start of a route recently performed in darkness is thought to reflect path integration of motion-related information. Here we provide evidence that motion-related interoceptive representations (proprioceptive, vestibular, and motor efference copy) combine with visual representations to form a single multimodal representation guiding navigation. We used immersive virtual reality to decouple visual input from motion-related interoception by manipulating the rotation or translation gain of the visual projection. First, participants walked an outbound path with both visual and interoceptive input, and returned to the start in darkness, demonstrating the influences of both visual and interoceptive information in a virtual reality environment. Next, participants adapted to visual rotation gains in the virtual environment, and then performed the path integration task entirely in darkness. Our findings were accurately predicted by a quantitative model in which visual and interoceptive inputs combine into a single multimodal representation guiding navigation, and are incompatible with a model of separate visual and interoceptive influences on action (in which path integration in darkness must rely solely on interoceptive representations). Overall, our findings suggest that a combined multimodal representation guides large-scale navigation, consistent with a role for visual imagery or a cognitive map.}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/108/3/1152.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1073/pnas.1011843108}, author = {Tcheang, L and B{\"u}lthoff, HH and Burgess, N} } @Article { 6781, title = {Walk this way: Approaching bodies can influence the processing of faces}, journal = {Cognition}, year = {2011}, month = {1}, volume = {118}, number = {1}, pages = {17-31}, abstract = {A highly familiar type of movement occurs whenever a person walks towards you. In the present study, we investigated whether this type of motion has an effect on face processing. We took a range of different 3D head models and placed them on a single, identical 3D body model. The resulting figures were animated to approach the observer. In a first series of experiments, we used a sequential matching task to investigate how the motion of an approaching person affects immediate responses to faces. We compared observers’ responses following approach sequences to their performance with figures walking backwards (receding motion) or remaining still. Observers were significantly faster in responding to a target face that followed an approach sequence, compared to both receding and static primes. In a second series of experiments, we investigated long-term effects of motion using a delayed visual search paradigm. After studying moving or static avatars, observers searched for target faces in static arrays of varyin g set sizes. Again, observers were faster at responding to faces that had been learned in the context of an approach sequence. Together these results suggest that the context of a moving body influences face processing, and support the hypothesis that our visual system has mechanisms that aid the encoding of behaviourally-relevant and familiar dynamic events.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T24-51CHMC4-1-H\&_cdi=4908\&_user=29041\&_pii=S0010027710002179\&_origin=browse\&_coverDate=11\%2F02\%2F2010\&_sk=999999999\&view=c\&wchp=dGLzVtz-zSkWA\&md5=c8de6ee3037}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.cognition.2010.09.004}, author = {Pilz, KS and Vuong, QC and B{\"u}lthoff, HH and Thornton, IM} } @Article { 6441, title = {The Thatcher illusion in humans and monkeys}, journal = {Proceedings of the Royal Society of London B}, year = {2010}, month = {10}, volume = {277}, number = {1696}, pages = {2973-2981}, abstract = {Primates possess the remarkable ability to differentiate faces of group members and to extract relevant information about the individual directly from the face. Recognition of conspecific faces is achieved by means of holistic processing, i.e. the processing of the face as an unparsed, perceptual whole, rather than as the collection of independent features (part-based processing). The most striking example of holistic processing is the Thatcher illusion. Local changes in facial features are hardly noticeable when the whole face is inverted (rotated 180\(^{\circ}\)), but strikingly grotesque when the face is upright. This effect can be explained by a lack of processing capabilities for locally rotated facial features when the face is turned upside down. Recently, a Thatcher illusion was described in the macaque monkey analogous to that known from human investigations. Using a habituation paradigm combined with eye tracking, we address the critical follow-up questions raised in the aforementioned study to show the Thatch er illusion as a function of the observer‘s species (humans and macaques), the stimulus‘ species (humans and macaques) and the level of perceptual expertise (novice, expert).}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://rspb.royalsocietypublishing.org/content/early/2010/05/13/rspb.2010.0438.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1098/rspb.2010.0438}, author = {Dahl, CD and Logothetis, NK and B{\"u}lthoff, HH and Wallraven, C} } @Article { 6783, title = {Bayesian integration of visual and vestibular signals for heading}, journal = {Journal of Vision}, year = {2010}, month = {9}, volume = {10}, number = {11}, pages = {1-13}, abstract = {Self-motion through an environment involves a composite of signals such as visual and vestibular cues. Building upon previous results showing that visual and vestibular signals combine in a statistically optimal fashion, we investigated the relative weights of visual and vestibular cues during self-motion. This experiment was comprised of three experimental conditions: vestibular alone, visual alone (with four different standard heading values), and visual–vestibular combined. In the combined cue condition, inter-sensory conflicts were introduced (\(\Delta\) = ±6\(^{\circ}\) or ±10\(^{\circ}\)). Participants performed a 2-interval forced choice task in all conditions and were asked to judge in which of the two intervals they moved more to the right. The cue-conflict condition revealed the relative weights associated with each modality. We found that even when there was a relatively large conflict between the visual and vestibular cues, participants exhibited a statistically optimal reduction in variance. On the other hand, we found that the pattern of results in the unimodal conditions did not predict the weights in the combined cue condition. Specifically, visual–vestibular cue combination was not predicted solely by the reliability of each cue, but rather more weight was given to the vestibular cue.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/10/11/23.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/10.11.23}, EPUB = {23}, author = {Butler, JS and Smith, ST and Campos, JL and B{\"u}lthoff, HH} } @Article { 6643, title = {Visual and Haptic Perceptual Spaces Show High Similarity in Humans}, journal = {Journal of Vision}, year = {2010}, month = {9}, volume = {10}, number = {11:2}, pages = {1-20}, abstract = {In this study, we show that humans form highly similar perceptual spaces when they explore complex objects from a parametrically defined object space in the visual and haptic domains. For this, a three-dimensional parameter space of well-defined, shell-like objects was generated. Participants either explored two-dimensional pictures or three-dimensional, interactive virtual models of these objects visually, or they explored three-dimensional plastic models haptically. In all cases, the task was to rate the similarity between two objects. Using these similarity ratings and multidimensional scaling (MDS) analyses, the perceptual spaces of the different modalities were then analyzed. Looking at planar configurations within this three-dimensional object space, we found that active visual exploration led to a highly similar perceptual space compared to passive exploration, showing that participants were able to reconstruct the complex parameter space already from two-dimensional pictures alone. Furthermore, we found that visual and haptic perceptual spaces had virtually identical topology compared to that of the physical stimulus space. Surprisingly, the haptic modality even slightly exceeded the visual modality in recovering the topology of the complex object space when the whole three-dimensional space was explored. Our findings point to a close connection between visual and haptic object representations and demonstrate the great degree of fidelity with which haptic shape processing occurs.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/10/11/2.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/10.11.2}, author = {Gaissert, N and Wallraven, C and B{\"u}lthoff, HH} } @Article { 6123, title = {The Effect of Viewing a Self-Avatar on Distance Judgments in an HMD-Based Virtual Environment}, journal = {Presence: Teleoperators and Virtual Environments}, year = {2010}, month = {6}, volume = {19}, number = {3}, pages = {230-242}, abstract = {Few HMD-based virtual environment systems display a rendering of the user’s own body. Subjectively, this often leads to a sense of disembodiment in the virtual world. We explore the effect of being able to see one’s own body in such systems on an objective measure of the accuracy of one form of space perception. Using an action-based response measure, we found that participants who explored near space while seeing fully-articulated and tracked visual representation of themselves subsequently made more accurate judgments of absolute egocentric distance to locations ranging from 4m to 6m away from where they were standing than did participants who saw no avatar. A non-animated avatar also improved distance judgments, but by a lesser amount. Participants who viewed either animated or static avatars positioned 3m in front of their own position made subsequent distance judgments with similar accuracy to the participants who viewed the equivalent animated or static avatar positioned at their own location. We discuss the implications of these results on theories of embodied perception in virtual environments.}, department = {Department B{\"u}lthoff}, web_url = {http://www.mitpressjournals.org/doi/pdf/10.1162/pres.19.3.230}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1162/pres.19.3.230}, author = {Mohler, BJ and Creem-Regehr, SH and Thompson, WB and B{\"u}lthoff, HH} } @Article { 6318, title = {The quick and the dead: when reaction beats intention}, journal = {Proceedings of the Royal Society of London B}, year = {2010}, month = {6}, volume = {277}, number = {1688}, pages = {1667-1674}, abstract = {Everyday behaviour involves a trade-off between planned actions and reaction to environmental events. Evidence from neurophysiology, neurology and functional brain imaging suggests different neural bases for the control of different movement types. Here we develop a behavioural paradigm to test movement dynamics for intentional versus reaction movements and provide evidence for a ‘reactive advantage’ in movement execution, whereby the same action is executed faster in reaction to an opponent. We placed pairs of participants in competition with each other to make a series of button presses. Within-subject analysis of movement times revealed a 10 per cent benefit for reactive actions. This was maintained when opponents performed dissimilar actions, and when participants competed against a computer, suggesting that the effect is not related to facilitation produced by action observation. Rather, faster ballistic movements may be a general property of reactive motor control, potentially providing a useful means of promoting survival.}, department = {Department B{\"u}lthoff}, web_url = {http://rspb.royalsocietypublishing.org/content/early/2010/01/28/rspb.2009.2123.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1098/rspb.2009.2123}, author = {Welchman, AE and Stanley, J and Schomers, MR and Miall, RC and B{\"u}lthoff, HH} } @Article { 6408, title = {Attentional Networks and Biological Motion}, journal = {Psihologija}, year = {2010}, month = {3}, volume = {43}, number = {1}, pages = {5-20}, abstract = {Our ability to see meaningful actions when presented with point-light traces of human movement is commonly referred to as the perception of biological motion. While traditional explanations have emphasized the spontaneous and automatic nature of this ability, more recent findings suggest that attention may play a larger role than is typically assumed. In two studies we show that the speed and accuracy of responding to point-light stimuli is highly correlated with the ability to control selective attention. In our first experiment we measured thresholds for determining the walking direction of a masked point-light figure, and performance on a range of attention-related tasks in the same set of observers. Mask-density thresholds for the direction discrimination task varied quite considerably from observer to observer and this variation was highly correlated with performance on both Stroop and flanker interference tasks. Other components of attention, such as orienting, alerting and visual search efficiency, showed no such relationship. In a second experiment, we examined the relationship between the ability to determine the orientation of unmasked point-light actions and Stroop interference, again finding a strong correlation. Our results are consistent with previous research suggesting that biological motion processing may requite attention, and specifically implicate networks of attention related to executive control and selection.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Psihologija-2010-43-5_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://scindeks.nb.rs/journaldetails.aspx?issn=0048-5705\&amp;lang=en}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.2298/PSI1001005C}, author = {Chandrasekaran, C and Turner, L and B{\"u}lthoff, HH and Thornton, IM} } @Article { 4179, title = {Multidimensional scaling analysis of haptic exploratory procedures}, journal = {ACM Transactions on Applied Perception}, year = {2010}, month = {1}, volume = {7}, number = {1:7}, pages = {1-17}, abstract = {Previous work in real and virtual settings has shown that the way in which we interact with objects plays a fundamental role in the way we perceive them. This article uses multidimensional scaling (MDS) analysis to further characterize and quantify the effects of using different haptic exploratory procedures (EPs) on perceptual similarity spaces. In Experiment 1, 20 participants rated similarity on a set of nine novel, 3D objects varying in shape and texture after either following their contours, laterally rubbing their centers, gripping them, or sequentially touching their tips. MDS analysis was used to recover perceptual maps of the objects and relative weights of perceptual dimensions from similarity data. Both the maps and relative weights of shape/texture properties were found to vary as a function of the EP used. In addition, large individual differences in the relative weight of shape/texture were observed. In Experiment 2, 17 of the previous participants repeated Experiment 1 after an average of 105 d ays. The same patterns of raw similarity ratings, perceptual maps, dimension weights, and individual differences were observed, indicating that perceptual similarities remained stable over time. The findings underscore the role of hand movements and individual biases in shaping haptic perceptual similarity. A framework for validating multimodal virtual displays based on the approach used in the study is also presented.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/expl_proc_4179[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1658349.1658356\&coll=portal\&dl=ACM,ACM\&idx=J932\&part=transaction\&WantType=Transactions\&title=TAP}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1658349.1658356}, author = {Cooke, T and Wallraven, C and B{\"u}lthoff, HH} } @Article { 4199, title = {Simulating believable forward accelerations on a stewart motion platform}, journal = {ACM Transactions on Applied Perception}, year = {2010}, month = {1}, volume = {7}, number = {1:5}, pages = {1-27}, abstract = {It is still an unsolved problem how to optimally simulate self-motion using motion simulators. We investigated how a forward acceleration can be simulated as believably as possible on a hexapod motion platform equipped with a projection screen. Human participants rated the believability of brief forward accelerations. These were simulated as visual forward accelerations over a ground plane with people as size cues, presented together with brief forward surge translations and backward pitches of the platform, and synchronous random up--down movements of the camera in the visual scene and the platform. The magnitudes of all of the parameters were varied independently across trials. Even though variability between participants was high, the most believable simulation occurred when visual accelerations were combined with backward pitches of the platform, which changed the gravitoinertial vector direction approximately consistent with the visual acceleration. However, a wide range of platform pitches was accepted as believable. With high visual acceleration cues most participants reported trials as realistic even when the platform tilt rate was above vestibular canal thresholds reported in other works. Other manipulated parameters had only a mild influence on the responses. These results can be used to optimize motion-cueing algorithms for simulating linear accelerations in motion simulators.}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1658349.1658354\&coll=portal\&dl=ACM\&idx=J932\&part=transaction\&WantType=Transactions\&title=ACM\%20Transactions\%20on\%20Applied\%20Perception\%20(TAP)\&CFID=75661239\&CFTOKEN=93480988}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {MPI f{\"u}r biologische Kybernetik, T{\"u}bingen}, language = {en}, DOI = {10.1145/1658349.1658354}, author = {Berger, DR and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Article { 6035, title = {Storing upright turns: how visual and vestibular cues interact during the encoding and recalling process}, journal = {Experimental Brain Research}, year = {2010}, month = {1}, volume = {200}, number = {1}, pages = {37-49}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/storing-upright-turn-Vidal-hhb_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/q330562617g08g31/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-009-1980-5}, author = {Vidal, M and B{\"u}lthoff, HH} } @Article { 5515, title = {Imagined Self-Motion Differs from Perceived Self-Motion: Evidence from a Novel Continuous Pointing Method}, journal = {PLoS One}, year = {2009}, month = {11}, volume = {4}, number = {11}, pages = {1-11}, abstract = {Background The extent to which actual movements and imagined movements maintain a shared internal representation has been a matter of much scientific debate. Of the studies examining such questions, few have directly compared actual full-body movements to imagined movements through space. Here we used a novel continuous pointing method to a) provide a more detailed characterization of self-motion perception during actual walking and b) compare the pattern of responding during actual walking to that which occurs during imagined walking. Methodology/Principal Findings This continuous pointing method requires participants to view a target and continuously point towards it as they walk, or imagine walking past it along a straight, forward trajectory. By measuring changes in the pointing direction of the arm, we were able to determine participants' perceived/imagined location at each moment during the trajectory and, hence, perceived/imagined self-velocity during the entire movement. The specific pattern of pointing behaviour that was revealed during sighted walking was also observed during blind walking. Specifically, a peak in arm azimuth velocity was observed upon target passage and a strong correlation was observed between arm azimuth velocity and pointing elevation. Importantly, this characteristic pattern of pointing was not consistently observed during imagined self-motion. Conclusions/Significance Overall, the spatial updating processes that occur during actual self-motion were not evidenced during imagined movement. Because of the rich description of self-motion perception afforded by continuous pointing, this method is expected to have significant implications for several research areas, including those related to motor imagery and spatial cognition and to applied fields for which mental practice techniques are common (e.g. rehabilitation and athletics).}, department = {Department B{\"u}lthoff}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=7EC338C2BF98904DAB7CCEA3B5344BA6.ambra02?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pone.0007793\&representation=PDF}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1371/journal.pone.0007793}, EPUB = {e7793}, author = {Campos, JL and Siegle, JH and Mohler, BJ and B{\"u}lthoff, HH and Loomis, JM} } @Article { 6207, title = {Three-Dimensional Assessment of Facial Development in Children With Pierre Robin Sequence}, journal = {Journal of Craniofacial Surgery}, year = {2009}, month = {11}, volume = {20}, number = {6}, pages = {2055-2060}, abstract = {Newborns with Pierre Robin sequence (PRS) have mandibular hypoplasia, glossoptosis, and possibly cleft palate. Their facial appearance is characteristic. The further facial development is controversial. The aim of this study was to analyze the facial development of children with PRS. In a prospective, cross-sectional study, 344 healthy children and 37 children with PRS and cleft palate younger than 8 years were scanned three-dimensionally. Twenty-one standard anthropometric landmarks were identified, and the images were superimposed. Growth curves for normal facial development were calculated. The facial morphology of children with PRS was compared with that of healthy children. The facial growth of children with PRS in the transversal and vertical direction was normal. In the sagittal direction, the mandibular deficit was confirmed. Except for the orbital landmarks and nasion, all landmarks of the midface demonstrated a significant sagittal deficit. This difference to healthy children remained constant for all ages. Our study cannot support the theory of mandibular catch-up growth. The sagittal deficit of the midface could be observed in all ages. This indicates that children with PRS have a very early, severe, and persistent underdevelopment of this part of the face. We conclude that this disturbance must be addressed in early childhood with orthodontic and speech therapy.}, department = {Department B{\"u}lthoff}, web_url = {http://journals.lww.com/jcraniofacialsurgery/Abstract/2009/11000/Three_Dimensional_Assessment_of_Facial_Development.21.aspx}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1097/SCS.0b013e3181be87db}, author = {Krimmel, M and Kluba, S and Breidt, M and Bacher, M and Dietz, K and B{\"u}lthoff, HH and Reinert, S} } @Article { 5824, title = {Cross-Modal Transfer in Visual and Haptic Face Recognition}, journal = {IEEE Transactions on Haptics}, year = {2009}, month = {10}, volume = {200}, number = {4}, pages = {236-240}, abstract = {We report four psychophysical experiments investigating cross-modal transfer in visual and haptic face recognition. We found surprisingly good haptic performance and cross-modal transfer for both modalities. Interestingly, transfer was asymmetric depending on which modality was learned first. These findings are discussed in relation to haptic object processing and face processing.}, department = {Department B{\"u}lthoff}, web_url = {http://www2.computer.org/portal/web/csdl/doi/10.1109/TOH.2009.18}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1109/TOH.2009.18}, author = {Dopjans, L and Wallraven, C and B{\"u}lthoff, HH} } @Article { 5527, title = {The role of attention on the integration of visual and inertial cues}, journal = {Experimental Brain Research}, year = {2009}, month = {9}, volume = {198}, number = {2-3}, pages = {287-300}, abstract = {The extent to which attending to one stimulus while ignoring another influences the integration of visual and inertial (vestibular, somatosensory, proprioceptive) stimuli is currently unknown. It is also unclear how cue integration is affected by an awareness of cue conflicts. We investigated these questions using a turn-reproduction paradigm, where participants were seated on a motion platform equipped with a projection screen and were asked to actively return a combined visual and inertial whole-body rotation around an earth-vertical axis. By introducing cue conflicts during the active return and asking the participants whether they had noticed a cue conflict, we measured the influence of each cue on the response. We found that the task instruction had a significant effect on cue weighting in the response, with a higher weight assigned to the attended modality, only when participants noticed the cue conflict. This suggests that participants used task-induced attention to reduce the influence of stimuli that conflict with the task instructions.}, department = {Department B{\"u}lthoff}, web_url = {http://springerlink.metapress.com/content/e672303w0688m17p/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-009-1767-8}, author = {Berger, DR and B{\"u}lthoff, HH} } @Article { 5995, title = {Seeing the hand while reaching speeds up on-line responses to a sudden change in target position}, journal = {The Journal of Physiology}, year = {2009}, month = {8}, volume = {587}, number = {19}, pages = {4605-4616}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, web_url = {http://jp.physoc.org/content/early/2009/08/10/jphysiol.2009.176362.abstract}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1113/jphysiol.2009.176362}, author = {Reichenbach, A and Thielscher, A and Peer, A and B{\"u}lthoff, HH and Bresciani, J-P} } @Article { 6036, title = {A multisensory approach to spatial updating: the case of mental rotations}, journal = {Experimental Brain Research}, year = {2009}, month = {7}, volume = {197}, number = {1}, pages = {59-68}, abstract = {Mental rotation is the capacity to predict the outcome of spatial relationships after a change in viewpoint. These changes arise either from the rotation of the test object array or from the rotation of the observer. Previous studies showed that the cognitive cost of mental rotations is reduced when viewpoint changes result from the observer’s motion, which was explained by the spatial updating mechanism involved during self-motion. However, little is known about how various sensory cues available might contribute to the updating performance. We used a Virtual Reality setup in a series of experiments to investigate table-top mental rotations under different combinations of modalities among vision, body and audition. We found that mental rotation performance gradually improved when adding sensory cues to the moving observer (from None to Body or Vision and then to Body \& Audition or Body \& Vision), but that the processing time drops to the same level for any of the sensor y contexts. These results are discussed in terms of an additive contribution when sensory modalities are co-activated to the spatial updating mechanism involved during self-motion. Interestingly, this multisensory approach can account for different findings reported in the literature.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/A-multisensory-approach-Vidal-Lehmann-hhb_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/9511k45076051x66/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-009-1892-4}, author = {Vidal, M and Lehmann, A and B{\"u}lthoff, HH} } @Article { 6638, title = {Learning illumination- and orientation-invariant representations of objects through temporal association}, journal = {Journal of Vision}, year = {2009}, month = {7}, volume = {9}, number = {7:6}, pages = {1-8}, abstract = {As the orientation or illumination of an object changes so does its appearance. This paper considers how observers are nonetheless able to recognize objects that have undergone such changes. In particular the paper tests the hypothesis that observers rely on temporal correlations between different object views to decide whether they are views of the same object or not. In a series of experiments subjects were shown a sequence of views representing a slowly transforming object. Testing revealed that subjects had formed object representations which were directly influenced by the temporal characteristics of the training views. In particular, introducing spurious correlations between views of different people‘s heads caused subjects to regard those views as being of a single person. This rapid and robust overriding of basic generalization processes supports the view that our recognition system tracks the correlated appearance of views of objects across time. Such view associations appear to allow the visual system to solve the view invariance problem without recourse to complex illumination models for extracting 3D form, or the use of the image plane transformations required to make appearance-based comparisons.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/9/7/6.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/9.7.6}, author = {Wallis, G and Backus, BT and Langer, M and Huebner, G and B{\"u}lthoff, HH} } @Article { 4688, title = {Learning influences the encoding of static and dynamic faces and their recognition across different spatial frequencies}, journal = {Visual Cognition}, year = {2009}, month = {7}, volume = {17}, number = {5}, pages = {716-735}, abstract = {Studies on face recognition have shown that observers are faster and more accurate at recognizing faces learned from dynamic sequences than those learned from static snapshots. Here, we investigated whether different learning procedures mediate the advantage for dynamic faces across different spatial frequencies. Observers learned two faces—one dynamic and one static—either in depth (Experiment 1) or using a more superficial learning procedure (Experiment 2). They had to search for the target faces in a subsequent visual search task. We used high-spatial frequency (HSF) and low-spatial frequency (LSF) filtered static faces during visual search to investigate whether the behavioural difference is based on encoding of different visual information for dynamically and statically learned faces. Such encoding differences may mediate the recognition of target faces in different spatial frequencies, as HSF may mediate featural face processing whereas LSF mediates configural processing. Our results show that the nature of the learning procedure alters how observers encode dynamic and static faces, and how they recognize those learned faces across different spatial frequencies. That is, these results point to a flexible usage of spatial frequencies tuned to the recognition task.}, department = {Department B{\"u}lthoff}, web_url = {http://pdfserve.informaworld.com/178690_758077663_902406191.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1080/13506280802340588}, author = {Pilz, KS and B{\"u}lthoff, HH and Vuong, QC} } @Article { 5516, title = {Measurement of instantaneous perceived self-motion using continuous pointing}, journal = {Experimental Brain Research}, year = {2009}, month = {5}, volume = {195}, number = {3}, pages = {429-444}, abstract = {In order to optimally characterize full-body self-motion perception during passive translations, changes in perceived location, velocity, and acceleration must be quantified in real time and with high spatial resolution. Past methods have failed to effectively measure these critical variables. Here, we introduce continuous pointing as a novel method with several advantages over previous methods. Participants point continuously to the mentally updated location of a previously viewed target during passive, full-body movement. High-precision motion-capture data of arm angle provide a measure of a participant’s perceived location and, in turn, perceived velocity at every moment during a motion trajectory. In two experiments, linear movements were presented in the absence of vision by passively translating participants with a robotic wheelchair or an anthropomorphic robotic arm (MPI Motion Simulator). The movement profiles included constant-velocity trajectories, two successive movement intervals separated by a b rief pause, and reversed-motion trajectories. Results indicate a steady decay in perceived velocity during constant-velocity travel and an attenuated response to mid-trial accelerations.}, department = {Department B{\"u}lthoff}, web_url = {http://springerlink.metapress.com/content/t0625668v1651t45/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-009-1805-6}, author = {Siegle, JH and Campos, JL and Mohler, BJ and Loomis, JM and B{\"u}lthoff, HH} } @Article { 5694, title = {Influence of the size of the field of view on motion perception}, journal = {Computers and Graphics}, year = {2009}, month = {4}, volume = {33}, number = {2}, pages = {139-146}, abstract = {Efficient navigation requires a good representation of body position/orientation in the environment and an accurate updating of this representation when the body-environment relationship changes. Such updating is based on the ability to correctly estimate the speed and amplitude of body displacements. Because navigation in virtual worlds often relies on the sole visual information, we investigated to which extent the size of the field of view (FoV) affects two basic aspects of motion perception: (i) the perceived amplitude of rotations about the body vertical axis (Experiment 1) and (ii) the perceived speed of forward translations (Experiment 2). Concerning the perception of rotation amplitude, we found that visual flow information gives rise to inaccurate and very variable estimations, with a systematic underestimation of rotations larger than 30 degrees. We also found that the accuracy of the estimations does not depend on the size of the FoV and that horizontal FoVs larger than 30 degrees do not improve the performance. Concerning speed perception, central FoVs smaller than 60 degrees gave rise to an underestimation of the visual speed. On the other hand, occluding the central area leaving only peripheral visual information available induced a systematic overestimation of visual speed, even when only the central 10 degrees of vision were occluded. Taken together, these results suggest that large FoVs are not required to estimate the amplitude of visual rotations about the vertical axis of the body, whereas central FoVs of at least 60 degrees are advisable when speed perception relies on visual flow information.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6TYG-4VGF3VR-1-19\&_cdi=5618\&_user=29041\&_orig=browse\&_coverDate=04\%2F30\%2F2009\&_sk=999669997\&view=c\&wchp=dGLbVtb-zSkWA\&md5=b4f2f6958b3f6f5de18521e4480a296f\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.cag.2009.01.003}, author = {Pretto, P and Ogier, M and B{\"u}lthoff, HH and Bresciani, J-P} } @Article { 5707, title = {Humans and Macaques Employ Similar Face-Processing Strategies}, journal = {Current Biology}, year = {2009}, month = {3}, volume = {19}, number = {6}, pages = {509-513}, abstract = {Primates developed the ability to recognize and individuate their conspecifics by the face. Despite numerous electrophysiological studies in monkeys [1–3], little is known about the face-processing strategies that monkeys employ. In contrast, face perception in humans has been the subject of many studies [4–6] providing evidence for specific face processing that evolves with perceptual expertise [7]. Importantly, humans process faces holistically, here defined as the processing of faces as wholes, rather than as collections of independent features (part-based processing) [8]. The question remains to what extent humans and monkeys share these face-processing mechanisms. By using the same experimental design and stimuli for both monkey and human behavioral experiments, we show that face processing is influenced by the species affiliation of the observed face stimulus (human versus macaque face). Furthermore, stimulus manipulations that selectively reduced holistic and part-based information systematically altered eye-scanning patterns for human and macaque observers similarly. These results demonstrate the similar nature of face perception in humans and monkeys and pin down effects of expert faceprocessing versus novice face-processing strategies. These findings therefore directly contribute to one of the central discussions in the behavioral and neurosciences about how faces are perceived in primates.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VRT-4VPN17C-5-2\&_cdi=6243\&_user=29041\&_orig=search\&_coverDate=03\%2F24\%2F2009\&_sk=999809993\&view=c\&wchp=dGLzVzz-zSkzk\&md5=e6f38dd7719b33b8f0c6b73ddac9cc6f\&ie=}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.cub.2009.01.061}, author = {Dahl, CD and Wallraven, C and B{\"u}lthoff, HH and Logothetis, NK} } @Article { 5583, title = {Circular, linear, and curvilinear vection in a large-screen virtual environment with floor projection}, journal = {Computers and Graphics}, year = {2009}, month = {2}, volume = {33}, number = {1}, pages = {47-58}, abstract = {Vection is defined as the compelling sensation of illusory self-motion elicited by a moving sensory, usually visual, stimulus. This paper presents collected introspective data, user discomfort and perceived speed data for the experience of linear, circular, and curvilinear vection in a large-screen, immersive, virtual environment. As a first step we evaluated the effectiveness of a floor projection on the perception of vection for four trajectories: linear forward, linear backward, circular left, and circular right. The floor projection, which considerably extended the field of view, was found to significantly improve the introspective measures of linear, but not circular, vection experienced in a photo-realistic three-dimensional town. In a second study we investigated the differences between 12 different motion trajectories on the illusion of self-motion. In this study we found that linear translations to the left and right are perceived as the least convincing, while linear down is perceived as the most convincing of the linear trajectories. Second, we found that while linear forward vection is not perceived to be very convincing, curvilinear forward vection is reported to be as convincing as circular vection. In a third and final experiment we investigated the perceived speed for all different trajectories and acquired data based on simulator sickness questionnaires to compute a discomfort factor associated with each type of trajectory. Considering our experimental results, we offer suggestions for increasing the sense of self-motion in simulators and VE applications, specifically to increase the number of curvilinear trajectories (as opposed to linear ones) and, if possible, add floor projection in order to improve the illusory sense of self-motion.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6TYG-4V3SY6B-1-1M\&_cdi=5618\&_user=29041\&_orig=browse\&_coverDate=02\%2F28\%2F2009\&_sk=999669998\&view=c\&wchp=dGLbVzz-zSkzV\&md5=1d4}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.cag.2008.11.008}, author = {Trutoiu, LC and Mohler, BJ and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Article { 6043, title = {Reply to Lages and Heron: Binocular 3D motion estimation}, journal = {Proceedings of the National Academy of the United States of America}, year = {2008}, month = {12}, volume = {105}, number = {51}, pages = {E118-E118}, abstract = {In examining 3D motion estimation (1), we start by considering the computation of two entirely plausible quantities—changes in disparity (\&\#948;) and azimuth (\&\#966;). Because these depend on the difference and mean of retinal signals, respectively, we expect \&\#966; to be more reliable. The impact of this differential reliability on motion estimation is best illustrated for pure motion in depth (Vz) and pure lateral motion (Vx). Vz depends only on the higher-variance \&\#948; signal, whereas Vx depends almost solely on \&\#966; for small movements. Thus we measure performance along these dimensions to illustrate the limitations imposed by the underlying computations. Lages and Heron (2) query whether it is biologically plausible for the brain to estimate Vx and Vz separately. As we have shown elsewhere (3), formulating the estimation problem in terms Vx and Vz does not imply that the brain estimates the components separately (although performance can clearly be measured along these dimensions as we have shown). Rather, trajectory angles could be calculated directly based on \&\#948; and \&\#966; (4). The Bayesian model we use (in ref. ,1, see figure 1C) selects the estimator from the two-dimensional (Vx, Vz) space rather than relying on independent estimation. Lages‘s previous work (5) suggested that a model based on static disparity (\&\#948;) provides the best account for 3D motion estimation. Although this is a formulation we have used previously (,3), we suggest that, within the context of judging moving objects, it is more plausible that estimation be based on motion rather than a disparity snapshot.}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/105/51/E118.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1073/pnas.0810330105}, author = {Welchman, AE and Lam, JM and B{\"u}lthoff, HH} } @Article { 5138, title = {The integration of higher order form and motion by the human brain}, journal = {NeuroImage}, year = {2008}, month = {10}, volume = {42}, number = {4}, pages = {1529-1536}, abstract = {Our experience with a dynamic environment has tuned our visual system to use form and motion as complementary sources of information for object recognition. To identify the neural systems involved in integrating form and motion information during dynamic object processing, we used an fMRI adaptation paradigm which factorially manipulated form and motion repetition. Observers were sequentially presented with pairs of rotating novel objects in which the form or rotation direction in depth could be repeated. They were required to discriminate either dimension of the second target object, while the first object served as a form or motion prime. At the behavioural level, observers were faster to recognize the target or discriminate its direction when primed by the same form. Importantly, this form priming effect was enhanced when prime and target objects rotated in the same direction. At the neural level, the two priming effects (i.e., the main effect of form repetition and the interaction between form and motion repetition) were associated with reduced activations in distinct brain regions. Bilateral lateral occipital regions exhibited reduced activation when form was repeated irrespective of rotation direction. In contrast, bilateral anterior fusiform and posterior middle temporal regions (overlapping with hMT+/V5) regions showed an adaptation effect that depended on both form and motion direction. Thus, the current results reveal a visual processing hierarchy with lateral occipito-temporal cortex representing an object’s 3D structure, and anterior fusiform and posterior middle temporal regions being involved in spatio-temporal integration of form and motion during dynamic object processing.}, department = {Department B{\"u}lthoff}, department2 = {Research Group Noppeney}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6WNP-4SH0Y0C-2-M\&_cdi=6968\&_user=29041\&_orig=search\&_coverDate=10\%2F01\%2F2008\&_sk=999579995\&view=c\&wchp=dGLbVtb-zSkWb\&md5=2afffb798d11cb801968184b420b9242\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.neuroimage.2008.04.265}, author = {Sarkheil, P and Vuong, QC and B{\"u}lthoff, HH and Noppeney, U} } @Article { 4770, title = {A high-end virtual reality setup for the study of mental rotations}, journal = {Presence}, year = {2008}, month = {8}, volume = {17}, number = {4}, pages = {365-375}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Presence-2008-17-365_4770[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.mitpressjournals.org/doi/pdf/10.1162/pres.17.4.365}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1162/pres.17.4.365}, author = {Lehmann, A and Vidal, M and B{\"u}lthoff, HH} } @Article { 5326, title = {Bayesian motion estimation accounts for a surprising bias in 3D vision}, journal = {Proceedings of the National Academy of the United States of America}, year = {2008}, month = {8}, volume = {105}, number = {33}, pages = {12087-12092}, abstract = {Determining the approach of a moving object is a vital survival skill that depends on the brain combining information about lateral translation and motion-in-depth. Given the importance of sensing motion for obstacle avoidance, it is surprising that humans make errors, reporting an object will miss them when it is on a collision course with their head. Here we provide evidence that biases observed when participants estimate movement in depth result from the brain\&lsquo;s use of a “prior” favoring slow velocity. We formulate a Bayesian model for computing 3D motion using independently estimated parameters for the shape of the visual system\&lsquo;s slow velocity prior. We demonstrate the success of this model in accounting for human behavior in separate experiments that assess both sensitivity and bias in 3D motion estimation. Our results show that a surprising perceptual error in 3D motion perception reflects the importance of prior probabilities when estimating environm ental pr operties.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/PNAS-Welchman-proofs_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/early/2008/08/11/0804378105.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1073/pnas.0804378105}, author = {Welchman, AE and Lam, JM and B{\"u}lthoff, HH} } @Article { 5529, title = {Inter-individual spatial diversity in motor control processes within the posterior parietal cortex assessed with transcranial magnetic stimulation}, journal = {Brain Stimulation}, year = {2008}, month = {7}, volume = {1}, number = {3}, pages = {283-284}, abstract = {Involvement of the left posterior parietal cortex (lPPC) in online motor control has been demonstrated in recent years using fMRI (Culham et al, 2006). However, the human homologue to macaque parietal reach region, or even more detailed functional anatomy of processes involved in motor control, is still controversial (lacoboni, 2006). The main challenge is the spatial co-localization of functions that are also involved in motor execution, e.g. attention, saccades, and motor planning (Astafiev et al, 2003). TMS offers the possibility to disentangle these functions due to its high temporal resolution, and can also discriminate necessary from co-activated brain areas. Desmurget et al (1999) showed that online correction for reaching to an altered target can be disturbed using TMS over the lPPC. In this study, we developed an fMRI localizer to assess lPPC sub-regions that are involved in online motor control. Subsequently, we tested these sites with event-related TMS. Using closed-loop reaching (with visual hand feedback) allows investigating the processes involved in body's effectors representation in addition to environment representation during goal-directed reaching, by introducing different visual perturbations. The fMRI localizer consists of blocks for fixation, saccades, and reaching with an MR-compatible joystick. Within the reaching blocks, different visual perturbations (including none) were randomized in a fast event-related design. The different perturbation conditions were contrasted against the unperturbed reaching to assess online-correction activation. Nine right-handed subjects were tested. On group level, different visual perturbations resulted in spatial different activation patterns in the lPPC. In addition, we observed pronounced inter-individual differences in activation. Maxima from the group analyses and the individuals own maxima were used as stimulation sites for the subsequent TMS study. Four of the subjects were tested so far using event-related TMS on target alteration. Despite huge inter-individual differences in BOLD activation, we could demonstrate a closer match of TMS effect localization with subject's individual activation than with group activation (fig. 1). This finding shows that TMS is capable of investigating sub-regions of the lPPC. Furthermore, it stresses the importance of individual analyses when investigating functions located there. The next step is to map the other visual perturbations.}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, web_url = {http://www.sciencedirect.com/science?_ob=MiamiImageURL\&_cid=276827\&_user=29041\&_pii=S1935861X08001538\&_check=y\&_origin=\&_coverDate=31-Jul-2008\&view=c\&wchp=dGLbVlS-zSkzS\&md5=afc13540a9d1352eb4a46d9b24a64de2/1-s2.0-S1935861X08001538-main.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.brs.2008.06.117}, author = {Reichenbach, A and Bresciani, J-P and Peer, A and B{\"u}lthoff, HH and Thielscher, A} } @Article { 6044, title = {Using morphs of familiar objects to examine how shape discriminability influences view sensitivity}, journal = {Attention, Perception and Psychophysics}, year = {2008}, month = {7}, volume = {70}, number = {5}, pages = {853-877}, abstract = {We investigated how the difficulty of detecting a shape change influenced the achievement of object constancy across depth rotations for object identification and categorization tasks. In three sequential matching experiments, people saw pictures of morphs between two everyday, nameable objects (e.g., bath-sink morphs, along a continuum between “bath” and “sink” end-point shapes). In each experiment, both view changes and shape changes influenced performance. Furthermore, the deleterious effects of view changes were strongest when shape discrimination was hardest. In our earlier research, using morphs of novel objects, we found a similar interaction between view sensitivity and shape sensitivity (Lawson, 2004b; Lawson \& B{\"u}lthoff, 2006; Lawson, B{\"u}lthoff, \& Dumbell, 2003). The present results extend these findings to familiar-object morphs. They suggest that recognition remains view-sensitive at the basic level of identification for everyday, nameable objects, and that the difficulty of shape discrimination plays a critical role in determining the degree of this view sensitivity.}, department = {Department B{\"u}lthoff}, web_url = {http://app.psychonomic-journals.org/content/70/5/853.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.3758/PP.70.5.853}, author = {Lawson, R and B{\"u}lthoff, HH} } @Article { 4599, title = {The contribution of different facial regions to the recognition of conversational expressions}, journal = {Journal of Vision}, year = {2008}, month = {6}, volume = {8}, number = {8:1}, pages = {1-23}, abstract = {The human face is an important and complex communication channel. Humans can, however, easily read in a face not only identity information, but also facial expressions with high accuracy. Here, we present the results of four psychophysical experiments in which we systematically manipulated certain facial areas in video sequences of nine conversational expressions to investigate recognition performance and its dependency on the motions of different facial parts. These studies allowed us to determine what information is \{it necessary\} and \{it sufficient\} to recognize the different facial expressions. Subsequent analyses of the face movements and correlation with recognition performance show that, for some expressions, one individual facial region can represent the whole expression. In other cases, the interaction of more than one facial area is needed to clarify the expression. The full set of results is used to develop a systematic description of the roles of different facial parts in the visual perception of conversational facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://journalofvision.org/8/8/1/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/8.8.1}, author = {Nusseck, M and Cunningham, DW and Wallraven, C and B{\"u}lthoff, HH} } @Article { 4957, title = {Working memory in wayfinding: a dual task experiment in a virtual city}, journal = {Cognitive Science}, year = {2008}, month = {6}, volume = {32}, number = {4}, pages = {755-770}, abstract = {This study examines the working memory systems involved in human wayfinding. In the learning phase 24 participants learned two routes in a novel photorealistic virtual environment displayed on a 220\(^{\circ}\) screen, while they were disrupted by a visual, a spatial, a verbal or - in a control group - no secondary task. In the following wayfinding phase the participants had to find and to ''virtually walk'' the two routes again. During this wayfinding phase a number of dependent measures were recorded. We show that encoding wayfinding knowledge interfered with the verbal and with the spatial secondary task. These interferences were even stronger than the interference of wayfinding knowledge with the visual secondary task. These findings are consistent with a dual coding approach of wayfinding knowledge.}, department = {Department B{\"u}lthoff}, web_url = {http://www.informaworld.com/smpp/ftinterface\verb=~=content=a793518292\verb=~=fulltext=713240930}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1080/03640210802067004}, author = {Meilinger, T and Knauff, M and B{\"u}lthoff, HH} } @Article { 5383, title = {Editorial}, journal = {ACM Transactions on Applied Perception}, year = {2008}, month = {5}, volume = {5}, number = {2:6}, pages = {1-2}, note = {not reviewed}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1361703\&jmp=cit\&coll=portal\&dl=ACM\&CFID=3668468\&CFTOKEN=84174010\#CIT}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1279920.1361703}, author = {Reinhard, E and B{\"u}lthoff, H} } @Article { 5094, title = {The prototype effect revisited: Evidence for an abstract feature model of face recognition}, journal = {Journal of Vision}, year = {2008}, month = {3}, volume = {8}, number = {3:20}, pages = {1-15}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/8/3/20/Wallis-2008-jov-8-3-20.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/8.3.20}, author = {Wallis, G and Siebeck, UE and Swann, K and Blanz, V and B{\"u}lthoff, HH} } @Article { 3996, title = {Evaluating the Perceptual Realism of Animated Facial Expressions}, journal = {ACM Transactions on Applied Perception}, year = {2008}, month = {1}, volume = {4}, number = {4:4}, pages = {1-20}, abstract = {The human face is capable of producing an astonishing variety of expressions—expressions for which sometimes the smallest difference changes the perceived meaning considerably. Producing realistic-looking facial animations that are able to transport this degree of complexity continues to be a challenging research topic in computer graphics. One important question that remains to be answered is: When are facial animations good enough? Here we present an integrated framework in which psychophysical experiments are used in a first step to systematically evaluate the perceptual quality of several different computer-generated animations with respect to real-world video sequences. The first experiment provides an evaluation of several animation techniques, exposing specific animation parameters that are important to achieve perceptual fidelity. In a second experiment we then use these benchmarked animation techniques in the context of perceptual research in order to systematically investigate the spatio-temporal characteristics of expressions. A third and final experiment uses the quality measures that were developed in the first two experiments to examine the perceptual impact of changing facial features to improve the animation techniques. Using such an integrated approach, we are able to provide important insights into facial expressions for both the perceptual and computer graphics community.}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?doid=1278760.1278764}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1278760.1278764}, author = {Wallraven, C and Breidt, M and Cunningham, DW and B{\"u}lthoff, HH} } @Article { 4926, title = {Categorization of natural scenes: Local versus global information and the role of color}, journal = {ACM Transactions on Applied Perception}, year = {2007}, month = {11}, volume = {4}, number = {3:19}, pages = {1-21}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/TAP-4-3-19-Vogel_4926[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1278387.1278393}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1278387.1278393}, author = {Vogel, J and Schwaninger, A and Wallraven, C and B{\"u}lthoff, HH} } @Article { 4592, title = {Evaluation of Real-World and Computer-Generated Stylized Facial Expressions}, journal = {ACM Transactions on Applied Perception}, year = {2007}, month = {11}, volume = {4}, number = {3:16}, pages = {1-24}, abstract = {The goal of stylization is to provide an abstracted representation of an image that highlights specific types of visual information. Recent advances in computer graphics techniques have made it possible to render many varieties of stylized imagery efficiently making stylization into a useful technique, not only for artistic, but also for visualization applications. In this paper, we report results from two sets of experiments that aim at characterizing the perceptual impact and effectiveness of three different stylization techniques in the context of dynamic facial expressions. In the first set of experiments, animated facial expressions are stylized using three common techniques (brush, cartoon, and illustrative stylization) and investigated using different experimental measures. Going beyond the usual questionnaire approach, these experiments compare the techniques according to several criteria ranging from subjective preference to task-dependent measures (such as recognizability, intensity) allowing us to compare behavioral and introspective approaches. The second set of experiments use the same stylization techniques on real-world video sequences in order to compare the effect of stylization on natural and artificial stimuli. Our results shed light on how stylization of image contents affects the perception and subjective evaluation of both real and computer-generated facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1278387.1278390}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1278387.1278390}, author = {Wallraven, C and B{\"u}lthoff, HH and Fischer, J and Cunningham, DW and Bartz, D} } @Article { 4805, title = {Virtual Reality for the Psychophysiological Assessment of Phobic Fear: Responses During Virtual Tunnel Driving}, journal = {Psychological Assessment}, year = {2007}, month = {9}, volume = {19}, number = {3}, pages = {340-346}, abstract = {An overall assessment of phobic fear requires not only a verbal self-report of fear but also an assessment of behavioral and physiological responses. Virtual reality can be used to simulate realistic (phobic) situations and therefore should be useful for inducing emotions in a controlled, standardized way. Verbal and physiological fear reactions were examined in 15 highly tunnel-fearful and 15 matched control participants in 3 virtual driving scenarios: an open environment, a partially open tunnel (gallery), and a closed tunnel. Highly tunnel-fearful participants were characterized by elevated fear responses specifically during tunnel drives as reflected in verbal fear ratings, heart rate reactions, and startle responses. Heart rate and fear ratings differentiated highly tunnel-fearful from control participants with an accuracy of 88\% and 93\%, respectively. Results indicate that virtual environments are valuable tools for the assessment of fear reactions and should be used in future experimental research.}, department = {Department B{\"u}lthoff}, web_url = {http://content.apa.org/journals/pas/19/3/340}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1037/1040-3590.19.3.340}, author = {M{\"u}hlberger, A and B{\"u}lthoff, HH and Wiedemann, G and Pauli, P} } @Article { 4791, title = {Do HDR displays support LDR content?: a psychophysical evaluation}, journal = {ACM Transactions on Graphics}, year = {2007}, month = {7}, volume = {26}, number = {3:38}, pages = {1-7}, abstract = {The development of high dynamic range (HDR) imagery has brought us to the verge of arguably the largest change in image display technologies since the transition from black-and-white to color television. Novel capture and display hardware will soon enable consumers to enjoy the HDR experience in their own homes. The question remains, however, of what to do with existing images and movies, which are intrinsically low dynamic range (LDR). Can this enormous volume of legacy content also be displayed effectively on HDR displays? We have carried out a series of rigorous psychophysical investigations to determine how LDR images are best displayed on a state-of-the-art HDR monitor, and to identify which stages of the HDR imaging pipeline are perceptually most critical. Our main findings are: (1) As expected, HDR displays outperform LDR ones. (2) Surprisingly, HDR images that are tonemapped for display on standard monitors are often no better than the best single LDR exposure from a bracketed sequence. (3) Most impor tantly of all, LDR data does not necessarily require sophisticated treatment to produce a compelling HDR experience. Simply boosting the range of an LDR image linearly to fit the HDR display can equal or even surpass the appearance of a true HDR image. Thus the potentially tricky process of inverse tone mapping can be largely circumvented.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/SIGGRAPH07_camera_ready_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/toc.cfm?id=1276377\&amp;coll=portal\&amp;dl=ACM\&amp;type=issue\&amp;idx=J778\&amp;part=transaction\&amp;WantType=Transactions\&amp;title=ACM\%20Transactions\%20on\%20Graphics\%20\%28TOG\%29}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1275808.1276425}, author = {Akyuz, AO and Fleming, RW and Riecke, BE and Reinhard, E and B{\"u}lthoff, HH} } @Article { 3571, title = {Isovist analysis captures properties of space relevant for locomotion and experience}, journal = {Perception}, year = {2007}, month = {6}, volume = {36}, number = {7}, pages = {1066-1083}, abstract = {In a series of exploratory experiments we investigated interrelations between structure and shape of architectural indoor spaces on the one hand, and affective experience and navigation behaviour on the other hand. For this, isovist-based descriptions of 16 virtual indoor scenes were correlated with behavioural data from the experimental tasks. For all tasks—two active navigation tasks and an introspective appraisal of experiential qualities—strong correlations between subjects’ behaviour and a small set of quantitative measurands derived from the isovists were found. The outcomes suggest that isovist analysis captures behaviourally relevant properties of space and is therefore a promising general means for predicting central experiential qualities of architecture and navigation behaviour.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/perception/fulltext/p36/p5587.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1068/p5587}, author = {Wiener, JM and Franz, G and Rossmanith, N and Reichelt, A and Mallot, HA and B{\"u}lthoff, HH} } @Article { 4195, title = {A Bayesian model of the disambiguation of gravitoinertial force by visual cues}, journal = {Experimental Brain Research}, year = {2007}, month = {5}, volume = {179}, number = {2}, pages = {263-290}, abstract = {The otoliths are stimulated in the same fashion by gravitational and inertial forces, so otolith signals are ambiguous indicators of self-orientation. The ambiguity can be resolved with added visual information indicating orientation and acceleration with respect to the earth. Here we present a Bayesian model of the statistically optimal combination of noisy vestibular and visual signals. Likelihoods associated with sensory measurements are represented in an orientation/acceleration space. The likelihood function associated with the otolith signal illustrates the ambiguity; there is no unique solution for self-orientation or acceleration. Likelihood functions associated with other sensory signals can resolve this ambiguity. In addition, we propose two priors, each acting on a dimension in the orientation/acceleration space: the idiotropic prior and the no-acceleration prior. We conducted experiments using a motion platform and attached visual display to examine the influence of visual signals on the interpret ation of the otolith signal. Subjects made pitch and acceleration judgments as the vestibular and visual signals were manipulated independently. Predictions of the model were confirmed: (1) visual signals affected the interpretation of the otolith signal, (2) less variable signals had more influence on perceived orientation and acceleration than more variable ones, and (3) combined estimates were more precise than single-cue estimates. We also show that the model can explain some well-known phenomena including the perception of upright in zero gravity, the Aubert effect, and the somatogravic illusion.}, department = {Department B{\"u}lthoff}, web_url = {http://springerlink.metapress.com/content/j534804133440170/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-006-0792-0}, author = {MacNeilage, PR and Banks, MS and Berger, DR and B{\"u}lthoff, HH} } @Article { 3874, title = {Multimodal Similarity and Categorization of Novel, Three-Dimensional Objects}, journal = {Neuropsychologia}, year = {2007}, month = {2}, volume = {45}, number = {3}, pages = {484-495}, abstract = {Similarity has been proposed as a fundamental principle underlying mental object representations and capable of supporting cognitive-level tasks such as categorization. However, much of the research has considered connections between similarity and categorization for tasks performed using a single perceptual modality. Considering similarity and categorization within a multimodal context opens up a number of important questions: Are the similarities between objects the same when they are perceived using different modalities or using more than one modality at a time? Is similarity still able to explain categorization performance when objects are experienced multimodally? In this study, we addressed these questions by having subjects explore novel, 3D objects which varied parametrically in shape and texture using vision alone, touch alone, or touch and vision together. Subjects then performed a pair-wise similarity rating task and a free sorting categorization task. Multidimensional scaling (MDS) analysis of similarity data revealed that a single underlying perceptual map whose dimensions corresponded to shape and texture could explain visual, haptic, and bimodal similarity ratings. However, the relative dimension weights varied according to modality: shape dominated texture when objects were seen, whereas shape and texture were roughly equally important in the haptic and bimodal conditions. Some evidence was found for a multimodal connection between similarity and categorization: the probability of category membership increased with similarity while the probability of a category boundary being placed between two stimuli decreased with similarity. In addition, dimension weights varied according to modality in the same way for both tasks. The study also demonstrates the usefulness of 3D printing technology and MDS techniques in the study of visuohaptic object processing.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/cooke_neuropsy_2006_3874[1].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0D-4JKYWRS-4-N\&_cdi=4860\&_user=29041\&_orig=browse\&_coverDate=12\%2F31\%2F2007\&_sk=999549996\&view=c\&wchp=dGLzVzz-zSkzV\&md5=58bd}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.neuropsychologia.2006.02.009}, author = {Cooke, T and J{\"a}kel, F and Wallraven, C and B{\"u}lthoff, HH} } @Article { 3914, title = {Object feature validation using visual and haptic similarity ratings}, journal = {ACM Transactions on Applied Perception}, year = {2006}, month = {10}, volume = {3}, number = {3}, pages = {239-261}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/cooke_tap_2006_3914[1].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?doid=1166087.1166093}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1166087.1166093}, author = {Cooke, T and Kannengiesser, S and Wallraven, C and B{\"u}lthoff, H} } @Article { 3768, title = {Spatial updating in virtual reality: the sufficiency of visual information}, journal = {Psychological Research}, year = {2006}, month = {9}, volume = {71}, number = {3}, pages = {298-313}, abstract = {Robust and effortless spatial orientation critically relies on “automatic and obligatory spatial updating”, a largely automatized and reflex-like process that transforms our mental egocentric representation of the immediate surroundings during ego-motions. A rapid pointing paradigm was used to assess automatic/obligatory spatial updating after visually displayed upright rotations with or without concomitant physical rotations using a motion platform. Visual stimuli displaying a natural, subject-known scene proved sufficient for enabling automatic and obligatory spatial updating, irrespective of concurrent physical motions. This challenges the prevailing notion that visual cues alone are insufficient for enabling such spatial updating of rotations, and that vestibular/proprioceptive cues are both required and sufficient. Displaying optic flow devoid of landmarks during the motion and pointing phase was insufficient for enabling automatic spatial updating, but could not be entirely ignored either. Interestingly, additional physical motion cues hardly improved performance, and were insufficient for affording automatic spatial updating. The results are discussed in the context of the mental transformation hypothesis and the sensorimotor interference hypothesis, which associates difficulties in imagined perspective switches to interference between the sensorimotor and cognitive (to-be-imagined) perspective.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Riecke__06_PsychologicalResearch_onlinePublication__Spatial_Updating_in_Virtual_Reality_-_The_Sufficiency_of_Visual_Information_3768[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/321247260x5446j0/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00426-006-0085-z}, author = {Riecke, BE and Cunningham, DW and B{\"u}lthoff, HH} } @Article { 3767, title = {Cognitive Factors can Influence Self-Motion Perception (Vection) in Virtual Reality}, journal = {ACM Transactions on Applied Perception}, year = {2006}, month = {7}, volume = {3}, number = {3}, pages = {194-216}, abstract = {Research on self-motion perception and simulation has traditionally focussed on the contribution of physical stimulus properties (bottom-up factors) using abstract stimuli. Here, we demonstrate that cognitive (top-down) mechanisms like ecological relevance and presence evoked by a virtual environment can also enhance visually induced self-motion illusions (vection). In two experiments, naive observers were asked to rate presence and the onset, intensity, and convincingness of circular vection induced by different rotating visual stimuli presented on a curved projection screen (FOV: 54\(^{\circ}\)\(\times\)45\(^{\circ}\)). Globally consistent stimuli depicting a natural 3D scene proved more effective in inducing vection and presence than inconsistent (scrambled) or unnatural (upside-down) stimuli with similar physical stimulus properties. Correlation analyses suggest a direct relationship between spatial presence and vection. We propose that the spatial reference frame evoked by the naturalistic environment increased the believability of the visual stimulus, such that it was more easily accepted as a stable scene with respect to which visual motion is more likely to be judged as self-motion than object-motion. This work extends our understanding of mechanisms underlying self-motion perception, and might thus help to improve the effectiveness and believability of Virtual Reality applications.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Riecke__06_TAP__Cognitive_Factors_can_Influence_Self_Motion_Perception_-Vection-_in_Virtual_Reality__asPrinted_3767[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1166087.1166091}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {http://doi.acm.org/10.1145/1166087.1166091}, author = {Riecke, BE and Schulte-Pelkum, J and Avraamides, MN and von der Heyde, M and B{\"u}lthoff, HH} } @Article { 4134, title = {Image-based material editing}, journal = {ACM Transactions on Graphics}, year = {2006}, month = {7}, volume = {25}, number = {3}, pages = {654-663}, abstract = {Photo editing software allows digital images to be blurred, warped or re-colored at the touch of a button. However, it is not currently possible to change the material appearance of an object except by painstakingly painting over the appropriate pixels. Here we present a method for automatically replacing one material with another, completely different material, starting with only a single high dynamic range image as input. Our approach exploits the fact that human vision is surprisingly tolerant of certain (sometimes enormous) physical inaccuracies, while being sensitive to others. By adjusting our simulations to be careful about those aspects to which the human visual system is sensitive, we are for the first time able to demonstrate significant material changes on the basis of a single photograph as input.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/ImageBasedMaterialEditing_4134[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {http://doi.acm.org/10.1145/1179352.1141937}, author = {Kahn, EA and Reinhard, E and Fleming, RW and B{\"u}lthoff, HH} } @Article { 3609, title = {A search advantage for faces learned in motion}, journal = {Experimental Brain Research}, year = {2006}, month = {6}, volume = {171}, number = {4}, pages = {436-447}, abstract = {Recently there has been growing interest in the role that motion might play in the perception and representation of facial identity. Most studies have considered old/new recognition as a task. However, especially for non-rigid motion, these studies have often produced contradictory results. Here, we used a delayed visual search paradigm to explore how learning is affected by non-rigid facial motion. In the current studies we trained observers on two frontal view faces, one moving non-rigidly, the other a static picture. After a delay, observers were asked to identify the targets in static search arrays containing 2, 4 or 6 faces. On a given trial target and distractor faces could be shown in one of five viewpoints, frontal, 22 or 45 degrees to the left or right. We found that familiarizing observers with dynamic faces led to a constant reaction time advantage across all set sizes and viewpoints compared to static familiarization. This suggests that non-rigid motion affects identity decisions even across exten ded periods of time and changes in viewpoint. Furthermore, it seems as if such effects may be difficult to observe using more traditional old/new recognition tasks.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Pilz_EBR_2006_3609[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://springerlink.metapress.com/content/765k65n8lq107352/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-005-0283-8}, author = {Pilz, KS and Thornton, IM and B{\"u}lthoff, HH} } @Article { 3521, title = {Comparing view sensitivity in shape discrimination to shape sensitivity in view discrimination}, journal = {Perception and Psychophysics}, year = {2006}, month = {5}, volume = {68}, number = {4}, pages = {655-673}, abstract = {In three picture-picture matching experiments, the effects of a view change on our ability to detect a shape change (Experiments 1 and 2) were contrasted with the effects of a shape change on our ability to detect a view change (Experiment 3). In each experiment, both view changes and shape changes influenced performance. However, shape changes had more influence than did view changes in the shape change detection task. Conversely, view changes were more influential when the task was to detect view changes. Thus, the participants could often discriminate between the effects of shape changes and the effects of view changes. The disruptive effect of task-irrelevant changes (view changes in the first two experiments; shape changes in the final experiment) does not support stankiewicz‘s (2002) claim that information about viewpoint and about shape can be estimated independently by human observers. However, the greater effect of variation in the task-relevant than in the task-irrelevant dimens ion indicates that the observers were moderately successful at disregarding irrelevant changes.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/835150p4781x05u7/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.3758/BF03208766}, author = {Lawson, R and B{\"u}lthoff, HH} } @Article { 3770, title = {Recognising novel deforming objects}, journal = {Visual Cognition}, year = {2006}, month = {5}, volume = {14}, number = {1}, pages = {85-88}, abstract = {Current theories of visual object recognition tend to focus on static properties, particularly shape. Nonetheless, visual perception is a dynamic experience–as a result of active observers or moving objects. Here, we investigate whether dynamic information can influence visual object-learning. Three learning experiments were conducted that required participants to learn and subsequently recognize different non-rigid objects that deformed over time. Consistent with previous studies of rigid depth-rotation, our results indicate that human observers do represent object-motion. Furthermore, our data suggest that dynamic information could compensate for when static cues are less reliable, for example, as a result of viewpoint variation.}, department = {Department B{\"u}lthoff}, web_url = {http://www.informaworld.com/smpp/ftinterface\verb=~=content=a747834181\verb=~=fulltext=713240930}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1080/13506280600627756}, author = {Chuang, L and Vuong, QC and Thornton, IM and B{\"u}lthoff, HH} } @Article { 2825, title = {An advantage for detecting dynamic targets in natural scenes}, journal = {Journal of Vision}, year = {2006}, month = {1}, volume = {6}, number = {1}, pages = {87-96}, abstract = {In the present study we tested the extent to which observers use dynamic information to detect targets in natural scenes. For this purpose, we used composite images in which target sequences were superimposed onto distractor sequences. We varied target visibility in the composite sequence, and the presence or absence of motion. Across four experiments, we found a dynamic advantage for target detection: Observers performed more accurately with dynamic than static target scenes. This advantage depended on the availability of target motion, irrespective of whether the target was upright or inverted in the image plane (Experiments 1-3). The magnitude of this advantage also depended on the availability of segmentation cues (Experiments 1 and 2) and on the distractors used (Experiments 2 and 4). Overall, the dynamic advantage reported extends previous work using isolated dynamic objects to more complex scenes.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Vuongetal2006_2825[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/6/1/8/Vuong-2006-jov-6-1-8.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, Tuebingen}, language = {en}, DOI = {10.1167/6.1.8}, author = {Vuong, QC and Hof, AF and B{\"u}lthoff, HH and Thornton, IM} } @Article { 3520, title = {Classification of Faces in Man and Machine}, journal = {Neural Computation}, year = {2006}, month = {1}, volume = {18}, number = {1}, pages = {143-165}, abstract = {We attempt to shed light on the algorithms humans use to classify images of human faces according to their gender. For this, a novel methodology combining human psychophysics and machine learning is introduced. We proceed as follows. First, we apply principal component analysis (PCA) on the pixel information of the face stimuli. We then obtain a data set composed of these PCA eigenvectors combined with the subjects' gender estimates of the corresponding stimuli. Second, we model the gender classification process on this data set using a separating hyperplane (SH) between both classes. This SH is computed using algorithms from machine learning: the support vector machine (SVM), the relevance vector machine, the prototype classifier, and the K-means classifier. The classification behavior of humans and machines is then analyzed in three steps. First, the classification errors of humans and machines are compared for the various classifiers, and we also assess how well machines can recreate the subjects' internal decision boundary by studying the training errors of the machines. Second, we study the correlations between the rank-order of the subjects' responses to each stimulus—the gender estimate with its reaction time and confidence rating—and the rank-order of the distance of these stimuli to the SH. Finally, we attempt to compare the metric of the representations used by humans and machines for classification by relating the subjects' gender estimate of each stimulus and the distance of this stimulus to the SH. While we show that the classification error alone is not a sufficient selection criterion between the different algorithms humans might use to classify face stimuli, the distance of these stimuli to the SH is shown to capture essentials of the internal decision space of humans.Furthermore, algorithms such as the prototype classifier using stimuli in the center of the classes are shown to be less adapted to model human classification behavior than algorithms such as the SVM based on stimuli close to the boundary between the classes.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/GraWicBueSch06_3520[0].pdf}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, web_url = {http://www.mitpressjournals.org/doi/abs/10.1162/089976606774841611}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1162/089976606774841611}, author = {Graf, ABA and Wichmann, FA and B{\"u}lthoff, HH and Sch{\"o}lkopf, B} } @Article { 3776, title = {Learning from Humans: Computational Modeling of Face Recognition}, journal = {Network}, year = {2005}, month = {12}, volume = {16}, number = {4}, pages = {401-418}, abstract = {In this paper we propose a computational architecture of face recognition based on evidence from cognitive research. Specifically, several recent psychophysical experiments have shown that humans process faces by a combination of configural and component information. Using an appearance-based implementation of this architecture based on low-level features and their spatial relations we were able to model aspects of human performance found in psychophysical studies. Furthermore, results from additional computational recognition experiments show that our framework is able to achieve excellent recognition performance even under large view rotations. Our interdisciplinary study is an example of how results from cognitive research can be used to construct recognition systems with increased performance. Finally, our modeling results also make new experimental predictions that will be tested in further psychophysical studies thus effectively closing the loop between psychophysical experimentation and computational m odeling.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/learning_from_humans_computational_modeling_of_face_recognition_3776[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.informaworld.com/smpp/ftinterface\verb=~=content=a748094272\verb=~=fulltext=713240930}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1080/09548980500508844}, author = {Wallraven, C and Schwaninger, A and B{\"u}lthoff, HH} } @Article { 3300, title = {Similar cortical correlates underlie visual object identification and orientation judgment}, journal = {Neuropsychologia}, year = {2005}, month = {8}, volume = {43}, number = {14}, pages = {2101-2108}, abstract = {Visual object perception has been suggested to follow two different routes in the human brain: a ventral, view-invariant occipital–temporal route processes object identity, whereas a dorsal, view-dependent occipital–parietal route processes spatial properties of an object. Using fMRI, we addressed the question whether these routes are exclusively involved in either object recognition or spatial representation. We presented subjects with images of natural objects and involved them either in object identification or object orientation judgment task. For both tasks, we observed activation in ventro-temporal as well as parietal areas bilaterally, with significantly stronger responses for the orientation judgment in both ventro-temporal as well as parietal areas. Our findings suggest that object identification and orientation judgment do not follow strictly separable cortical pathways, but rather involve both the dorsal and the ventral stream.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Altmann-etal-Neuropsychologia-2005_3300[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {doi:10.1016/j.neuropsychologia.2005.03.015}, author = {Altmann, C and Grodd, W and Kourtzi, Z and B{\"u}lthoff, HH and Karnath, H-O} } @Article { 3465, title = {Low-Level Images Cues in the Perception of Translucent Materials}, journal = {ACM Transactions on Applied Perception}, year = {2005}, month = {7}, volume = {2}, number = {3}, pages = {346-382}, abstract = {When light strikes a translucent material (such as wax, milk or fruit flesh), it enters the body of the object, scatters and re-emerges from the surface. The diffusion of light through translucent materials gives them a characteristic visual softness and glow. What image properties underlie this distinctive appearance? What cues allow us to tell whether a surface is translucent or opaque? Previous work on the perception of semi-transparent materials was based on a very restricted physical model of thin filters [Metelli 1970; 1974a,b]. However, recent advances in computer graphics [Jensen et al. 2000; Jensen and Buhler 2002] allow us to efficiently simulate the complex sub-surface light transport effects that occur in real translucent objects. Here we use this model to study the perception of translucency, using a combination of psychophysics and image statistics. We find that many of the cues that were traditionally thought to be important for semi-transparent filters (e.g., X-junctions) are not relevant for solid translucent objects. We discuss the role of highlights, colour, object size, contrast, blur and lighting direction in the perception of translucency. We argue that the physics of translucency are too complex for the visual system to estimate intrinsic physical parameters by inverse optics. Instead, we suggest that we identify translucent materials by parsing them into key regions and by gathering image statistics from these regions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/fleming-buelthoff-acm-tap-2005_3465[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1077399.1077409}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {doi.acm.org/10.1145/1077399.1077409}, author = {Fleming, R and B{\"u}lthoff, HH} } @Article { 3540, title = {Manipulating video sequences to determine the components of conversational facial expressions}, journal = {ACM Transactions on Applied Perception}, year = {2005}, month = {7}, volume = {2}, number = {3}, pages = {251-269}, abstract = {Communication plays a central role in everday life. During an average conversation, information is exchanged in a variety of ways, including through facial motion. Here, we employ a custom, model-based image manipulation technique to selectively ''freeze'' portions of a face in video recordings in order to determine the areas that are sufficient for proper recognition of nine conversational expressions. The results show that most expressions rely primarily on a single facial area to convey meaning, with different expressions using different areas. The results also show that already the combination of rigid head, eye, eyebrow, and mouth motions is sufficient to produce expressions that are as easy to recognize as the original, unmanipulated recordings. Finally, the results show that the manipulation technique introduced few perceptible artifacts into the altered video sequences. This fusion of psychophysics and computer graphics techniques provides not only fundamental insights into human perception and cognitio n, but also yields the basis for a systematic description of what needs to move in order to produce realistic, recognizable conversational facial animations.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/cunningham-etal-ACM-tap-2005_3540[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1077399.1077404}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {doi.acm.org/10.1145/1077399.1077404}, author = {Cunningham, D and Kleiner, M and Wallraven, C and B{\"u}lthoff, H} } @Article { 3029, title = {Visual cues can be sufficient for triggering automatic, reflexlike spatial updating}, journal = {ACM Transactions on Applied Perception}, year = {2005}, month = {7}, volume = {2}, number = {3}, pages = {183-215}, abstract = {''Spatial updating'' refers to the process that automatically updates our egocentric mental representation of our immediate surround during self-motions, which is essential for quick and robust spatial orientation. To investigate the relative contribution of visual and vestibular cues to spatial updating, two experiments were performed in a high-end Virtual Reality system. Participants were seated on a motion platform and saw either the surrounding room or a photorealistic virtual model presented via head-mounted display or projection screen. After upright rotations, participants had to point ''as accurately and quickly as possible'' to previously-learned targets that were outside of the current field of view (FOV). Spatial updating performance, quantified as response time, config-uration error, and pointing error, was comparable in the real and virtual reality conditions when the FOV was matched. Two further results challenge the prevailing basic assumptions about spatial updating: First, automatic, reflex-like spatial updating occurred without any physical motion, i.e., visual motion information from a known scene alone can indeed be sufficient, especially for large FOVs. Second, continuous motion information is not, in fact, mandatory for spatial updating - merely presenting static images of new orientations proved sufficient, motivating our distinction between continuous and instant-based spatial updating.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/riecke-heyde-buelthoff-acm-tap-2005_3029[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://doi.acm.org/10.1145/1077399.1077401}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1077399.1077401}, author = {Riecke, B and von der Heyde, M and B{\"u}lthoff, HH} } @Article { 3475, title = {Is prior knowledge of object geometry used in visually guided reaching?}, journal = {Journal of Vision}, year = {2005}, month = {6}, volume = {5}, number = {6}, pages = {504-514}, abstract = {We investigated whether humans use prior knowledge of the geometry of faces in visually guided reaching. When viewing the inside of a mask of a face, the mask is often perceived as being a normal (convex) face, instead of the veridical, hollow (concave) shape. In this ''hollow-face illusion,'' prior knowledge of the shape of faces dominates perception, even when in conflict with information from binocular disparity. Computer images of normal and hollow faces were presented, such that depth information from binocular disparity was consistent or in conflict with prior knowledge of the geometry. Participants reached to touch either the nose or cheek of the faces or gave verbal estimates of the corresponding distances. We found that reaching to touch was dominated by prior knowledge of face geometry. However, hollow faces were estimated to be flatter than normal faces. This suggests that the visual system combines binocular disparity and prior assumptions, rather than completely discounting one or the other. When c omparing the magnitude of the hollow-face illusion in reaching and verbal tasks, we found that the flattening effect of the illusion was similar for verbal and reaching tasks.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Hartung-2005-jov-5-6-2_3475[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://journalofvision.org/5/6/2/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/5.6.2}, author = {Hartung, B and Schrater, P and B{\"u}lthoff, HH and Kersten, D and Franz, V} } @Article { 3438, title = {3D shape perception from combined depth cues in human visual cortex}, journal = {Nature Neuroscience}, year = {2005}, month = {5}, volume = {8}, number = {6}, pages = {820-827}, abstract = {Our perception of the world‘s three-dimensional (3D) structure is critical for object recognition, navigation and planning actions. To accomplish this, the brain combines different types of visual information about depth structure, but at present, the neural architecture mediating this combination remains largely unknown. Here, we report neuroimaging correlates of human 3D shape perception from the combination of two depth cues. We measured fMRI responses while observers judged the 3D structure of two sequentially presented images of slanted planes defined by binocular disparity and perspective. We compared the behavioral and fMRI responses evoked by changes in one or both of the depth cues. fMRI responses in extrastriate areas (hMT+/V5 and lateral occipital complex), rather than responses in early retinotopic areas, reflected differences in perceived 3D shape, suggesting ‘combined-cue‘ representations in higher visual areas. These findings provide insight into the neural circuits engaged when the human brain combines different information sources for unified 3D visual perception.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3438.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.nature.com/neuro/journal/v8/n6/pdf/nn1461.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1038/nn1461}, author = {Welchman, AE and Deubelius, A and Conrad, V and B{\"u}lthoff, HH and Kourtzi, Z} } @Article { 2232, title = {An empirical approach to the experience of architectural space in virtual reality—exploring relations between features and affective appraisals of rectangular indoor spaces}, journal = {Automation in Construction}, year = {2005}, month = {3}, volume = {14}, number = {2: eCAADe 2003, Digital Design}, pages = {165-172}, abstract = {In the presented exploratory study, quantitative relations between the experience of architectural spaces and physical properties were investigated using virtual reality (VR) simulations. Geometric properties from a component-based description of rectangular rooms were tested on their suitability as predictor variables for experiential qualities. In a virtual-reality-based perceptual experiment, qualities of 16 vacant rectangular interiors were rated in eight principal categories by 16 participants using the semantic differential scaling technique. The simulated scenes were automatically generated by means of a custom made utility that also provided for the component-based room descriptions. The data analysis revealed strong correlations between several scene features and the averaged rated experience. For example, a preference for ratios near to the golden section could be observed for spatial proportions, which are not directly perceivable. Altogether, a set of five widely independent factors (openness, two room proportions, room area, and balustrade height) turned out to be most effective for describing the observed variance in the attributed experiential qualities. The combination of realistic virtual reality simulations and psychophysical data raising methods proved to be an effective means for basic architectural research. Several quantitative relations between physical properties and the emotional experience of architectural space could be demonstrated.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2232.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science/article/pii/S092658050400069X}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Graz, Austria}, DOI = {10.1016/j.autcon.2004.07.009}, author = {Franz, G and von der Heyde, M and B{\"u}lthoff, HH} } @Article { 2543, title = {Orientation congruency effects for familiar objects: Coordinate transformations in object recognition}, journal = {Psychological Science}, year = {2005}, month = {3}, volume = {16}, number = {3}, pages = {214-221}, abstract = {How do we recognize objects after spatial transformations? Recent neurocomputational models proposed that object recognition is based on coordinate transformations which align memory and stimulus representations. If the recognition of disoriented objects is achieved by adjusting a coordinate system (or reference frame) then recognition should be facilitated when the object is preceded by a different object in the same orientation. Two objects were presented in close temporal contiguity in brief masked displays, either in congruent or incongruent picture plane orientations. In two experiments, naming accuracy was higher for congruent orientations. The congruency effect was independent of superordinate category membership (Experiment 1), and was found for objects with different (horizontal or vertical) main axis of elongation (Experiment 2). The results indicate congruency effects for common familiar objects, even for dissimilar shapes. The findings are compatible with models in which object recognition is achi eved by an adjustment of a perceptual coordinate system.}, department = {Department B{\"u}lthoff}, web_url = {http://www.blackwell-synergy.com/doi/pdf/10.1111/j.0956-7976.2005.00806.x}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1111/j.0956-7976.2005.00806.x}, author = {Graf, M and Kaping, D and B{\"u}lthoff, HH} } @Article { 3341, title = {The dynamics of visual pattern masking in natural scene processing: A magnetoencephalography study}, journal = {Journal of Vision}, year = {2005}, month = {3}, volume = {5}, number = {3}, pages = {275-286}, abstract = {We investigated the dynamics of natural scene processing and mechanisms of pattern masking in a scene-recognition task. Psychophysical recognition performance and the magnetoencephalogram (MEG) were recorded simultaneously. Photographs of natural scenes were briefly displayed and in the masked condition immediately followed by a pattern mask. Viewing the scenes without masking elicited a transient occipital activation that started approximately 70 ms after the pattern onset, peaked at 110 ms, and ended after 170 ms. When a mask followed the target an additional transient could be reliably identified in the MEG traces. We assessed psychophysical performance levels at different latencies of this transient. Recognition rates were reduced only when the additional activation produced by the pattern mask overlapped with the initial 170 ms of occipital activation from the target. Our results are commensurate with an early cortical locus of pattern masking and indicate that 90 ms of undistorted cortical processing is necessary to reliably recognize a scene. Our data also indicate that as little as 20 ms of undistorted processing is sufficient for above-chance discrimination of a scene from a distracter.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Rieger-2005-jov-5-3-10_3341[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://journalofvision.org/5/3/10/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1167/5.3.10}, author = {Rieger, J and Braun, C and B{\"u}lthoff, HH and Gegenfurtner, K} } @Article { 2602, title = {Effects of rearranged Vision on Event-related Lateralizations of the EEG during Pointing}, journal = {Biological Psychology}, year = {2005}, month = {1}, volume = {68}, number = {1}, pages = {15-39}, abstract = {We used event-related lateralizations of the EEG (ERLs) and reversed vision to study visuomotor processing with conflicting proprioceptive and visual information during pointing. Reversed vision decreased arm-related lateralization, probably reflecting the simultaneous activity of left and right arm specific neurons: Neurons in the hemisphere contralateral to the observed action were probably activated by visual feedback, neurons in the hemisphere contralateral to the response side by the somatomotor feedback. Lateralization related to the target in parietal cortex increased, indicating that visual to motor transformation in parietal cortex required additional time and resources with reversed vision. A short period of adaptation to an additional lateral displacement of the visual field increased arm-contralateral activity in parietal cortex during the movement. This is in agreement with the Clower et al. study (1996), which showed that adaptation to a lateral displacement of the visual field is reflected in increased parietal involvement during pointing. Key words: EEG, event-related lateralizations, reversed vision, pointing}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2602.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T4T-4CFV7BT-1-3J\&_cdi=4983\&_user=29041\&_orig=search\&_coverDate=01\%2F31\%2F2005\&_sk=999319998\&view=c\&wchp=dGLzVlz-zSkWW\&md5=a9c41a1fc1725ca7fd61d1af47d51913\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1016/j.biopsycho.2004.03.016}, author = {Berndt, I and Franz, VH and B{\"u}lthoff, HH and G{\"o}tz, KG and Wascher, E} } @Article { 2818, title = {Visual, haptic and crossmodal recognition of scenes}, journal = {Experimental Brain Research}, year = {2004}, month = {10}, day = {15}, volume = {161}, number = {2}, pages = {233-242}, abstract = {Real world scene perception can often involve more than one sensory modality. Here we investigated the visual, haptic and crossmodal recognition of scenes of familiar objects. In three experiments participants first learned a scene of objects arranged in random positions on a platform. After learning, the experimenter swapped the position of two objects in the scene and the task for the participant was to identify the two swapped objects. In Experiment 1, we found a cost in scene recognition performance when there was a change in sensory modality and scene orientation between learning and test. The cost in crossmodal performance was not due to the participants verbally encoding the objects (Experiment 2) or by differences between serial and parallel encoding of the objects during haptic and visual learning respectively (Experiment 3). Instead, our findings suggest that differences between visual and haptic representations of space may affect the recognition of scenes of objects across these modalities.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2818.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/media/MGATTNWTTR7A9ALWUP4U/Contributions/W/6/3/W/W63WV3B2LYQW3G1M.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/s00221-004-2067-y}, author = {Newell, F and Woods, AT and Mernagh, M and B{\"u}lthoff, HH} } @Article { 3055, title = {Computational Modeling of Face Recognition Based on Psychophysical Experiments}, journal = {Swiss Journal of Psychology}, year = {2004}, month = {9}, volume = {63}, number = {3}, pages = {207-215}, abstract = {Recent results from psychophysical studies are discussed which clearly show that face processing is not only holistic. Humans do encode face parts (component information) in addition to information about the spatial interrelationship of facial features (global configural information). Based on these findings we propose a computational architecture of face recognition, which implements a component and configural route for encoding and recognizing faces. Modeling results showed a striking similarity between human psychophysical data and the computational model. In addition, we could show that our framework is able to achieve good recognition performance even under large view rotations. Thus, our study is an example of how an interdisciplinary approach can provide a deeper understanding of cognitive processes and lead to further insights in human psychophysics as well as computer vision.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/SchWalBul2004_3055[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1024/1421-0185.63.3.207}, author = {Schwaninger, A and Wallraven, C and B{\"u}lthoff, HH} } @Article { 3574, title = {Editorial}, journal = {ACM Transactions on Applied Perception}, year = {2004}, month = {7}, volume = {1}, number = {1}, pages = {1-2}, note = {not reviewed}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1008723\&CFID=31223694\&CFTOKEN=80756307}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1145/1008722.1008723}, author = {Reinhard, E and B{\"u}lthoff, HH} } @Article { 2867, title = {The role of image size in the recognition of conversational facial expressions}, journal = {Computer Animation \& Virtual Worlds}, year = {2004}, month = {7}, volume = {15}, number = {3-4}, pages = {305-310}, abstract = {Facial expressions can be used to direct the flow of a conversation as well as to improve the clarity of communication. The critical physical differences between expressions can, however, be small and subtle. Clear presentation of facial expressions in applied settings, then, would seem to require a large conversational agent. Given that visual displays are generally limited in size, the usage of a large conversational agent would reduce the amount of space available for the display of other information. Here, we examine the role of image size in the recognition of facial expressions. The results show that conversational facial expressions can be easily recognized at surprisingly small image sizes.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2867.pdf}, department = {Department B{\"u}lthoff}, web_url = {doi.acm.org/10.1145/1077399.1077404}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {doi.acm.org/10.1145/1077399.1077404}, author = {Cunningham, D and Nusseck, M and Wallraven, C and B{\"u}lthoff, HH} } @Article { 2507, title = {Merging the Senses into a Robust Percept}, journal = {Trends in Cognitive Sciences}, year = {2004}, month = {4}, volume = {8}, number = {4}, pages = {162-169}, abstract = {For perceiving the environment our brain uses multiple sources of sensory information derived from several different modalities, including vision, touch and audition. All these different sources of information have to be efficiently merged to form a coherent and robust percept. Here we highlight some of the mechanisms underlying this merging of the senses in the brain. We show that depending on the type of information different combination and integration strategies are used and that prior knowledge is often required for interpreting the sensory signals.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2507.pdf}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VH9-4BVP99P-1-N\&_cdi=6061\&_user=29041\&_orig=search\&_coverDate=04\%2F30\%2F2004\&_sk=999919995\&view=c\&wchp=dGLzVzz-zSkzV\&md5=7e20182e5625df31980e8f9a12c4a338\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max-Planck-Institut f{\"u}r Biologische Kybernetik}, language = {en}, DOI = {10.1016/j.tics.2004.02.002}, author = {Ernst, MO and B{\"u}lthoff, HH} } @Article { 2584, title = {Interactions between view changes and shape changes in picture-picture matching}, journal = {Perception}, year = {2003}, month = {12}, volume = {32}, number = {12}, pages = {1465-1498}, abstract = {Four experiments are reported in which pictures of different morphs of novel, complex, 3-D objects, similar to objects which we must identify in the real world, were presented. We investigated how changes of viewpoint influence our ability to discriminate between morphs. View changes had a powerful effect on performance in picture - picture matching tasks when similarly shaped morphs had to be discriminated. Shape changes were detected faster and more accurately when morphs were depicted from the same rather than different views. In contrast, view change had no effect when dissimilarly shaped morphs had to be discriminated. This interaction between the effects of view change and shape change was found both for simultaneous stimulus presentation and for sequential presentation with interstimulus intervals up to 3600 ms. The interaction was found after repeated presentations of the stimuli before the matching task and after practice at the matching task as well as after no such pre-exposure to the stimuli or to the task. The results demonstrate the difficulty in activating abstract, view-insensitive representations to help to achieve object constancy, even when matching over long interstimulus intervals or after stimuli have already been seen many times.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2584.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p5031}, series = {12}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p5031}, author = {Lawson, R and B{\"u}lthoff, HH and Dumbell, S} } @Article { KourtziEGB2003, title = {Representation of the perceived 3-D object shape in the human lateral occipital complex}, journal = {Cerebral Cortex}, year = {2003}, month = {9}, volume = {13}, number = {9}, pages = {911-920}, abstract = {We used human functional magnetic resonance imaging (fMRI) to test whether the human lateral occipital complex (LOC), an area known to be involved in the analysis of visual shape, represents the perceived 3-D shape of objects or simply their 2-D contours. We employed an fMRI adaptation paradigm, in which repeated presentation of a stimulus results in decreased responses compared to responses to different stimuli. We found adaptation in the LOC for images of objects with the same perceived 3-D shape structure but different 2-D contours that resulted from small rotations of the objects in the frontal plane or in depth. However, no adaptation was observed in the LOC for images of objects that had the same 2-D contours but differed in their perceived 3-D shape; namely, 2-D silhouettes versus 3-D shaded images of objects, or convex versus concave objects. Differences in the fMRI adaptation responses across subregions in the LOC suggest that different neural populations in the LOC may mediate different mechanisms for the processing of object features.}, department = {Department B{\"u}lthoff}, web_url = {http://cercor.oxfordjournals.org/content/13/9/911.full.pdf+html}, DOI = {10.1093/cercor/13.9.911}, author = {Kourtzi, Z and Erb, M and Grodd, W and B{\"u}lthoff, HH} } @Article { 1367, title = {The use of facial motion and facial form during the processing of identity.}, journal = {Vision Research}, year = {2003}, month = {8}, volume = {43}, number = {18}, pages = {1921-1936}, abstract = {Previous research has shown that facial motion can carry information about age, gender, emotion and, at least to some extent, identity. By combining recent computer animation techniques with psychophysical methods, we show that during the computation of identity the human face recognition system integrates both types of information: individual non-rigid facial motion and individual facial form. This has important implications for cognitive and neural models of face perception, which currently emphasize a separation between the processing of invariant aspects (facial form) and changeable aspects (facial motion) of faces.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1367.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-48WN4BB-2-23\&_cdi=4873\&_user=29041\&_pii=S0042698903002360\&_origin=browse\&_coverDate=08\%2F31\%2F2003\&_sk=999569981\&view=c\&wchp=dGLzVlz-zSkWz\&md5=042e142b505cd7c3f95cc61336efc7e9\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0042-6989(03)00236-0}, author = {Knappmeyer, B and Thornton, IM and B{\"u}lthoff, HH} } @Article { 2023, title = {Extrinsic cues aid shape recognition from novel viewpoints}, journal = {Journal of Vision}, year = {2003}, month = {4}, volume = {3}, number = {3:1}, pages = {183-198}, abstract = {It has been shown previously that the visual recognition of shape is susceptible to the mismatch between the retinal input and its representation in long-term memory, especially when this mismatch arises from rotations in depth. One possibility is that the visual recognition system deals with such mismatch by a transformation of the input or the representation thereby bringing both into alignment for comparison. In either case, knowing what transformation has taken place should facilitate recognition. In natural circumstances, objects do not disappear and appear in different orientations inexplicably and an observer usually knows what to expect according to the context. This context includes the environment, and the history of the observers’ movements, which specify the transient relationship between the object, the environment and the observer. We used interactive computer graphics to study the effects of providing observers with either implicit or explicit indications of their view transformations in the recognition of a class of shape found previously to be highly view-dependent. Results show that these cues aid recognition to varying degrees but mostly for oblique views and primarily in terms of accuracy not response times. These results provide evidence for egocentric encoding of shape and suggest that knowing ones' transformation in view helps to reduce the problem space involved in matching a shape percept with a mental representation.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2023.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://journalofvision.org/3/3/1/}, series = {3}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1167/3.3.1}, author = {Christou, CG and Tjan, BS and B{\"u}lthoff, HH} } @Article { 1640, title = {Grasp effects of the Ebbinghaus illusion: Obstacle-avoidance is not the explanation.}, journal = {Experimental Brain Research}, year = {2003}, month = {4}, volume = {149}, number = {4}, pages = {470-477}, abstract = {The perception-versus-action hypothesis states that visual information is processed in two different streams, one for visual awareness (or perception) and one for motor performance. Previous reports that the Ebbinghaus illusion deceives perception but not grasping seemed to indicate that this dichotomy between perception and action was fundamental enough to be reflected in the overt behavior of non-neurological, healthy humans. Contrary to this view we show that the Ebbinghaus illusion affects grasping to the same extent as perception. We also show that the grasp effects cannot be accounted for by non-perceptual obstacle avoidance mechanisms as has recently been suggested. Instead, even subtle variations of the Ebbinghaus illusion affect grasping in the same way as they affect perception. Our results suggest that the same signals are responsible for the perceptual effects and for the motor effects of the Ebbinghaus illusion. This casts doubt on one line of evidence, which used to strongly favor the perception-versus-action hypothesis.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1640.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/nhwvbfvvap1v0gp0/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/s00221-002-1364-6}, author = {Franz, VH and B{\"u}lthoff, HH and Fahle, M} } @Article { 2034, title = {A chimeric point-light walker}, journal = {Perception}, year = {2003}, month = {3}, volume = {32}, number = {3}, pages = {377-383}, abstract = {Ambiguity has long been used as a probe into visual processing. Here, we describe a new dynamic ambiguous figure-the chimeric point-light walker--which we hope will prove to be a useful tool for exploring biological motion. We begin by describing the construction of the stimulus and discussing the compelling finding that, when presented in a mask, observers consistently fail to notice anything odd about the walker, reporting instead that they are watching an unambiguous figure moving either to the left or right. Some observers report that the initial percept fluctuates, moving first to the left, then to the right, or vice versa; others always perceive a constant direction. All observers, when briefly shown the unmasked ambiguous figure, have no difficulty in perceiving the novel motion pattern once the mask is returned. These two findings--the initial report of unambiguous motion and the subsequent 'primed' perception of the ambiguity--are both consistent with an important role for top-down processing in biological motion. We conclude by suggesting several domains within the realm of biological-motion processing where this simple stimulus may prove to be useful.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2034.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p5010}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p5010}, author = {Thornton, IM and Vuong, QC and B{\"u}lthoff, HH} } @Article { 2013, title = {Perceptual organization of local elements into global shapes in the human visual cortex}, journal = {Current Biology}, year = {2003}, month = {2}, volume = {13}, number = {4}, pages = {342-349}, abstract = {The question of how local image features on the retina are integrated into perceived global shapes is central to our understanding of human visual perception. Psychophysical investigations have suggested that the emergence of a coherent visual percept, or a ''good-Gestalt'', is mediated by the perceptual organization of local features based on their similarity. However, the neural mechanisms that mediate unified shape perception in the human brain remain largely unknown. Using human fMRI, we demonstrate that not only higher occipitotemporal but also early retinotopic areas are involved in the perceptual organization and detection of global shapes. Specifically, these areas showed stronger fMRI responses to global contours consisting of collinear elements than to patterns of randomly oriented local elements. More importantly, decreased detection performance and fMRI activations were observed when misalignment of the contour elements disturbed the perceptual coherence of the contours. However, grouping of the misaligned contour elements by disparity resulted in increased performance and fMRI activations, suggesting that similar neural mechanisms may underlie grouping of local elements to global shapes by different visual features (orientation or disparity). Thus, these findings provide novel evidence for the role of both early feature integration processes and higher stages of visual analysis in coherent visual perception.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2013.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VRT-47YXJ16-Y-1\&_cdi=6243\&_user=29041\&_pii=S0960982203000526\&_origin=\&_coverDate=02\%2F18\%2F2003\&_sk=999869995\&view=c\&wchp=dGLzVlz-zSkWW\&md5=ad173c6e65795870ea8edbb1c3d9af16\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0960-9822(03)00052-6}, author = {Altmann, CF and B{\"u}lthoff, HH and Kourtzi, Z} } @Article { 1827, title = {Gaze-eccentricity effects on road position and steering}, journal = {Journal of Experimental Psychology: Applied}, year = {2002}, month = {12}, volume = {8}, number = {4}, pages = {247-258}, abstract = {The effects of gaze-eccentricity on the steering of an automobile were studied. Drivers performed an attention task while attempting to drive down the middle of a straight road in a simulation. Steering was biased in the direction of fixation and deviation from the center of the road was proportional to the gaze direction until saturation at approximately 15 degrees gaze-angle from straight ahead. This effect remains when the position of the head was controlled and a reverse-steering task was used. Furthermore, the effect was not dependent upon speed, but reversed when the forward movement of the driver was removed from the simulation. Thus, small deviations in a driver's gaze can lead to significant impairments of the ability to drive a straight course.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1827.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6X06-484NKPN-4-1\&_cdi=7206\&_user=29041\&_pii=S1076898X03001692\&_origin=\&_coverDate=12\%2F31\%2F2002\&_sk=999919995\&view=c\&wchp=dGLbVlW-zSkzS\&md5=f176928f28f2589a996abf4c50b1924d\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1037/1076-898X.8.4.247}, author = {Readinger, WO and Chatziastros, A and Cunningham, DW and B{\"u}lthoff, HH and Cutting, JE} } @Article { 1202, title = {Visual Homing is possible without Landmarks: A Path Integration Study in Virtual Reality}, journal = {Presence: Teleoperators and Virtual Environments}, year = {2002}, month = {10}, volume = {11}, number = {5}, pages = {443-473}, abstract = {The literature often suggests that proprioceptive and especially vestibular cues are required for navigation and spatial orientation tasks involving rotations of the observer. To test this notion, we conducted a set of experiments in virtual environments where only visual cues were provided. Participants had to execute turns, reproduce distances or perform triangle completion tasks. Most experiments were performed in a simulated 3D field of blobs, thus restricting navigation strategies to path integration based on optic flow. For our experimental setup (half-cylindrical 180\(^{\circ}\) projection screen), optic flow information alone proved to be sufficient for untrained participants to perform turns and reproduce distances with negligible systematic errors, irrespective of movement velocity. Path integration by optic flow was sufficient for homing by triangle completion, but homing distances were biased towards the mean response. Additional landmarks that were only temporarily available did not improve homing performance. However, navigation by stable, reliable landmarks led to almost perfect homing performance. Mental spatial ability test scores correlated positively with homing performance especially for the more complex triangle completion tasks, suggesting that mental spatial abilities might be a determining factor for navigation performance. In summary, visual path integration without any vestibular or kinesthetic cues can be sufficient for elementary navigation tasks like rotations, translations, and triangle completion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1202.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://mitpress.mit.edu/catalog/item/default.asp?sid=7FFDB92B-EF42-408A-9F41-504F210447B3\&ttype=6\&tid=9224}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1162/105474602320935810}, author = {Riecke, BE and van Veen, HAHC and B{\"u}lthoff, HH} } @Article { 1942, title = {Categorical perception of familiar objects.}, journal = {Cognition}, year = {2002}, month = {9}, volume = {85}, number = {2}, pages = {113-143}, abstract = {We report three experiments where the categorical perception of familiar, three-dimensional objects was investigated. A continuum of shape change between 15 pairs of objects was created and the images along the continuum were used as stimuli. In Experiment 1 participants were first required to discriminate pairs of images of objects that lay along the shape continuum. Then participants were asked to classify each morph-image into one of two pre-specified classes. We found evidence for categorical perception in some but not all of our object pairs. In Experiment 2 we varied the viewpoint of the objects in the discrimination task and found that effects of categorical perception generalized across changes in view. In Experiment 3 similarity ratings for each object pair were collected. These similarity scores correlated with the degree of perceptual categorization found for the object pairs. Our findings suggest that some familiar objects are perceived categorically and that categorical perception is closely tied to inter-object perceptual similarity.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1942.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T24-461XKP0-5-1\&_cdi=4908\&_user=29041\&_pii=S001002770200104X\&_origin=\&_coverDate=09\%2F30\%2F2002\&_sk=999149997\&view=c\&wchp=dGLbVlW-zSkWb\&md5=dc47f2f2dbc69bc6eb7663ddb536f3f9\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0010-0277(02)00104-X}, author = {Newell, FN and B{\"u}lthoff, HH} } @Article { 1901, title = {Effects of pointing direction and direction predictability on event-related lateralizations of the EEG}, journal = {Human Movement Science}, year = {2002}, month = {9}, volume = {21}, number = {3}, pages = {387-410}, abstract = {In two experiments, we investigated hemispheric electroencephalography (EEG) differences in 9(12) healthy volunteers during pointing to lateral and central targets. The questions addressed were whether horizontal pointing direction and the predictability of pointing direction modulated hemispheric differences (event-related lateralizations of the EEG = ERLs). To vary pointing direction predictability, targets were displayed either randomly at one of nine different positions on a screen (random) or at the same horizontal position in five subsequent trials (sequenced) while vertical positions varied randomly. Event-related lateralizations (ERLs) varied with pointing direction. This was true across changes in target eccentricity and pointing distance. Foci of the ERLs were in premotor and posterior parietal cortex, which might reflect the critical involvement of these areas in the control of visually guided reaching. Direction predictability reduced the parietal and premotor ERL before pointing onset, probably reflecting a lesser effort in visuomotor transformation. Predictability also added an overlying N2pc component to the early ERL after target onset and increased direction effects during movement.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1901.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6V8T-46X947W-3-4S\&_cdi=5879\&_user=29041\&_pii=S0167945702001227\&_origin=\&_coverDate=09\%2F30\%2F2002\&_sk=999789996\&view=c\&wchp=dGLbVlz-zSkWA\&md5=95e50eaa055964e011de39582c75a51b\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0167-9457(02)00122-7}, author = {Berndt, I and Franz, VH and B{\"u}lthoff, HH and Wascher, E} } @Article { 1016, title = {An unexpected role for visual feedback in vehicle steering control}, journal = {Current Biology}, year = {2002}, month = {2}, volume = {12}, number = {4}, pages = {295-299}, abstract = {Some motor tasks can be completed, quite literally, with our eyes shut. Most people can touch their nose without looking or reach for an object after only a brief glance at its location. This distinction leads to one of the defining questions of movement control: is information gleaned prior to starting the movement sufficient to complete the task (open loop), or is feedback about the progress of the movement required (closed loop)? One task that has commanded considerable interest in the literature over the years is that of steering a vehicle, in particular lane-correction and lane-changing tasks. Recent work has suggested that this type of task can proceed in a fundamentally open loop manner, with feedback mainly serving to correct minor, accumulating errors. This paper reevaluates the conclusions of these studies by conducting a new set of experiments in a driving simulator. We demonstrate that, in fact, drivers rely on regular visual feedback, even during the well-practiced steering task of lane changing. Without feedback, drivers fail to initiate the return phase of the maneuver, resulting in systematic errors in final heading. The results provide new insight into the control of vehicle heading, suggesting that drivers employ a simple policy of ''turn and see,'' with only limited understanding of the relationship between steering angle and vehicle heading.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1016.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VRT-457VR7R-M-2\&_cdi=6243\&_user=29041\&_pii=S0960982202006851\&_origin=\&_coverDate=02\%2F19\%2F2002\&_sk=999879995\&view=c\&wchp=dGLzVzz-zSkzV\&md5=12b72611152f6a0ab7c0dc851ddf03fd\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0960-9822(02)00685-1}, author = {Wallis, GM and Chatziastros, A and B{\"u}lthoff, HH} } @Article { 644, title = {Object-selective responses in the human motion area MT/MST}, journal = {Nature Neuroscience}, year = {2002}, month = {1}, volume = {5}, number = {1}, pages = {17-18}, abstract = {The perception of moving objects and our successful interaction with them entail that the visual system integrates shape and motion information about objects. However, neuroimaging studies have implicated different human brain regions in the analysis of visual motion1, 2 (medial temporal cortex; MT/MST) and shape3, 4 (lateral occipital complex; LOC), consistent with traditional approaches in visual processing that attribute shape and motion processing to anatomically and functionally separable neural mechanisms. Here we demonstrate object-selective fMRI responses (higher responses for intact than for scrambled images of objects) in MT/MST, and especially in a ventral subregion of MT/MST, suggesting that human brain regions involved mainly in the processing of visual motion are also engaged in the analysis of object shape.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf644.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.nature.com/neuro/journal/v5/n1/pdf/nn780.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1038/nn780}, author = {Kourtzi, Z and B{\"u}lthoff, HH and Erb, M and Grodd, W} } @Article { 1927, title = {Artificial systems as models in biological cybernetics}, journal = {Behavioral and Brain Sciences}, year = {2001}, month = {12}, volume = {24}, number = {6}, pages = {1071-1072}, abstract = {From the perspective of biological cybernetics, ''real world'' robots have no fundamental advantage over computer simulations when used as models for biological behavior. They can even weaken biological relevance. From an engineering point of view, however, robots can benefit from solutions found in biological systems. We emphasize the importance of this distinction and give examples for artificial systems based on insect biology.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/artificial_systems_as_models_in_biological_cybernetics_1927[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://journals.cambridge.org/action/displayFulltext?type=1\&fid=136544\&jid=BBS\&volumeId=24\&issueId=06\&aid=136543\&bodyId=\&membershipNumber=\&societyETOCSession=}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1017/S0140525X0144012X}, author = {Neumann, T and Huber, S and B{\"u}lthoff, HH} } @Article { 34, title = {Driving in the future: Temporal visuomotor adaptation and generalization}, journal = {Journal of Vision}, year = {2001}, month = {11}, volume = {1}, number = {2:3}, pages = {88-98}, abstract = {Rapid and accurate visuomotor coordination requires tight spatial and temporal sensorimotor synchronization. The introduction of a sensorimotor or intersensory misalignment (either spatial or temporal) impairs performance on most tasks. For more than a century, it has been known that a few minutes of exposure to a spatial misalignment can induce a recalibration of sensorimotor spatial relationships, a phenomenon that may be referred to as spatial visuomotor adaptation. Here, we use a high-fidelity driving simulator to demonstrate that the sensorimotor system can adapt to temporal misalignments on very complex tasks, a phenomenon that we refer to as temporal visuomotor adaptation. We demonstrate that adapting on a single street produces an adaptive state that generalizes to other streets. This shows that temporal visuomotor adaptation is not specific to a single visuomotor transformation, but generalizes across a class of transformations. Temporal visuomotor adaptation is strikingly parallel to spatial visuomotor adaptation, and has strong implications for the understanding of visuomotor coordination and intersensory integration.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf34.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/1/2/3/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1167/1.2.3}, author = {Cunningham, DW and Chatziastros, A and von der Heyde, M and B{\"u}lthoff, HH} } @Article { 36, title = {Effects of visual illusions on grasping}, journal = {Journal of Experimental Psychology: Human Perception and Performance}, year = {2001}, month = {10}, volume = {27}, number = {5}, pages = {1124-1144}, abstract = {In 2 experiments, the Muller-Lyer illusion (F. C. Muller-Lyer, 1889; N = 16) and the parallel-lines illusion (W. Wundt, 1898; N = 26) clearly affected maximum preshape aperture in grasping (both ps < .001). The grasping effects were similar but not perfectly equal to the perceptual effects. Control experiments show that these differences can be attributed to problems in matching the perceptual task and the grasping task. A model is described stating the assumptions that are needed to compare the grasping effects and the perceptual effects of visual illusions. Further studies on the relationship between perception and grasping are reviewed. These studies provide no clear evidence for a dissociation between perception and grasping and therefore do not support the action versus perception hypothesis (A. D. Milner \& M. A. Goodale, 1995).}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/effects_of_visual_illusions_on_grasping_36[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://psycnet.apa.org/journals/xhp/27/5/1124.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1037/0096-1523.27.5.1124}, author = {Franz, V and Fahle, M and B{\"u}lthoff, HH and Gegenfurtner, K} } @Article { 51, title = {Detection of animals in natural images using far peripheral vision}, journal = {European Journal of Neuroscience}, year = {2001}, month = {9}, volume = {14}, number = {5}, pages = {869-876}, abstract = {It is generally believed that the acuity of the peripheral visual field is too poor to allow accurate object recognition and, that to be identified, most objects need to be brought into foveal vision by using saccadic eye movements. However, most measures of form vision in the periphery have been done at eccentricities below 10 degrees and have used relatively artificial stimuli such as letters, digits and compound Gabor patterns. Little is known about how such data would apply in the case of more naturalistic stimuli. Here humans were required to categorize briefly flashed (28 ms) unmasked photographs of natural scenes (39 degrees high, and 26 degrees across) on the basis of whether or not they contained an animal. The photographs appeared randomly in nine locations across virtually the entire extent of the horizontal visual field. Accuracy was 93.3\% for central vision and decreased almost linearly with increasing eccentricity (89.8\% at 13 degrees, 76.1\% at 44.5 degrees and 71.2\% at 57.5 degrees). Even at the most extreme eccentricity, where the images were centred at 70.5 degrees, subjects scored 60.5\% correct. No evidence was found for hemispheric specialization. This level of performance was achieved despite the fact that the position of the image was unpredictable, ruling out the use of precued attention to target locations. The results demonstrate that even high-level visual tasks involving object vision can be performed using the relatively coarse information provided by the peripheral retina.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf51.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://onlinelibrary.wiley.com/doi/10.1046/j.0953-816x.2001.01717.x/pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1046/j.0953-816x.2001.01717.x}, author = {Thorpe, SJ and Gegenfurtner, KR and Fabre-Thorpe, M and B{\"u}lthoff, HH} } @Article { 56, title = {A prior for global convexity in local shape-from-shading.}, journal = {Perception}, year = {2001}, month = {4}, volume = {30}, number = {4}, pages = {403-410}, abstract = {To solve the ill-posed problem of shape-from-shading, the visual system often relies on prior assumptions such as illumination from above or viewpoint from above. Here we demonstrate that a third prior assumption is used-namely that the surface is globally convex. We use complex surface shapes that are realistically rendered with computer graphics, and we find that performance in a local-shape-discrimination task is significantly higher when the shapes are globally convex than when they are globally concave. The results are surprising because the qualitative global shapes of the surfaces are perceptually unambiguous. The results generalise findings such as the hollow-potato illusion (Hill and Bruce 1994 Perception 23 1335-1337) which consider global shape perception only.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf56.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/perception/fulltext/p30/p3178.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p3178}, author = {Langer, MS and B{\"u}lthoff, HH} } @Article { 54, title = {Effects of temporal association on recognition memory.}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, year = {2001}, month = {4}, volume = {98}, number = {8}, pages = {4800-4804}, abstract = {The influence of temporal association on the representation and recognition of objects was investigated. Observers were shown sequences of novel faces in which the identity of the face changed as the head rotated. As a result, observers showed a tendency to treat the views as if they were of the same person. Additional experiments revealed that this was only true if the training sequences depicted head rotations rather than jumbled views: in other words, the sequence had to be spatially as well as temporally smooth. Results suggest that we are continuously associating views of objects to support later recognition, and that we do so not only on the basis of the physical similarity, but also the correlated appearance in time of the objects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf54.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.pnas.org/content/98/8/4800.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1073/pnas.071028598}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Article { 1200, title = {Viewpoint Dependence in Visual and Haptic Object Recognition}, journal = {Psychological Science}, year = {2001}, month = {1}, volume = {12}, number = {1}, pages = {37-42}, abstract = {On the whale, people recognize objects best when they see the objects from a familiar view and worse when they see the objects from views that were previously occluded from sight. Unexpectedly, we found haptic object recognition to be viewpoint-specific as well, even though hand movements were unrestricted. This viewpoint dependence was due to the hands preferring the back ''view'' of the objects. Furthermore, when the sensory modalities (visual vs. haptic) differed between learning an object and recognizing it, recognition performance was best when the objects were rotated back-to-front between learning and recognition. Our data indicate that the visual system recognizes the front view of objects best, whereas the hand recognizes objects best from the back.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1200.pdf}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://pss.sagepub.com/content/12/1/37.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1111/1467-9280.00307}, author = {Newell, F and Ernst, MO and Tjan, BS and B{\"u}lthoff, HH} } @Article { 76, title = {Perception, representation and recognition: A holistic view of recognition}, journal = {Spatial Vision}, year = {2000}, month = {11}, volume = {13}, number = {2-3}, pages = {265-275}, abstract = {It is clear that humans have mental representations of their spatial environments and that these representations are useful, if not essential, in a wide variety of cognitive tasks such as identification of landmarks and objects, guiding actions and navigation and in directing spatial awareness and attention. Determining the properties of mental representation has long been a contentious issue (see Pinker, 1984). One method of probing the nature of human representation is by studying the extent to which representation can surpass or go beyond the visual(or sensory) experience from which it derives. From a strictly empiricist standpoint what is not sensed cannot be represented; except as a combination of things that have been experienced. But perceptual experience is always limited by our view of the world and the properties of our visual system. It is therefore not surprising when human representation is found to be highly dependent on the initial viewpoint of the observer and on any shortcomings thereof. However, representation is not a static entity; it evolves with experience. The debate as to whether human representation of objects is view-dependent or view-invariant that has dominated research journals recently may simply be a discussion concerning how much information is available in the retinal image during experimental tests and whether this information is sufficient for the task at hand. Here we review an approach to the study of the development of human spatial representation under realistic problem solving scenarios. This is facilitated by the use of realistic virtual environments, exploratory learning and redundancy in visual detail.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf76.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ingentaconnect.com/search/download;jsessionid=a80u1jkd5msd6.alice?pub=infobike\%3a\%2f\%2fvsp\%2fspv\%2f2000\%2f00000013\%2fF0020002\%2fart00012\&mimetype=application\%2fpdf\&exitTargetId=1309267672714}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1163/156856800741081}, author = {Christou, C and B{\"u}lthoff, HH} } @Article { 105, title = {What's scene and not seen: Influences of movement and task upon what we see}, journal = {Visual Cognition}, year = {2000}, month = {10}, volume = {7}, number = {1-3}, pages = {175-190}, abstract = {Studies concerning the processing of natural scenes using eye movement equipment have revealed that observers retain surprisingly little information from one fixation to the next. Other studies, in which fixation remained constantwhile elements within the scene were changed, have shown that, even without refixation, objects within a scene are surprisingly poorly represented. Although this effect has been studied in some detail in static scenes, there has been relatively little work on scenes as we would normally experience them, namely dynamic and ever changing. This paper describes a comparable form of change blindness in dynamic scenes, in which detection is performed in the presence of simulated observer motion. The study also describes how change blindness is affected by the manner in which the observer interacts with the environment, by comparing detection performance of an observer as the passenger or driver of a car. The experiments show that observer motion reduces the detection of orientation and location changes, and that the task of driving causes a concentration of object analysis on or near the line of motion, relative to passive viewing of the same scene.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf105.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.tandfonline.com/doi/abs/10.1080/135062800394757}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1080/135062800394757}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Article { 88, title = {Neuronal representation of object orientation}, journal = {Neuropsychologia}, year = {2000}, month = {9}, volume = {38}, number = {9}, pages = {1235-1241}, abstract = {The dissociation between object identity and object orientation observed in six patients with brain damage, has been taken as evidence for a view-invariant model of object recognition. However, there was also some indication that these patients were not generally agnosic for object orientation but were able to gain access to at least some information about objects' canonical upright. We studied a new case (KB) with spared knowledge of object identity and impaired perception of object orientation using a Forced choice paradigm to contrast directly the patient's ability to perceive objects' canonical upright vs non-upright orientations. We presented 2D-pictures of objects with unambiguous canonical upright orientations in four different orientations (0 degrees, -90 degrees, +90 degrees, 180 degrees). KB showed no impairment in identifying letters, objects, animals, or faces irrespective of their given orientation. Also, her knowledge of upright orientation of stimuli was perfectly preserved. In sharp contrast, KB was not able to judge the orientation when the stimuli were presented in a non-upright orientation. The findings give further support for a distributed view-based representation of objects in which neurons become tuned to the features present in certain views of an object. Since we see more upright than inverted animals and familiar objects, the statistics of these images leads to a larger number of neurons tuned for objects in an upright orientation. We suppose that probably for this reason KB's knowledge of upright orientation was found to be more robust against neuronal damage than knowledge of other orientations, (C) 2000 Elsevier Science Ltd. All rights reserved.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf88.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0D-40J1CTF-4-9\&_cdi=4860\&_user=29041\&_pii=S0028393200000439\&_origin=\&_coverDate=08\%2F01\%2F2000\&_sk=999619990\&view=c\&wchp=dGLzVzb-zSkWA\&md5=c9f4403269fd7de6fdeadced3a803149\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0028-3932(00)00043-9}, author = {Karnath, HO and Ferber, S and B{\"u}lthoff, HH} } @Article { 92, title = {Depth discrimination from shading under diffuse lighting.}, journal = {Perception}, year = {2000}, month = {6}, volume = {29}, number = {6}, pages = {649-660}, abstract = {The human visual system has a remarkable ability to interpret smooth patterns of light on a surface in terms of 3-D surface geometry. Classical studies of shape-from-shading perception have assumed that surface irradiance varies with the angle between the local surface normal and a collimated light source. This model holds, for example, on a sunny day. One common situation in which this model fails to hold, however, is under diffuse lighting such as on a cloudy day. Here we report on the first psychophysical experiments that address shape-from- shading under a uniform diffuse-lighting condition. Our hypothesis was that shape perception can be explained with a perceptual model that ''dark means deep''. We tested this hypothesis by comparing performance in a depth-discrimination task to performance in a brightness-discrimination task, using identical stimuli. We found a significant correlation between responses in the two tasks, supporting a dark-means-deep model, However, overall performance in the depth-discrimination task was superior to that predicted by a dark-means-deep model. This implies that humans use a more accurate model than dark-means- deep to perceive shape-from-shading under diffuse lighting.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf92.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p3060}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p3060}, author = {Langer, MS and B{\"u}lthoff, HH} } @Article { 80, title = {Grasping visual illusions: No evidence for a dissociation between perception and action}, journal = {Psychological Science}, year = {2000}, month = {1}, volume = {11}, number = {1}, pages = {20-25}, abstract = {Neuropsychological studies prompted the theory that the primate visual system might be organized into two parallel pathways, one for conscious perception and one for guiding action. Supporting evidence in healthy subjects seemed to come from a dissociation in visual illusions: In previous studies, the Ebbinghaus (or Titchener) illusion deceived perceptual judgments of size, but only marginally influenced the size estimates used in grasping. Contrary to those results, the findings from the present study show that there is no difference in the sizes of the perceptual and grasp illusions if the perceptual and grasping tasks are appropriately matched. We show that the differences found previously can be accounted for by a hitherto unknown , nonadditive effect in the addition. We conclude that the illusion does not provide evidence for the existence of two distinct pathways for perception and action in the visual system.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf80.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://pss.sagepub.com/content/11/1/20.full.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1111/1467-9280.00209}, author = {Franz, VH and Gegenfurtner, KR and B{\"u}lthoff, HH and Fahle, M} } @Article { 79, title = {Touch can change visual slant perception}, journal = {Nature Neuroscience}, year = {2000}, month = {1}, volume = {3}, number = {1}, pages = {69-73}, abstract = {The visual system uses several signals to deduce the three- dimensional structure of the environment, including binocular disparity, texture gradients, shading and motion parallax. Although each of these sources of information is independently insufficient to yield reliable three-dimensional structure from everyday scenes, the visual system combines them by weighting the available information; altering the weights would therefore change the perceived structure. We report that haptic feedback (active touch) increases the weight of a consistent surface- slant signal relative to inconsistent signals. Thus, appearance of a subsequently viewed surface is changed: the surface appears slanted in the direction specified by the haptically reinforced signal.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf79.pdf}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://www.nature.com/neuro/journal/v3/n1/pdf/nn0100_69.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1038/71140}, author = {Ernst, MO and Banks, MS and B{\"u}lthoff, HH} } @Article { 183, title = {View dependence in scene recognition after active learning}, journal = {Memory \& Cognition}, year = {1999}, month = {11}, volume = {27}, number = {6}, pages = {996-1007}, abstract = {Human spatial encoding of three-dimensional navigable space was studied, using a virtual environment simulation. This allowed subjects to become familiar with a realistic scene by making simulated rotational and translational movements during training. Subsequent tests determined whether subjects could generalize their recognition ability by identifying novel-perspective views and topographic floor plans of the scene. Results from picture recognition tests showed that familiar direction views were most easily recognized, although significant generalization to novel views was observed. Topographic floor plans were also easily identified. In further experiments, novel-view performance diminished when active training was replaced by passive viewing of static images of the scene. However, the ability to make self-initiated movements, as opposed to watching dynamic movie sequences, had no effect on performance. These results suggest that representation of navigable space is view dependent and highlight the importance of spatial-temporal continuity during learning.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/view_dependence_in_scene_recognition_after_active_learning_183[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/004h175h38868t77/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.3758/BF03201230}, author = {Christou, C and B{\"u}lthoff, HH} } @Article { 217, title = {Why the visual recognition system might encode the effects of illumination}, journal = {Vision Research}, year = {1999}, month = {8}, volume = {38}, number = {15-16}, pages = {2259-2275}, abstract = {A key problem in recognition is that the image of an object depends on the lighting conditions. We investigated whether recognition is sensitive to illumination using 3-D objects that were lit from either the left or right, varying both the shading and the cast shadows. In experiments 1 and 2 participants judged whether two sequentially presented objects were the same regardless of illumination. Experiment 1 used six objects that were easily discriminated and that were rendered with cast shadows. While no cost was found in sensitivity, there was a response time cost over a change in lighting direction. Experiment 2 included six additional objects that were similar to the original six objects making recognition more difficult. The objects were rendered with cast shadows, no shadows, and as a control, white shadows. With normal shadows a change in lighting direction produced costs in both sensitivity and response times. With white shadows there was a much larger cost in sensitivity and a comparable cost in response times. Without cast shadows there was no cost in either measure, but the overall performance was poorer. Experiment 3 used a naming task in which names were assigned to six objects rendered with cast shadows. Participants practised identifying the objects in two viewpoints lit from a single lighting direction. Viewpoint and illumination invariance were then tested over new viewpoints and illuminations. Costs in both sensitivity and response time were found for naming the familiar objects in unfamiliar lighting directions regardless of whether the viewpoint was familiar or unfamiliar. Together these results suggest that illumination effects such as shadow edges: (1) affect visual memory; (2) serve the function of making unambigous the three-dimensional shape; and (3) are modeled with respect to object shape, rather than simply encoded in terms of their effects in the image.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/why_the_visual_recognition_system_might_encode_the_effects_of_illumination_217[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-3WBFMK9-3-F\&_cdi=4873\&_user=29041\&_pii=S0042698998000418\&_origin=\&_coverDate=08\%2F31\%2F1998\&_sk=999619984\&view=c\&wchp=dGLbVlz-zSkWW\&md5=d4ebc293868519cfc507935af8fabe7a\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0042-6989(98)00041-8}, author = {Tarr, MJ and Kersten, D and B{\"u}lthoff, HH} } @Article { 181, title = {What object attributes determine canonical views?}, journal = {Perception}, year = {1999}, month = {5}, volume = {28}, number = {5}, pages = {575-599}, abstract = {We investigated preferred or canonical views for familiar and three-dimensional nonsense objects using computer-graphics psychophysics. We assessed the canonical views for objects by allowing participants to actively rotate realistically shaded three-dimensional models in real-time. Objects were viewed on a Silicon Graphics workstation and manipulated in virtual space with a three-degree-of-freedom input device. In the first experiment, participants adjusted each object to the viewpoint from which they would take a photograph if they planned to use the object to illustrate a brochure. In the second experiment, participants mentally imaged each object on the basis of the name and then adjusted the object to the viewpoint from which they imagined it. In both experiments, there was a large degree of consistency across participants in terms of the preferred view for a given object. Our results provide new insights on the geometrical, experiential, and functional attributes that determine canonical views under ecological conditions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf181.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p2897}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p2897}, author = {Blanz, V and Tarr, MJ and B{\"u}lthoff, HH} } @Article { 184, title = {Effects of parametric manipulation of inter-stimulus similarity on 3D object categorization}, journal = {Spatial Vision}, year = {1999}, month = {1}, volume = {12}, number = {1}, pages = {107-123}, abstract = {To explore the nature of the representation space of 3D objects, we studied human performance in forced-choice categorization of objects composed of four geon-like parts emanating from a common center. Two categories were defined by prototypical objects, distinguished by qualitative properties of their parts (bulging vs waist-like limbs). Subjects were trained to discriminate between the two prototypes (shown briefly, from a number of viewpoints, in stereo) in a 1-interval forced-choice task, until they reached a 90\% correct-response performance level. After training, in the first experiment, 11 subjects were tested on shapes obtained by varying the prototypical parameters both orthogonally (ORTHO) and in parallel (PARA) to the line connecting the prototypes in the parameter space. For the eight subjects who performed above chance, the error rate increased with the ORTHO parameter-space displacement between the stimulus and the corresponding prototype; the effect of the PARA displacement was weaker. Thus, the parameter-space location of the stimuli mattered more than the qualitative contrasts, which were always present. To find out whether both prototypes or just the nearest one to the test shape influenced the decision, in the second experiment we varied the similarity between the categories. Specifically, in the test stage trials the distance between the two prototypes could assume one of three values (FAR, INTERMEDIATE, and NEAR). For the 13 subjects who performed above chance, the error rate (on physically identical stimuli) in the NEAR condition was higher than in the other two conditions. The results of the two experiments contradict the prediction of theories that postulate exclusive reliance on qualitative contrasts, and support the notion of a representation space in which distances to more than one reference point or prototype are encoded (Edelman, 1998).}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf184.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ingentaconnect.com/search/download?pub=infobike\%3a\%2f\%2fvsp\%2fspv\%2f1999\%2f00000012\%2f00000001\%2fart00006\&mimetype=application\%2fpdf\&exitTargetId=1309268380820}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1163/156856899X00067}, author = {Edelman, S and B{\"u}lthoff, HH and B{\"u}lthoff, I} } @Article { 222, title = {Learning to recognize objects}, journal = {Trends In Cognitive Sciences}, year = {1999}, month = {1}, volume = {3}, number = {1}, pages = {22-31}, abstract = {Evidence from neurophysiological and psychological studies is coming together to shed light on how we represent and recognize objects. This review describes evidence supporting two major hypotheses: the first is that objects are represented in a mosaic-like form in which objects are encoded by combinations of complex, reusable features, rather than two-dimensional templates, or three-dimensional models. The second hypothesis is that transform-invariant representations of objects are learnt through experience, and that this learning is affected by the temporal sequence in which different views of the objects are seen, as well as by their physical appearance.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/learning_to_recognize_objects_222[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VH9-3W6MS32-9-1\&_cdi=6061\&_user=29041\&_pii=S1364661398012613\&_origin=\&_coverDate=01\%2F01\%2F1999\&_sk=999969998\&view=c\&wchp=dGLzVzz-zSkzS\&md5=c1f18e691253502124a120e14ed6f2e2\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S1364-6613(98)01261-3}, author = {Wallis, G and B{\"u}lthoff, HH} } @Article { 196, title = {On robots and flies: Modeling the visual orientation behavior of flies.}, journal = {Robotics and Autonomous Systems}, year = {1998}, month = {12}, volume = {29}, number = {4}, pages = {227-242}, abstract = {Although artificial and biological systems face similar sensorimotor control problems, until today only a few attempts have been made to implement specific biological control structures on robots. Nevertheless, the process of designing the sensorimotor control of a robot can contribute to our understanding of these mechanisms and can provide the basis of a critical evaluation of existing biological models. Flies have developed a specialized visuomotor control for tasks such as course stabilization, fixation and approach towards stationary objects, tracking of moving objects and landing, which are based on the analysis of visual motion information. Theoretical and experimental results suggest that in flies the visuomotor control for course stabilization as well as fixation and approach towards stationary objects may be implemented at least partially by one common sensory-circuit. We present agents with a visuomotor controller that regulates the two behaviors of course stabilization and object fixation. To test this controller under real world conditions, we implemented it on a miniature robot. We have been able to show that in addition to course stabilization and object fixation, the robot also approaches stationary objects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf196.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6V16-3YGDFYD-2-1\&_cdi=5666\&_user=29041\&_pii=S092188909900055X\&_origin=\&_coverDate=12\%2F31\%2F1999\&_sk=999709995\&view=c\&wchp=dGLzVlz-zSkzk\&md5=042aa373cc2888e72b06f534b07aa205\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0921-8890(99)00055-X}, author = {Huber, SA and Franz, MO and B{\"u}lthoff, HH} } @Article { 154, title = {Where did I take that snapshot? Scene-based homing by image matching}, journal = {Biological Cybernetics}, year = {1998}, month = {10}, volume = {79}, number = {3}, pages = {191-202}, abstract = {In homing tasks, the goal is often not marked by visible objects but must be inferred from the spatial relation to the visual cues in the surrounding scene. The exact computation of the goal direction would require knowledge about the distances to visible landmarks, information, which is not directly available to passive vision systems. However, if prior assumptions about typical distance distributions are used, a snapshot taken at the goal suffices to compute the goal direction from the current view. We show that most existing approaches to scene-based homing implicitly assume an isotropic landmark distribution. As an alternative, we propose a homing scheme that uses parameterized displacement fields. These are obtained from an approximation that incorporates prior knowledge about perspective distortions of the visual environment. A mathematical analysis proves that both approximations do not prevent the schemes from approaching the goal with arbitrary accuracy, but lead to different errors in the computed goal direction. Mobile robot experiments are used to test the theoretical predictions and to demonstrate the practical feasibility of the new approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/where_did_i_take_that_snapshot_154[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/vk511adjpnxh9ln4/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/s004220050470}, author = {Franz, M and Sch{\"o}lkopf, B and B{\"u}lthoff, HH} } @Article { 243, title = {An introduction to object recognition}, journal = {Zeitschrift f{\"u}r Naturforschung C}, year = {1998}, month = {8}, volume = {53}, number = {7-8}, pages = {610-621}, abstract = {In this report we present a general introduction to object recognition. We begin with brief discussions of the terminology used in the object recognition literature and the psychophysical tasks that are used to investigate object recognition. We then discuss models of shape representation. We dispense with the idea that shape representations are like the 3-D models used in computer aided design and explore instead models of shape representation that are based on feature descriptions. As these descriptions encode only the features that are visible from a particular viewpoint, they are generally viewpoint-specific, We discuss various means of achieving viewpoint-invariant recognition using such descriptions, including reliance on diagnostic features visible from a wide range of viewpoints, storage of multiple descriptions for each object, and the use of transformation mechanisms. Finally, we discuss how differences in viewpoint dependence that are often observed for within-category and between-category recognition tasks could be due to differences in the types of features that are naturally available to distinguish among different objects in these tasks.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf243.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.znaturforsch.com/ac/v53c/c53c.htm}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, author = {Liter, JC and B{\"u}lthoff, HH} } @Article { 265, title = {Navigating through a virtual city: Using virtual reality technology to study human action and perception.}, journal = {Future Generation Computer Systems}, year = {1998}, month = {8}, volume = {14}, number = {3-4}, pages = {231-242}, abstract = {Images formed by a human face change with viewpoint. A new technique is described for synthesizing images of faces from new viewpoints, when only a single 2D image is available. A novel 2D image of a face can be computed without explicitly computing the 3D structure of the head. The technique draws on a single generic 3D model of a human head and on prior knowledge of faces based on example images of other faces seen in different poses. The example images are used to ''learn'' a pose-invariant shape and texture description of a new face. The 3D model is used to solve the correspondence problem between images showing faces in different poses. The proposed method is interesting for view independent face recognition tasks as well as for image synthesis problems in areas like teleconferencing and virtualized reality.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Navigating_through_a_virtual_city_Using_virtual_reality_technology_to_study_human_action_and_perception_265[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1707835}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0167-739X(98)00027-2}, author = {van Veen, H-J and Distler, H and Braun, S and B{\"u}lthoff, HH} } @Article { 250, title = {Stimulus-specific effects in face recognition over changes in viewpoint}, journal = {Vision Research}, year = {1998}, month = {8}, volume = {38}, number = {15-16}, pages = {2351-2363}, abstract = {Individual faces vary considerably in both the duality and quantity of the information they contain for recognition and for viewpoint generalization. In the present study. we assessed the typicality, recognizability, and viewpoint generalizability of individual faces using data from both human observers and from a computational model of face recognition across viewpoint change. The two-stage computational model incorporated a viewpoint alignment operation and a recognition-by- interpolation operation. An interesting aspect of this particular model is that the effects of typicality it predicts at the alignment and recognition stages dissociate, such that face typicality is beneficial for the success of the alignment process, but is adverse for the success of the recognition process. We applied a factor analysis to the covariance data for the human- and model-derived face measures across the different viewpoints and found two axes that appeared consistently across all viewpoints. Projection scores for individual faces on these axes (i.e. the extent to which a face's 'performance profile' matched the pattern of human- and model-derived scores on that axis), correlated across viewpoint changes to a much higher degree than did the raw recognizability scores of the faces. These results suggest that the stimulus information captured in the model measures may underlie distinct and dissociable aspects of the recognizability of individual faces across viewpoint change.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf250.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-3WBFMK9-9-7\&_cdi=4873\&_user=29041\&_pii=S004269899800042X\&_origin=\&_coverDate=08\%2F31\%2F1998\&_sk=999619984\&view=c\&wchp=dGLbVzW-zSkWA\&md5=ea8ff9859bd863f621263a7b72227209\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0042-6989(98)00042-X}, author = {O'Toole, AJ and Edelman, S and B{\"u}lthoff, HH} } @Article { 259, title = {Image-based object recognition in man, monkey and machine}, journal = {Cognition}, year = {1998}, month = {7}, volume = {67}, number = {1-2}, pages = {1-20}, abstract = {Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae. Recent findings from human psychophysics, neurophysiology and machine vision provide converging evidence for `image-based' models in which objects are represented as collections of viewpoint-specific local features. This approach is contrasted with `structural-description' models in which objects are represented as configurations of 3D volumes or parts. We then review recent behavioral results that address the biological plausibility of both approaches, as well as some of their computational advantages and limitations. We conclude that, although the image-based approach holds great promise, it has potential pitfalls that may be best overcome by including structural information. Thus, the most viable model of object recognition may be one that incorporates the most appealing aspects of both image-based and structural-description theories.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf259.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T24-3TDR775-1-3\&_cdi=4908\&_user=29041\&_pii=S0010027798000262\&_origin=\&_coverDate=07\%2F17\%2F1998\&_sk=999329998\&view=c\&wchp=dGLzVlz-zSkWz\&md5=c49a8fe35489b1a38503db14759fafba\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0010-0277(98)00026-2}, author = {Tarr, MJ and B{\"u}lthoff, HH} } @Article { 148, title = {Top-down influences on stereoscopic depth-perception}, journal = {Nature Neuroscience}, year = {1998}, month = {7}, volume = {1}, number = {3}, pages = {254-257}, abstract = {The interaction between depth perception and object recognition has important implications for the nature of mental object representations and models of hierarchical organization of visual processing. It is often believed that the computation of depth influences subsequent high-level object recognition processes, and that depth processing is an early vision task that is largely immune to 'top-down' object-specific influences, such as object recognition. Here we present experimental evidence that challenges both these assumptions in the specific context of stereoscopic depth-perception. We have found that observers' recognition of familiar dynamic three- dimensional (3D) objects is unaffected even when the objects' depth structure is scrambled, as long as their two-dimensional (2D) projections are unchanged. Furthermore, the observers seem perceptually unaware of the depth anomalies introduced by scrambling. We attribute the latter result to a top-down recognition-based influence whereby expectations about a familiar object's 3D structure override the true stereoscopic information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf148.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.nature.com/neuro/journal/v1/n3/pdf/nn0798_254.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1038/699}, author = {B{\"u}lthoff, I and B{\"u}lthoff, HH and Sinha, P} } @Article { 155, title = {Learning view graphs for robot navigation}, journal = {Autonomous Robots}, year = {1998}, month = {3}, volume = {5}, number = {1}, pages = {111-125}, abstract = {We present a purely vision-based scheme for learning a topological representation of an open environment. The system represents selected places by local views of the surrounding scene, and finds traversable paths between them. The set of recorded views and their connections are combined into a graph model of the environment. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. In robot experiments, we demonstrate that complex visual exploration and navigation tasks can thus be performed without using metric information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/learning_view_graphs_for_robot_navigation_155[1].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/u68872370577qj0h/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1023/A:1008821210922}, author = {Franz, M and Sch{\"o}lkopf, B and Mallot, HA and B{\"u}lthoff, HH} } @Article { 263, title = {How is bilateral symmetry of human faces used for recognition of novel views?}, journal = {Vision Research}, year = {1998}, month = {1}, volume = {38}, number = {1}, pages = {79-89}, abstract = {The role of bilateral symmetry in face recognition is investigated in two psychophysical experiments using a Same/Different paradigm. The results of Experiment 1 confirm the hypothesis that the ability to identify mirror symmetric patterns is used for viewpoint generalization by approximating the view symmetric to the learned view by its mirror reversed image. The results of Experiment 2 show that the match between this virtual view and the test image is performed directly between the images. Performance drops dramatically if the symmetry between the intensity patterns of the learning and the testing view is disturbed by an symmetric illumination, although the symmetry between the spatial arrangement of high-level features is retained. Experimental results are discussed in terms of their relation to existing approaches to object recognition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf263.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-3WTP10F-15-2\&_cdi=4873\&_user=29041\&_pii=S004269899700165X\&_origin=\&_coverDate=01\%2F31\%2F1998\&_sk=999619998\&view=c\&wchp=dGLzVzz-zSkWA\&md5=25a9c25b96ff9d2b2b4dcc24afbbbe0c\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0042-6989(97)00165-X}, author = {Troje, NF and B{\"u}lthoff, HH} } @Article { 427, title = {To what extent do unique parts influence recognition across changes in viewpoint?}, journal = {Psychological Science}, year = {1997}, month = {7}, volume = {8}, number = {4}, pages = {282-282}, abstract = {We investigated how varying the number of unique parts within an object influences recognition across changes in viewpoint The stimuli were shaded objects composed of five three-dimensional volumes linked end to end with varying connection angles Of the five volumes, zero, one, three, or five were qualitatively distinct (e g, brick vs cone), the rest being tubes Sequential-matching and naming tasks were used to assess the recognition of these stimuli over rotations in depth Three major results stand out First, regardless of the number of distinct parts, there was increasingly poorer recognition performance with increasing change in viewpoint Second, the impact of viewpoint change for objects with one unique part was less than that for the other objects Third, additional parts beyond a single unique part produced strong viewpoint dependency comparable to that obtained for objects with no distinct parts Thus, visual recognition may be explained by a view-based theory in which viewpoint-specific representations encode both quantitative and qualitative features.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf427.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://pss.sagepub.com/content/8/4/282.full.pdf+html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1111/j.1467-9280.1997.tb00439.x}, author = {Tarr, MJ and B{\"u}lthoff, HH and Zabinski, M and Blanz, V} } @Article { 375, title = {Sex classification is better with three-dimensional head structure than with image intensity information.}, journal = {Perception}, year = {1997}, month = {1}, volume = {26}, number = {1}, pages = {75-84}, abstract = {The sex of a face is perhaps its most salient feature. A principal components analysis (PCA) was applied separately to the three-dimensional (3-D) structure and graylevel image (GLI) data from laser-scanned human heads. Individual components from both analyses captured information related to the sex of the face. Notably, single projection coefficients characterized complex differences between the 3-D structure of male and female heads and between male and female GLI maps. In a series of simulations, the quality of the information available in the 3-D head versus GLI data for predicting the sex of the face has been compared. The results indicated that the 3-D head data supported more accurate sex classification than the GLI data, across a range of PCA-compressed (dimensionality-reduced) representations of the heads. This kind of dual face representation can give insight into the nature of the information available to humans for categorizing and remembering faces.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Perception-1997-26-75_375[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p260075}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1068/p260075}, author = {O'Toole, AJ and Vetter, T and Troje, NF and B{\"u}lthoff, HH} } @Article { 527, title = {A psychophysical and computational analysis of intensity-based stereo.}, journal = {Biological Cybernetics}, year = {1996}, month = {10}, volume = {75}, number = {3}, pages = {187-198}, abstract = {WWe describe two psychophysical experiments testing predictions of the square difference mechanism we have previously proposed for intensity–based stereo. Experiment 1 assesses the relative contributions of disparity and contrast to intensity–based stereo by measuring detection thresholds. The product of disparity and contrast at threshold is shown to be constant. In experiment 2, we measure quantitatively the global depth position perceived in stereograms of curved, smoothly shaded surfaces. The results show that disparity averaging over the surface involves a contrast-dependent weighting function. The results from both experiments are consistent with predictions derived from the square difference mechanism. The relation of this mechanism to feature correspondence stereopsis and shape–from–shading is discussed and a general framework for assessing the modularity of stereopsis is presented.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf527.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/xm0gxtq5lcyhgx55/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/s004220050286}, author = {Mallot, HA and Arndt, PA and B{\"u}lthoff, HH} } @Article { 541, title = {Face recognition under varying poses: The role of texture and shape}, journal = {Vision Research}, year = {1996}, month = {6}, volume = {36}, number = {12}, pages = {1761-1771}, abstract = {Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes, It has long been known that both profile and full-face views result in poorer recognition performance than a 3/4 view, However, little data exist which investigate this phenomenon in detail. The present work provides such data using a high angular resolution and a large range of poses, Since there are inconsistencies in the literature concerning these issues, we emphasize the different roles of the learning view and the testing view in the recognition experiment, We also emphasize the roles of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: (1) only the learning view but not the testing view affects recognition performance, (2) For textured faces the optimal learning view is closer to the full- face view than for the shaded faces, (3) For shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/face_recognition_under_varying_poses_the_role_of_texture_and_shape_541[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-3VXNHBP-S-1\&_cdi=4873\&_user=29041\&_pii=0042698995002308\&_origin=\&_coverDate=06\%2F30\%2F1996\&_sk=999639987\&view=c\&wchp=dGLzVzz-zSkzk\&md5=a07faee274f12703140ee6e110c217c8\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/0042-6989(95)00230-8}, author = {Troje, N and B{\"u}lthoff, HH} } @Article { 520, title = {Phenomenal competition for poses of the human head.}, journal = {Perception}, year = {1996}, month = {3}, volume = {25}, number = {3}, pages = {367-368}, abstract = {We show a cylindrical projection of the human head. This projection is ambiguous with respect to head pose. Viewing such a projection produces perceptual competition for a few discrete views.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/phenomenal_competition_for_poses_of_the_human_head_520[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p250367}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p250367}, author = {Kersten, D and Troje, N and B{\"u}lthoff, HH} } @Article { 670, title = {Is Human Object Recognition Better Described by Geon Structural Descriptions or by Multiple Views? Comment on Biederman and Gerhardstein (1993)}, journal = {Journal of Experimental Psychology: Human Perception and Performance}, year = {1995}, month = {12}, volume = {21}, number = {6}, pages = {1494-1505}, abstract = {Is human object recognition viewpoint dependent or viewpoint invariant under “everyday” conditions? I. Biederman and P.C. Gerhardstein (1993) argued that viewpoint-invariant mechanisms are used almost exclusively. However, our analysis indicates that (a) their conditions for immediate viewpoint invariance lack the generality to characterize a wide range of recognition phenomena, (b) the extensive body of viewpoint-dependent results cannot be dismissed as processing “by-products” or “experimental artifacts,” and (c) geon structural descriptions cannot coherently account for category recognition, the domain they are intended to explain. The weight of current evidence supports an exemplar-based multiple-views mechanism as an important component of both exemplar-specific and categorical recognition. *1 This research was supported by U.S. Air Force Office of Scientific Research Contract F49620-91-J-0169 and by the U.S. Office of Naval Research Contract N00014-93-1-0305. Many of the ideas presented in this article were developed during visits by Michael J. Tarr to the Max-Planck-Institut f{\"u}r Biologische Kybernetik, T{\"u}bingen, Germany.*2 This article is based on a more detailed version available as Max-Planck Technical Report No. 3, which may be obtained via anonymous ftp to ftp.mpik-tueb.mpg.de as pub/mpi-memos/tr-003.ps.z.*3 We thank Dan Kersten for his insightful comments and thoughtful advice, Shimon Edelman, David Kriegman, Emanuela Bricolo, William Hayward, Laurie Heller, Pepper Williams, and Alice O'Toole for their comments. We also thank William Hayward for initiating the idea expressed in Figure 3 as well as Pierre Jolicoeur for helpful comments.Corresponding Author Contact Information}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/is_human_object_recognition_better_described_by_geon_structural_descriptions_or_by_multiple_views_670[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6X08-46RVR0F-18-1\&_cdi=7208\&_user=29041\&_pii=S0096152302006375\&_origin=\&_coverDate=12\%2F31\%2F1995\&_sk=999789993\&view=c\&wchp=dGLbVlW-zSkWW\&md5=b59174218405285575ecd7c4c92d0b71\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, author = {Tarr, MJ and B{\"u}lthoff, HH} } @Article { 667, title = {An integrated approach to the study of object features in visual recognition}, journal = {Network}, year = {1995}, month = {11}, volume = {6}, number = {4}, pages = {603-618}, abstract = {We propose to assess the relevance of theories of synaptic modification as models of feature extraction in human vision, by using masks derived from synaptic weight patterns to occlude parts of the stimulus images in psychophysical experiments. In the experiment reported here, we found that a mask derived from principal component analysis of object images was more effective in reducing the generalization performance of human subjects than a mask derived from another method of feature extraction (BCM), based on higher-order statistics of the images.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf667.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ingentaconnect.com/content/apl/network/1995/00000006/00000004/art00005}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1088/0954-898X/6/4/005}, author = {Intrator, N and Edelman, S and B{\"u}lthoff, HH} } @Article { 620, title = {How are three-dimensional objects represented in the brain?}, journal = {Cerebral Cortex}, year = {1995}, month = {5}, volume = {5}, number = {3}, pages = {247-260}, abstract = {In this report we discuss a variety of psychophysical experiments that explore different aspects of the problem of object recognition and representation in human vision. In all experiments, subjects were presented with realistically rendered images of computer-generated 3D objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects‘ prior exposure to the stimulus objects. Contrary to the predictions of the paradigmatic theory of recognition, which holds that object representations are viewpoint invariant, performance in all experiments was consistently viewpoint dependent, was only partially aided by binocular stereo and other depth information, was specific to viewpoints that were familiar, and was systematically disrupted by rotation in depth more than by deforming the 2D images of the stimuli. The emerging concept of multiple-views representation supported by these results is consistent with recently advanced computational theories of recognition based on view interpolation. Moreover, in several simulated experiments employing the same stimuli used in experiments with human subjects, models based on multiple-views representations replicated many of the psychophysical results concerning the observed pattern of human performance.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/how_are_three_dimensional_objects_represented_in_the_brain_620[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://cercor.oxfordjournals.org/content/5/3/247.long}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1093/cercor/5.3.247}, author = {B{\"u}lthoff, HH and Edelman, SY and Tarr, MJ} } @Article { 617, title = {Human stereovision without localized image features}, journal = {Biological Cybernetics}, year = {1995}, month = {3}, volume = {72}, number = {4}, pages = {279-293}, abstract = {Many theories of human stereovision are based on feature matching and the related correspondence problem. In this paper, we present psychophysical experiments indicating that localized image features such as Laplacian zerocrossings, intensity extrema, or centroids are not necessary for binocular depth perception. Smooth one-dimensional intensity profiles were combined into stereograms with mirror-symmetric half-images such that these localized image features were either absent or did not carry stereo information. In a discrimination task, subjects were asked to distinguish between stereograms differing only by an exchange of these half-images (ortho- vs. pseudoscopic stereograms). In a depth ordering task, subjects had to judge which of the two versions appeared in front. Subjects are able to solve both tasks even in the absence of the mentioned image features. The performance is compared to various possible stereo mechanisms. We conclude that localized image features and the correspondences between them are not necessary to perceive stereoscopic depth. One mechanism accounting for our data is correlation or mean square difference.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/human_stereovision_without_localized_images_features_617[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/jh705m1r57810527/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00202784}, author = {Arndt, PA and Mallot, HA and B{\"u}lthoff, HH} } @Article { 677, title = {Separate neural pathways for the visual analysis of object shape in perception and prehension}, journal = {Current Biology}, year = {1994}, month = {7}, volume = {4}, number = {7}, pages = {604-610}, abstract = {Background: Earlier work with neurological patients has shown that the visual perception of object size and orientation depends on visual pathways in the cerebral cortex that are separate from those mediating the use of these same object properties in the control of goal-directed grasping. We present evidence suggesting that the same dissociation between perception and action is evident in the visual processing of object shape. In other words, discrimination between objects on the basis of their shape appears to be mediated by visual mechanisms that are functionally and neurally distinct from those controlling the pre-shaping of the hand during grasping movements directed at those same objects. Results We studied two patients with lesions in different parts of the cerebral visual pathways. One patient (RV), who had sustained bilateral lesions of the occipitoparietal cortex, was unable to use visual information to place her fingers correctly on the circumference of irregularly shaped objects when asked to pick them up, even though she had no difficulty in visually discriminating one such object from another. Conversely, a second patient (DF), who had bilateral damage in the ventrolateral occipital region, had no difficulty in placing her fingers on appropriate opposition points during grasping, even though she was unable to discriminate visually amongst such objects. Conclusions This double dissociation lends strong support to the idea that the visual mechanisms mediating the perception of objects are functionally and neurally distinct from those mediating the control of skilled actions directed at those objects. It also supports the recent proposal of Goodale and Milner that visual perception depends on a ventral stream of projections from the primary visual cortex to the inferotemporal cortex, whereas the visual control of skilled actions depends on a dorsal stream from the primary visual cortex to the posterior parietal cortex.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/seperate_neural_pathways_for_the_visual_analysis_of_object_shape_in_perception_and_prehension_677[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6VRT-4DGVHRM-30-F\&_cdi=6243\&_user=29041\&_pii=S0960982200001329\&_origin=\&_coverDate=07\%2F31\%2F1994\&_sk=999959992\&view=c\&wchp=dGLzVzb-zSkWz\&md5=de579398635fb7ecc0593e419cd0777d\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0960-9822(00)00132-9}, author = {Goodale, MA and Meenan, JP and B{\"u}lthoff, HH and Nicolle, DA and Murphy, KJ and Raciot, CI} } @Article { 678, title = {View-dependent object recognition by monkeys.}, journal = {Current Biology}, year = {1994}, month = {5}, volume = {4}, number = {5}, pages = {401-414}, abstract = {Background: How do we recognize visually perceived three-dimensional objects, particularly when they are seen from novel view-points? Recent psychophysical studies have suggested that the human visual system may store a relatively small number of two-dimensional views of a three-dimensional object, recognizing novel views of the object by interpolation between the stored sample views. In order to investigate the neural mechanisms underlying this process, physiological experiments are required and, as a prelude to such experiments, we have been interested to know whether the observations made with human observers extend to monkeys.Results We trained monkeys to recognize computer-generated images of objects presented from an arbitrarily chosen training view and containing sufficient three-dimensional information to specify the object’s structure. We subsequently tested the trained monkeys’ ability to generalize recognition of the object to views generated by rotation of the target object around any arbitrary axis. The monkeys recognized as the target only those two-dimensional views that were close to the familiar, training view. Recognition became increasingly difficult for the monkeys as the stimulus was rotated away from the experienced viewpoint, and failed for views farther than about 40\(^{\circ}\) from the training view. This suggests that, in the early stages of learning to recognize a previously unfamiliar object, the monkeys build two-dimensional, viewer-centered object representations, rather than a three-dimensional model of the object. When the animals were trained with as few as three views of the object, 120\(^{\circ}\) apart, they could often recognize all the views of the object resulting from rotations around the same axis.Conclusion Our experiments show that recognition of three-dimensional novel objects is a function of the object's retinal projection. This suggests that non-human primates, like humans, may accomplish view-invariant recognition of familiar objects by a viewer-centered system that interpolates between a small number of stored views. The measures of recognition performance can be simulated by a regularization network that stores a few familiar views, and is endowed with the ability to interpolate between these views. Our results provide the basis for physiological studies of object-recognition by monkeys and suggest that the insights gained from such studies should apply also to humans.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/view_dependent_object_recognition_by_monkeys_678[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=GatewayURL\&_origin=CELLPRESS\&_urlversion=4\&_method=citationSearch\&_version=1\&_src=FPDF\&_piikey=S0960982200000890\&md5=3fb1b055245b5be752fe2e006b83cef3}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0960-9822(00)00089-0}, author = {Logothetis, NK and Pauls, J and B{\"u}lthoff, HH and Poggio, T} } @Article { 679, title = {The importance of symmetry and virtual views in three-dimensional object recognition}, journal = {Current Biology}, year = {1994}, month = {1}, volume = {4}, number = {1}, pages = {18-23}, abstract = {Background: Human observers can recognize three-dimensional objects seen in novel orientations, even when they have previously seen only a relatively small number of different views of the object. How our visual system does this is a key problem in vision research. Recent theories and experiments suggest that the human visual system might store a relatively small number of sample two-dimensional views of a three-dimensional object, and recognize novel views by a process of interpolation between the stored sample views. These sample views may be collected during a training phase as the visual system familiarizes itself with the object.Results Here, we investigate whether constraints on the shapes of objects commonly encountered in the real world can reduce the number of training views required for recognition of three-dimensional objects. We are particularly concerned with the constraint of object symmetry. We show that if an object is bilaterally symmetrical, then additional ‘virtual views’ can automatically be generated from one sample view by symmetry transformations. These virtual views should make it more easy to recognize novel views of a symmetric than an asymmetric object, when a single sample view has been seen. Recognition should be particularly facilitated when the novel views are close to the virtual view. We present psychophysical results that bear out these predictions.Conclusion Our results show that the human visual system can indeed exploit symmetry to facilitate object recognition, and support the model for object recognition in which a small number of two-dimensional views are remembered and combined to recognize novel views of the same object. These results raise questions about how symmetry is recognized, and symmetry transformations implemented, in real, biological neural networks.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf679.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=GatewayURL\&_origin=CELLPRESS\&_urlversion=4\&_method=citationSearch\&_version=1\&_src=FPDF\&_piikey=S096098220000004X\&md5=23c00f1c94816b9e1adb1f936319c14a}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/S0960-9822(00)00004-X}, author = {Vetter, T and Poggio, T and B{\"u}lthoff, HH} } @Article { 683, title = {Shape from texture: ideal observers and human psychophysics}, journal = {Vision Research}, year = {1993}, month = {8}, volume = {33}, number = {12}, pages = {1723-1737}, abstract = {We describe an ideal observer model for estimating ''shape from texture'' which is derived from the principles of statistical information. For a given family of surface shapes, measures of statistical information can be computed for two different texture cues--density and orientation of texels. These measures can be used to predict lower bounds on the variance of shape judgements of ''ideal'' and human observers. They can also predict optimal weights for cue integration for the inference of shape from texture. These weights are directly proportional to the information carried by each cue. The ideal observer model therefore predicts that the variance of subjects‘ responses in a psychophysical shape judgement task should reflect the statistical importance of individual texture cues. Our results show that human performance in shape judgements for a one-parameter family of parabolic cylinders is often better than what an ideal observer achieves using a density cue alone. Therefore other information, for example the compression cue, must be used by human observers. For the first time, such results have been obtained without recourse to the unnatural cue conflict paradigms used in previous experiments. The model makes further predictions for the perception of planar slanted surfaces in the case of wide field of view.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/shape_from_texture_ideal_observers_and_human_psychophysics_683[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-484F0WC-1M1-1\&_cdi=4873\&_user=29041\&_pii=004269899390037W\&_origin=\&_coverDate=08\%2F31\%2F1993\&_sk=999669987\&view=c\&wchp=dGLzVlb-zSkzk\&md5=7c8ea94f94fababd23c327612e5d9d3a\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/0042-6989(93)90037-W}, author = {Blake, A and B{\"u}lthoff, HH and Sheinberg, DL} } @Article { 699, title = {Orientation dependence in the recognition of familiar and novel views of Three-Dimensional Objects}, journal = {Vision Research}, year = {1992}, month = {12}, volume = {32}, number = {12}, pages = {2385-2400}, abstract = {We report four experiments that investigated the representation of novel three-dimensional (3D) objects by the human visual system. In the first experiment, canonical views were demonstrated for novel objects seen equally often from all test viewpoints. The next two experiments showed that the canonical views persisted under repeated testing, and in the presence of a variety of depth cues, including binocular stereo. The fourth experiment probed the ability of subjects to generalize recognition to unfamiliar views of objects previously seen at a limited range of attitudes. Both mono and stereo conditions yielded the same increase in the error rate with misorientation relative to the training attitude. Taken together, these results support the notion that 3D objects are represented by multiple specific views, possibly augmented by partial viewer-centered 3D information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf699.pdf}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6T0W-484707D-C2-1\&_cdi=4873\&_user=29041\&_pii=004269899290102O\&_origin=\&_coverDate=12\%2F31\%2F1992\&_sk=999679987\&view=c\&wchp=dGLbVlW-zSkWl\&md5=a5343d605469bc342b55cb338ff16b73\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/0042-6989(92)90102-O}, author = {Edelman, S and B{\"u}lthoff, HH} } @Article { 697, title = {Interaction between transparency and structure from motion}, journal = {Neural Computation}, year = {1992}, month = {7}, volume = {4}, number = {4}, pages = {573-589}, abstract = {It is well-known that the human visual system can reconstruct depth from simple random-dot displays given binocular disparity or motion information. This fact has lent support to the notion that stereo and structure from motion systems rely on low-level primitives derived from image intensities. In contrast, the judgment of surface transparency is often considered to be a higher-level visual process that, in addition to pictorial cues, utilizes stereo and motion information to separate the transparent from the opaque parts. We describe a new illusion and present psychophysical results that question this sequential view by showing that depth from transparency and opacity can override the bias to see rigid motion. The brain's computation of transparency may involve a two-way interaction with the computation of structure from motion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf697.pdf}, web_url = {http://portal.acm.org/citation.cfm?id=148183}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1162/neco.1992.4.4.573}, author = {Kersten, D and B{\"u}lthoff, HH and Schwartz, BL and Kurtz, KJ} } @Article { 700, title = {Psychophysical support for a 2-D view interpolation theory of object recognition}, journal = {Proceedings of the National Academy of Science of the United States of America}, year = {1992}, month = {1}, volume = {89}, number = {1}, pages = {60-64}, abstract = {Does the human brain represent objects for recognition by storing a series of two-dimensional snapshots, or are the object models, in some sense, three-dimensional analogs of the objects they represent? One way to address this question is to explore the ability of the human visual system to generalize recognition from familiar to novel views of three-dimensional objects. Three recently proposed theories of object recognition --- viewpoint normalization or alignment of 3D models (Ullman, 1989), linear combination of two--dimensional views (Ullman and Basri, 1991) and view approximation (Poggio and Edelman, 1990) --- predict different patterns of generalization to unfamiliar views. We have exploited the conflicting predictions to test the three theories directly in a psychophysical experiment involving computer-generated three-dimensional objects. Our results suggest that the human visual system is better described as recognizing these objects by two-dimensional view interpolation than by alignment or other methods that rely on object-centered three-dimensional models.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf700.pdf}, web_url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC48175/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, author = {B{\"u}lthoff, HH and Edelman, S} } @Article { 720, title = {Stereo Integration, Mean Field Theory and Psychophysics}, journal = {Network}, year = {1991}, month = {11}, volume = {2}, number = {4}, pages = {423-442}, abstract = {We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision. This formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the matching. We use techniques from statistical physics to show how our theory relates to previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf720.pdf}, web_url = {http://www.ingentaconnect.com/content/apl/network/1991/00000002/00000004/art00006}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1088/0954-898X/2/4/006}, author = {Yuille, A and Geiger, D and B{\"u}lthoff, HH} } @Article { 709, title = {Bayesian Models for Seeing Shapes and Depth}, journal = {Comments on Theoretical Biology}, year = {1991}, month = {4}, volume = {2}, number = {4}, pages = {283-314}, abstract = {We review computational models of shape and depth perception and relate them to visual psychophysics. The Bayesian approach to vision provides a fruitful theoretical framework both for modelling individual modules, such as stereo, shading, texture and occlusion, and for integrating their information. In this formalism we represent depth by one, or more, surfaces with prior probabilities for surface shape, corresponding to natural constraints, in order to avoid the ill-posedness of vision. On theoretical grounds, the less information available to the module (and the less accurate it is) then the more important the priors become. This suggests that visual illusions, and biased perceptions, will arise for scenes for which the priors are not appropriate. We describe psychophysical experiments which are consistent with these ideas. For integration of different modules we advocate strong coupling, so that the modules can interact during computation and the priors can be modified. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration and different psychophysical experiments can be understood within the Bayesian approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf709.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, author = {B{\"u}lthoff, HH and Yuille, A} } @Article { 715, title = {Perceived depth scales with disparity gradient}, journal = {Perception}, year = {1991}, month = {2}, volume = {20}, number = {2}, pages = {145-153}, abstract = {Perceived difference in depth between two adjacent stimuli decreases with increasing disparity gradient even if the disparity stays constant, ie when the stimuli approach each other along paths within fronto-parallel planes. This depth scaling effect is more pronounced with line stimuli than with two isolated points or two small symbols and is insignificant for easily discriminable symbols. The decrease in perceived depth is more pronounced for horizontal orientation than for oblique or vertical orientation. The ratio of perceived depth difference to displayed disparity difference also decreases when the distance between the stimuli increases at a constant gradient in depth. This is to say that we are more correct in our depth estimates for steep gradients in depth when the euclidean distance between the stimuli is short.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf715.pdf}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=p200145}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1068/p200145}, author = {B{\"u}lthoff, HH and Fahle, M and Sklar, E} } @Article { 713, title = {Inverse Perspective Mapping Simplifies Optical Flow Computation and Obstacle Detection}, journal = {Biological Cybernetics}, year = {1991}, month = {1}, volume = {64}, number = {3}, pages = {177-185}, abstract = {We present a scheme for obstacle detection from optical flow which is based on strategies of biological information processing. Optical flow is established by a local ldquovotingrdquo (non-maximum suppression) over the outputs of correlation-type motion detectors similar to those found in the fly visual system. The computational theory of obstacle detection is discussed in terms of space-variances of the motion field. An efficient mechanism for the detection of disturbances in the expected motion field is based on ldquoinverse perspective mappingrdquo, i.e., a coordinate transform or retinotopic mapping applied to the image. It turns out that besides obstacle detection, inverse perspective mapping has additional advantages for regularizing optical flow algorithms. Psychophysical evidence for body-scaled obstacle detection and related neurophysiological results are discussed.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/inverse_perspective_mapping_simplifies_optical_flow_computation_and_obstacle_detection_713[0].pdf}, web_url = {http://www.springerlink.com/content/y077310v40556844/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00201978}, author = {Mallot, HA and B{\"u}lthoff, HH and Little, J and Bohrer, S} } @Article { 716, title = {Shape from Specularities: Computation and Psychophysics.}, journal = {Philosophical Transactions of the Royal Society of London B}, year = {1991}, volume = {331}, number = {1260}, pages = {237-252}, abstract = {Images of artificial and natural scenes typically contain many `specularities' generated by mirror-like reflection from glossy surfaces. Until fairly recently computational models of visual processes have tended to regard specularities as obscuring underlying scene structure. Mathematical modelling shows that, on the contrary, they are rich in local geometric information. Recent psychophysical findings support the notion that the brain can apply that information. Our results concern the inference of 3D structure from 2D shaded images of glossy surfaces. Stereoscopically viewed highlights or `specularities' are found to serve as cues for 3D local surface-geometry.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/shape_from_specularities_computation_and_psychophysics_716[0].pdf}, web_url = {http://rstb.royalsocietypublishing.org/content/331/1260/237.abstract}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1098/rstb.1991.0012}, author = {Blake, A and B{\"u}lthoff, HH} } @Article { 741, title = {Does the brain know the physics of specular reflection?}, journal = {Nature}, year = {1990}, month = {1}, volume = {343}, number = {6254}, pages = {165-168}, abstract = {Images of artificial and natural scenes typically contain many highlights generated by mirror-like reflection from glossy surfaces. Until recently, computational models of visual processes have tended to regard highlights as obscuring the structure of the underlying scene. The truth is that, on the contrary, highlights are rich in local geometric information. Here we report that the three-dimensional appearance of a highlight on a computer-simulated stereoscopic curved surface affects observers‘ judgement of surface gloss. We also show that the 3-D appearance of a highlight affects the perception of surface curvature -- that is, it can force an ambiguous convex-concave figure to change state. We thus conclude that human visual analysis seems to employ a physical model of the interaction of light with curved surfaces, a model firmly based on ray optics and differential geometry.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/does_the_brain_know_the_physics_of_specular_reflection_741[0].pdf}, web_url = {http://www.nature.com/nature/journal/v343/n6254/pdf/343165a0.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1038/343165a0}, author = {Blake, A and B{\"u}lthoff, HH} } @Article { 755, title = {A Parallel Algorithm for Real-Time Computation of Motion}, journal = {Nature}, year = {1989}, month = {2}, volume = {337}, number = {6207}, pages = {549-553}, abstract = {The precise measurement of the two-dimensional field of velocities from time-varying two-dimensional images is impossible in general. It is, however, possible to compute suitable 'optical flows' that are qualitatively similar to the velocity field in most cases. We describe a simple, parallel algorithm that computes an optical flow from sequences of real images, which is consistent with human psychophysics and suggests plausible physiological models. In particular, our algorithm runs on a Connection Machine supercomputer in close-to-real time. It shows several of the same ''illusions9 that are perceived by humans. A natural physiological implementation of the model is consistent with data from cortical areas V1 and MT.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/a_parallel_algorithm_for_real_time_computation_of_optical_flow_755[0].pdf}, web_url = {http://www.nature.com/nature/journal/v337/n6207/pdf/337549a0.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1038/337549a0}, author = {B{\"u}lthoff, HH and Little, JJ and Poggio, T} } @Article { 775, title = {Integration of depth modules: stereo and shading}, journal = {Journal of the Optical Society of America A}, year = {1988}, month = {10}, volume = {5}, number = {10}, pages = {1749-1758}, abstract = {We studied the integration of image disparities, edge information, and shading in the three-dimensional perception of complex yet well-controlled images generated with a computer-graphics system. The images showed end-on views of flat- and smooth-shaded ellipsoids, i.e., images with and without intensity discontinuities (edges). A map of perceived depth was measured by adjusting a small stereo depth probe interactively to the perceived surface. Our data show that disparate shading (even in the absence of disparate edges) yields a vivid stereoscopic depth perception. The perceived depth is significantly reduced if the disparities are completely removed (shape-from-shading). If edge information is available, it overrides both shape-from-shading and disparate shading. Degradations of depth perception corresponded to a reduced depth rather than to an increased scatter in the depth measurement. The results are compared with computer-vision algorithms for both single cues and their integration for three-dimensional vision.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf775.pdf}, web_url = {http://www.opticsinfobase.org/viewmedia.cfm?uri=josaa-5-10-1749\&seq=0}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1364/JOSAA.5.001749}, author = {B{\"u}lthoff, HH and Mallot, HA} } @Article { 783, title = {Using Neuropharmacology to Distinguish between Excitatory and Inhibitory Movement Detection Mechanisms in the Fly Calliphora erythrocephala}, journal = {Biological Cybernetics}, year = {1988}, month = {7}, volume = {59}, number = {2}, pages = {71-80}, abstract = {By combining neuropharmacology and electrophysiology, we tried to determine whether the main neuronal mechanism responsible for direction-selective motion detection in the fly is based on an excitatory or an inhibitory synaptic interaction. By blocking inhibitory interactions with picrotoxinin, an antagonist of the inhibitory neurotransmitter GABA, we could abolish most of the directional selectivity of a large-field movement-sensitive neuron (HI-cell) in the lobula plate of the blowfly Calliphora erythrocephala. These modifications are similar to changes observed in the optomotor response of the fruitfly Drosophila melanogaster after application of picrotoxinin (B{\"u}lthoff and B{\"u}lthoff l987a, b). Assuming a simplified logical model, these results are compatible with inhibitory synaptic interactions at the level of the elementary movement detectors. The picrotoxinin induced changes in direction selectivity are not due to modifications of the peripheral visual processing in the retina and lamina. This was show n by simultaneous recordings of the electroretinogram and the HI-cell. The latencies between drug injections into various parts of the brain and their first effects on the HI-cell suggest that the inhibitory mechanism for motion detection is located in the medulla rather than in the lobula plate.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/using_neuropharmacology_to_distinguish_between_excitatory_and_inhibitory_movement_detection_mechanisms_783[0].pdf}, web_url = {http://www.springerlink.com/content/g14q11gxh2237421/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00317769}, author = {Schmid, A and B{\"u}lthoff, HH} } @Article { 1277, title = {Independent spatial waves of biochemical differentiation along the surface of chicken brain as revealed by the sequential expression of acetylcholinesterase}, journal = {Cell and Tissue Research}, year = {1988}, month = {3}, volume = {251}, number = {3}, pages = {587-595}, abstract = {AChE-positive cells suddenly amass in a superficial layer of the neuroepithelium; this layer finally covers, in a sheat-like manner, the entire surface of the embryonic chicken brain. This feature is functionally not understood; however, it appears shortly after the neurons become post-mitotic, and the lateral extensions of this layer can easily be traced using histochemistry on serial brain sections. The layer can therefore be exploited to delineate spatially the waves of onset of biochemical tissue differentiation. We have studied whole brains between stages 11 and 30 and provide the first complete spatial schemes of brain differentiation based on computer-reconstructed, two- and three-dimensional maps. The brain does not differentiate in one smooth coherent wave, but instead five separate primary AChE-activation zones are detected: the first originating at stage 11 (ldquorhombencephalic waverdquo), the second at the same time (ldquomidbrain waverdquo), the third at stage 15 (''ldquotectal waverdquo). A fourth zone develops later, at stage 18, from the bottom part of the telencephalon to the top. Retinal development also starts at stage 18. In a given area, it appears that AChE-development shortly precedes that of the formation of major fiber tracts. AChE might therefore represent a prerequisite for fiber growth and pathfinding.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/independent_spatial_waves_of_biochemical_differentiation_1277[0].pdf}, department = {Department G{\"o}tz}, web_url = {http://www.springerlink.com/content/n5226k8p6n6jhw55/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00214007}, author = {Layer, PG and Rommel, S and B{\"u}lthoff, HH and Hengstenberg, R} } @Article { 833, title = {GABA-antagonist inverts movement and object detection in flies}, journal = {Brain Research}, year = {1987}, month = {3}, volume = {407}, number = {1}, pages = {152-158}, abstract = {Movement detection is one of the most elementary visual computations performed by vertebrates as well as invertebrates. However, comparatively little is known about the biophysical mechanisms underlying this computation. It has been proposed on both physiological1.8.21 and theoretical2.15.23 grounds that inhibition plays a crucial role in the directional selectivity of elementary movement detectors (EMDs). For the first time, we have studied electrophysiological and behavioral changes induced in flies after application of picrotoxinin, an antagonist of GABA. The results show that inhibitory interactions play an important role in movement detection in flies. Furthermore, our behavioral results suggest that the computation of object position is based primarily on movement detection.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf833.pdf}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6SYR-485RK87-1R-1\&_cdi=4841\&_user=29041\&_pii=0006899387912303\&_origin=\&_coverDate=03\%2F24\%2F1987\&_sk=995929998\&view=c\&wchp=dGLzVzz-zSkzS\&md5=d8090eb575009f2a056c984b1b95a05d\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/0006-8993(87)91230-3}, author = {B{\"u}lthoff, HH and B{\"u}lthoff, I} } @Article { 823, title = {Combining Neuropharmacology and Behavior to Study Motion Detection in Flies.}, journal = {Biological Cybernetics}, year = {1987}, month = {2}, volume = {55}, number = {5}, pages = {313-320}, abstract = {The optomotor following response, a behavior based on movement detection was recorded in the fruitflyDrosophila melanogaster before and after the injection of picrotoxinin, an antagonist of the inhibitory neurotransmitter GABA. The directional selectivity of this response was transiently abolished or inverted after injection. This result is in agreement with picrotoxinin-induced modifications observed in electrophysiological activity of direction-selective cells in flies (B{\"u}lthoff and Schmid 1983; Schmid and B{\"u}lthoff, in preparation). Furthermore, walking and flying flies treated with picrotoxinin followed more actively motion from back to front instead of front to back as in normal animals. Since the difference in the responses to front to back and back to front motions is proposed to be the basis of fixation behavior in flies (Reichardt 1973) our results support this notion and are inconsistent with schemes explaining fixation by alternative mechanisms.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/combining_neuropharmacology_and_behavior_to_study_motion_detection_in_flies_823[0].pdf}, web_url = {http://www.springerlink.com/content/y056t6h64564n574/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF02281977}, author = {B{\"u}lthoff, HH and B{\"u}lthoff, I} } @Article { 843, title = {Identification of [3H]deoxyglucose-labelled interneurons in the fly from serial autoradiographs}, journal = {Brain Research}, year = {1984}, month = {7}, volume = {305}, number = {2}, pages = {384-388}, abstract = {Using the [3H]deoxyglucose technique we find in the third visual ganglion of the fly,Musca domestica, a number of neuronal profiles whose labelling strongly depends on the direction of visual movement. By reconstruction from serial autoradiographs of semithin sections the three-dimensional morphology of the labelled profiles, we demonstrate that cell bodies, neurites, axons and arborizations of two interneurons are labelled whose homologues inCalliphora have been identified as movement-sensitive centrifugal horizontal cells (‘CH-cells’). A set of three other cells whose homologues inCalliphora show similar electrophysiological responses to horizontal movement (‘HS-cells’) exhibit very little label on either side. It is suggested that the relation between deoxyglucose mapping and physiological activity can be investigated at the cellular level by using this system of fly interneurons.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/identification_of_3hdeoxyglucose_labelled_interneurons_in_the_fly_from_serial_autoradiographs_843[0].pdf}, web_url = {http://www.sciencedirect.com/science?_ob=MImg\&_imagekey=B6SYR-4835VPT-5F-1\&_cdi=4841\&_user=29041\&_pii=0006899384904487\&_origin=\&_coverDate=07\%2F09\%2F1984\&_sk=996949997\&view=c\&wchp=dGLzVzb-zSkWB\&md5=88804cf822ec949054f4b837dc014cab\&ie=/sdarticle.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1016/0006-8993(84)90448-7}, author = {Buchner, E and Buchner, S and B{\"u}lthoff, HH} } @Article { 854, title = {Recurrent Inversion of Visual Orientation in the Walking Fly, Drosophila melanogaster}, journal = {Journal of Comparative Physiology}, year = {1982}, month = {12}, volume = {148}, number = {4}, pages = {471-481}, abstract = {Movement-induced visual orientation in flies depends largely upon predictable responses which establish simple ldquooptomotor balancerdquo or complex ldquopseudo searchrdquo in the appropriate visual environment. Less conspicuous course diverting spontaneous actions of the flies become important in pattern-induced visual orientation. The apparently stochastic spontaneous actions of the houseflyMusca domestica still allow powerful probabilistic predictions of orientation during stationary flight (Reichardt and Poggio 1981). The predominance of non-stochastic spontaneous actions such as ldquobody saccadesrdquo, focussing and shift of ldquovisual attentionrdquo, plasticity of response components etc. in the fruitflyDrosophila melanogaster (Heisenberg and Wolf 1979–1980) accounts for complementary behavioural options which reduce the relevance of probabilistic predictions of orientation in this fly. The conjecture of ldquocomplementary optionsrdquo is based on a striking antagonism between orientation towards a visual object (fixation), and orientation in the opposite direction (anti-fixation), in the walking fly. Forced choice in a multiple-Y-maze quite definitely elicits fixation in the wild type, and antifixation in the ldquooptomotor blindrdquo mutantomb H31 (Fig. 3). However, these effects cannot be attributed to a continuous predominance of attraction in the wild type and repellence in the mutant. This is shown under comparable conditions of free choice in an arena: The flies of either strain alternate between fixation and anti-fixation of an inaccessible visual object (Fig. 4a), and keep running to and fro between two of these objects in ldquoBuridan's paradigmrdquo (Fig. 4b, c), even if the objects are not alike (Fig. 4d). The sequence of approach, retreat and transition may be repeated a few thousand times to the point of exhaustion (Fig. 5). The process resembles the recurrent alternation of ambiguous figures such as the Necker cube in human perception. The recurrent transition between competitive objects counteracts the accumulation of spontaneous preferences, and is likely to explain the apparent lack of pattern-discrimination under operant and non-operant conditions of continued free choice inDrosophila. The conspicuous dichotomy of fixation and anti-fixation in the same environment is, as yet, incompatible with the phenomenological theory of visually controlled orientation in larger flies.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/recurrent_inversion_of_visual_orientation_in_the_walking_fly_drosophila_melanogaster_854[0].pdf}, department = {Department G{\"o}tz}, web_url = {http://www.springerlink.com/content/t3387xj869267630/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00619785}, author = {B{\"u}lthoff, HH and G{\"o}tz, KG and Herre, M} } @Article { 856, title = {Tracking and chasing in houseflies (Musca): An analysis of 3-D flight trajectories}, journal = {Biological Cybernetics}, year = {1982}, month = {9}, volume = {45}, number = {2}, pages = {123-130}, abstract = {The flight trajectories of free flying female and male houseflies have been analyzed in 3 dimensions. Both female and male flies track other flies. The turning velocity agr (around the vertical axis) is linearly dependent upon the horizontal angle psgrF (that is the angle between the trajectory of the tracking fly and the target) for small values of psgrF in females and for the whole range of psgrF in males. The 3-dimensional velocity ugr xyz of the chasing fly is linearly dependent upon the distance between leading and chasing fly in males but not in females. Male chasing thus appears to be more efficient than female tracking. It is shown that earlier assumptions on visual control of flight in female flies derived from experiments on fixed flying flies are justified.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/tracking_and_chasing_in_houseflies_856[0].pdf}, department = {Department Reichardt}, web_url = {http://www.springerlink.com/content/l241007721762545/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00335239}, author = {Wehrhahn, C and Poggio, T and B{\"u}lthoff, HH} } @Article { 850, title = {Drosophila Mutants Disturbed in Visual Orientation I: Mutants affected in Early Visual Processing}, journal = {Biological Cybernetics}, year = {1982}, month = {8}, volume = {45}, number = {1}, pages = {63-70}, abstract = {With the Y-maze selection technique described in Part I 2 strains of probably central nervous system (CNS) mutants have been isolated. These mutants show defects in the computation of both position and movement. One of these mutants (nofEB12) shows strong avoidance of small patterns moving with high velocity. This inversion of the object-induced orientation response can be mainly attributed to a modification of responses to fast progressive (front-to-back) movement. It is thus possible that overall optomotor behaviour may be decomposed into a set of genetically independent modules.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/drosophila_mutants_disturbed_in_visual_orientation_mutants_affected_in_early_visual_processing_850[0].pdf}, web_url = {http://www.springerlink.com/content/q722t1808475u318/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00387216}, author = {B{\"u}lthoff, HH} } @Article { 851, title = {Drosophila Mutants Disturbed in Visual Orientation II: Mutants Affected in Movement and Position Computation}, journal = {Biological Cybernetics}, year = {1982}, month = {8}, volume = {45}, number = {1}, pages = {71-77}, abstract = {With the Y-maze selection technique described in Part I 2 strains of probably central nervous system (CNS) mutants have been isolated. These mutants show defects in the computation of both position and movement. One of these mutants (nofEB12) shows strong avoidance of small patterns moving with high velocity. This inversion of the object-induced orientation response can be mainly attributed to a modification of responses to fast progressive (front-to-back) movement. It is thus possible that overall optomotor behaviour may be decomposed into a set of genetically independent modules.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/drosophila_mutants_disturbed_in_visual_orientation_mutants_affected_in_movement_and_position_computation_851[0].pdf}, web_url = {http://www.springerlink.com/content/q722t1808475u318/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1007/BF00387216}, author = {B{\"u}lthoff, HH} } @Article { 853, title = {Isolation of sex-linked mutants disturbed in visual orientation}, journal = {Drosophila Information Service}, year = {1982}, month = {8}, volume = {58}, pages = {32-33}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/isolation_of_sex-linked_mutants_disturbed_in_visual_orientation_853[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, author = {B{\"u}lthoff, HH} } @Article { 858, title = {Visual orientation of Drosophila mutants in a multiple Y-maze}, journal = {Drosophila Information Service}, year = {1982}, month = {8}, volume = {58}, pages = {31}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/visual_orientation_of_drosophila_mutants_in_a_multiple_y-maze_858[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, author = {B{\"u}lthoff, HH} } @Article { 860, title = {Figure-ground discrimination in the visual system of Drosophila melanogaster}, journal = {Biological Cybernetics}, year = {1981}, month = {8}, volume = {41}, number = {2}, pages = {139-145}, abstract = {Drosophila melanogaster is able to detect a small visual object hidden in a background of identical texture, as long as there is relative motion between their retinal images. The properties of figure-ground discrimination in the walking fly are studied under experimental conditions where the positions of figure and ground oscillate sinusoidally with similar frequency and similar amplitude but with different phase. The following points have been established. (a) The average turning reaction of the stationarily walkingDrosophila depends on phase; contrary to results obtained with the flyingMusca (Reichardt and Poggio, 1979), antiphasic oscillation of figure and ground does not suppress the attrativeness of the figure. (b) A translatory response has been found which also depends on the phase difference of the oscillatory movements of figure and ground. (c) The time course of the responses and its intra- and inter-individual variability do not seem to fit into a rigid model of figure-ground discrimination.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf860.pdf}, url2 = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/abstract_figure_ground_discrimination_in_the_visual_system_of_drosophila_melanogaster_860[1].pdf}, department = {Department G{\"o}tz}, web_url = {http://www.springerlink.com/content/u4237t2u148t4428/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, DOI = {10.1007/BF00335368}, author = {B{\"u}lthoff, HH} } @Article { 863, title = {3-D Analysis of the Flight Trajectories of Flies (Drosophila melanogaster)}, journal = {Zeitschrift f{\"u}r Naturforschung C}, year = {1980}, month = {10}, volume = {35}, number = {9-10}, pages = {811-815}, abstract = {We have developed a computer system for reconstructing and analyzing three dimensional flight trajectories of flies. Its application to the study of the free flight behaviour of the fruitfly Drosophila melanogaster is described. The main results are: a) Drosophila males only occasionally track other flies; b) in such cases the fly's angular velocity is a function of the error angle under which the leading fly is seen; c) body saccades can be demonstrated during cruising flights; d) high angular velocities are strongly correlated with low forward velocities, probably reflecting an aerodynamic constraint of flight. The 3-D technique described may provide an adequate tool for studying the organization of the systems present in flies and for relating the free flight behaviour to previous analyses of tethered flies.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf863.pdf}, url2 = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/3_d_analysis_of_the_flight_trajectories_of_flies_VERBESSERTE_VERSION_863[1].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, author = {B{\"u}lthoff, HH and Poggio, T and Wehrhahn, C} } @Article { 865, title = {Analogous motion illusion in man and fly}, journal = {Nature}, year = {1979}, month = {4}, volume = {278}, number = {5705}, pages = {636-638}, abstract = {Since Wertheimer's classic paper1, research in motion perception has been concerned with the study of visual illusions such as phi-motion. Various phenomena of this type are easy to elicit by successive changes of the light flux in spatially distinct photoreceptors, and easy to explain by the specific properties of the motion detectors, although there are reports to the contrary2. The present account deals with a less easily comprehensible illusion which is elicited by simultaneous changes of the light flux in differently illuminated receptors3−5. The phenomenon has previously been ascribed to the prolonged latency of the 'light-on' responses at lower levels of illumination which converts simultaneous stimuli into successive signals6, but this does not explain the illusion satisfactorily3. MacKay and co-workers were the first to attribute the apparent motion to the adaptive properties of the input channels of the motion detectors4. We show that the illusion can be induced in the fruitfly, Drosophila melanogaster, as well as in man. The course control response to motion provides a quantitative assay of the illusion in the fly. The results suggest that the illusion originates in the distortion of the visual signals before motion detection.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/analogous_motion_illusion_in_man_and_fly_865[0].pdf}, department = {Department G{\"o}tz}, web_url = {http://www.nature.com/nature/journal/v278/n5705/pdf/278636a0.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, DOI = {10.1038/278636a0}, author = {B{\"u}lthoff, HH and G{\"o}tz, KG} } @Inproceedings { ChuangNB2013, title = {A Fixed-Based Flight Simulator Study: The Interdependence of Flight Control Performance and Gaze Efficiency}, year = {2013}, month = {7}, pages = {1-10}, abstract = {Here, a descriptive study is reported that addresses the relationship between flight control performance and instrument scanning behavior. This work was performed in a fixed-based flight simulator. It targets the ability of untrained novices to pilot a lightweight rotorcraft in a flight scenario that consisted of fundamental mission task elements such as speed and altitude changes. The results indicate that better control performance occurs when gaze is more selective for and focused on key instruments. Ideal instrument scanning behavior is proposed and its relevance for training instructions and visual instrument design is discussed.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/HCI-I-2013-Chuang.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.hcii2013.org/}, event_place = {Las Vegas, NV, USA}, event_name = {15th International Conference on Human-Computer Interaction (HCI International 2013)}, state = {accepted}, author = {Chuang, LL and Nieuwenhuizen, FM and B{\"u}lftoff, HH} } @Inproceedings { SecchiFBR2013, title = {Bilateral Control of the Degree of Connectivity in Multiple Mobile-robot Teleoperation}, year = {2013}, month = {5}, pages = {-}, abstract = {This paper presents a novel bilateral controller that allows to stably teleoperate the degree of connectivity in the mutual interaction between a remote group of mobile robots considered as the slave-side. A distributed leaderfollower scheme allows the human operator to command the overall group motion. The group autonomously maintains the connectivity of the interaction graph by using a decentralized gradient descent approach applied to the Fiedler eigenvalue of a properly weighted Laplacian matrix. The degree of connectivity, and then the flexibility, of the interaction graph can be finely tuned by the human operator through an additional bilateral teleoperation channel. Passivity of the overall system is theoretically proven and extensive human/hardware in-the-loop simulations are presented to empirically validate the theoretical analysis.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/2013d-SecFraBueRob.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2013.org/}, event_place = {Karlsruhe, Germany}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2013)}, state = {accepted}, author = {Secchi, C and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { RiedelFRBS2012, title = {Experiments on Intercontinental Haptic Control of Multiple UAVs}, year = {2013}, pages = {227-238}, abstract = {In this paper we propose and experimentally validate a bilateral teleoperation framework where a group of UAVs are controlled over an unreliable network with typical intercontinental time delays and packet losses. This setting is meant to represent a realistic and challenging situation for the stability the bilateral closed-loop system. In order to increase human telepresence, the system provides the operator with both a video stream coming from the onboard cameras mounted on the UAVs, and with a suitable haptic cue, generated by a forcefeedback device, informative of the UAV tracking performance and presence of impediments on the remote site. In addition to the theoretical background, we describe the hardware and software implementation of this intercontinental teleoperation: this is composed of a semi-autonomous group of multiple quadrotor UAVs, a 3-DOF haptic interface, and a network connection based on a VPN tunnel between Germany and South Korea. The whole software framework is based upon the Robotic Operating System (ROS) communication standard.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/IAS-2012-Riedel2.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ias-12.org/main/}, editor = {Lee, S. , H. Cho, K.-J. Yoon, J. Lee}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Intelligent Autonomous Systems 12}, event_place = {Jeju Island, South Korea}, event_name = {12th International Conference on Intelligent Autonomous Systems (IAS-12)}, ISBN = {978-3-642-33931-8}, DOI = {10.1007/978-3-642-33932-5_22}, author = {Riedel, M and Franchi, A and Robuffo Giordano, P and B{\"u}lthoff, HH and Son, HI} } @Inproceedings { LacheleFBR2012, title = {SwarmSimX: Real-time Simulation Environment for Multi-robot Systems}, year = {2012}, month = {11}, pages = {375-387}, abstract = {In this paper we present a novel simulation environment called SwarmSimX with the ability to simulate dozens of robots in a realistic 3D environment. The software architecture of SwarmSimX allows new robots, sensors, and other libraries to be loaded at runtime, extending the functionality of the simulation environment significantly. In addition, SwarmSimX allows an easy exchange of the underlying libraries used for the visual and physical simulation to incorporate different libraries (e.g., improved or future versions). A major feature is also the possibility to perform the whole simulation in real-time allowing for human-in-the-loop or hardware-in-the-loop scenarios. SwarmSimX has been already employed in several works presenting haptic shared control of multiple mobile robots (e.g., quadrotor UAVs). Additionally, we present here two validation tests showing the physical fidelity and the real-time performance of SwarmSimX. For the tests we used NVIDIA® PhysX® and Ogre3D as physics and rendering libraries, respectively.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012m-LaeFraBueRob-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.2012.simpar.org/}, editor = {Noda, I. , N. Ando, D. Brugali, J.J. Kuffner}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Simulation, Modeling, and Programming for Autonomous Robots}, event_place = {Tsukuba, Japan}, event_name = {3rd International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR 2012)}, ISBN = {978-3-642-34326-1}, DOI = {10.1007/978-3-642-34327-8_34}, author = {L{\"a}chele, J and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { SpicaFOBR2012, title = {Aerial Grasping of a Moving Target with a Quadrotor UAV}, year = {2012}, month = {10}, pages = {4985-4992}, abstract = {Abstract—For a quadrotor aircraft, we study the problem of planning a trajectory that connects two arbitrary states while allowing the UAV to grasp a moving target at some intermediate time. To this end, two classes of canonical grasping maneuvers are defined and characterized. A planning strategy relying on differential flatness is then proposed to concatenate one or more grasping maneuvers by means of spline-based subtrajectories, with the additional objective of minimizing the total transfer time. The proposed planning algorithm is not restricted to pure hovering-to-hovering motions and takes into account practical constraints, such as the finite duration of the grasping phase. The effectiveness of the proposed approach is shown by means of physically-based simulations.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/IROS-2012-Spica.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2012.org/site/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Vilamoura, Portugal}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012)}, ISBN = {978-1-4673-1737-5}, DOI = {10.1109/IROS.2012.6385771}, author = {Spica, R and Franchi, A and Oriolo, G and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { SonHBL2012, title = {Effects of imperfect communication network on haptic teleoperator's performance}, year = {2012}, month = {10}, pages = {1772-1777}, abstract = {There is, practically, imperfect communication network (e.g., time delay and packet loss/switching) in haptic interaction (or teleoperation) systems. It is well known that such imperfect communication degrades teleoperator's performance as well as stability. We hypothesis that as an imperfectness level in the communication network is increasing, the teleoperator's performance is decreasing monotonically. In this paper, we verified the hypothesis via a human-centered evaluation of the teleoperator's perceptual performance in terms of just noticeable difference (JND), point of subject equality (PSE), and perception time using two psychophysical experiments: experiment of packet separation time and experiment of packet loss. In the experiment of packet separation time, there were significant increases of JND and PSE as the packet separation time was increased. However, interestingly, there was no significant decrease of teleoperator's perceptual performance in the experiment of packet loss although the packet loss rate was increased until 75 \%. The experimental results clearly shows that the packet separation time affects on the teleoperator's perceptual performance more than the packet loss rate.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=06393131}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Jeje, South Korea}, event_name = {12th International Conference on Control, Automation and Systems (ICCAS 2012)}, ISBN = {978-1-4673-2247-8}, author = {Son, HI and Hong, A and B{\"u}lthoff, HH and Lee, D} } @Inproceedings { VenrooijMvAvMB2012, title = {How effective is an armrest in mitigating biodynamic feedthrough?}, year = {2012}, month = {10}, pages = {2150-2155}, abstract = {Biodynamic feedthrough (BDFT) refers to a phenomenon where vehicle accelerations feed through the human body, causing involuntary limb motions, which may cause involuntary control inputs. Many studies have been devoted to mitigating BDFT effects. In the current paper, the effectiveness of a simple, cheap and widely-used hardware component is studied: the armrest. An experiment was conducted in which the BDFT dynamics were measured with and without armrest for different levels of neuromuscular admittance (i.e., different settings of the limb dynamics). The results show that the effect of the armrest on BDFT dynamics varies, both with frequency and neuromuscular admittance.}, department = {Department B{\"u}lthoff}, web_url = {http://www.smc2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Seoul, South Korea}, event_name = {IEEE International Conference on Systems, Man, and Cybernetics (SMC 2012)}, ISBN = {978-1-4673-1713-9}, DOI = {10.1109/ICSMC.2012.6378058}, author = {Venrooij, J and Mulder, M and van Paassen, MM and Abbink, DA and van der Helm, VCT and M, Mulder and B{\"u}lthoff, HH} } @Inproceedings { DropPDVM2012_2, title = {Identification of the Transition from Compensatory to Feedforward Behavior in Manual Control}, year = {2012}, month = {10}, pages = {2008-2013}, abstract = {The human in manual control of a dynamical system can use both feedback and feedforward control strategies and will select a strategy based on performance and required effort. Literature has shown that feedforward control is used during tracking tasks in response to predictable targets. The influence of an external disturbance signal on the utilization of a feedforward control strategy has never been investigated, however. We hypothesized that the human will use a combined feedforward and feedback control strategy whenever the predictable target signal is sufficiently strong, and a predominantly feedback strategy whenever the random disturbance signal is dominant. From the data of a human-in-the-loop experiment we conclude that feedforward control is used in all the considered experimental conditions, including those where the disturbance signal is dominant and feedforward control does not deliver a marked performance advantage.}, department = {Department B{\"u}lthoff}, web_url = {http://www.smc2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Seoul, South Korea}, event_name = {IEEE International Conference on Systems, Man, and Cybernetics (SMC 2012)}, ISBN = {978-1-4673-1713-9}, DOI = {10.1109/ICSMC.2012.6378033}, author = {Drop, FM and Pool, DM and Damveld, HJ and van Paassen, MM and B{\"u}lthoff, HH and Mulder, M} } @Inproceedings { MasoneFBR2012, title = {Interactive Planning of Persistent Trajectories for Human-Assisted Navigation of Mobile Robots}, year = {2012}, month = {10}, pages = {2641-2648}, abstract = {This work extends the framework of bilateral shared control of mobile robots with the aim of increasing the robot autonomy and decreasing the operator commitment. We consider persistent autonomous behaviors where a cyclic motion must be executed by the robot. The human operator is in charge of modifying online some geometric properties of the desired path. This is then autonomously processed by the robot in order to produce an actual path guaranteeing: i) tracking feasibility, ii) collision avoidance with obstacles, iii) closeness to the desired path set by the human operator, and iv) proximity to some points of interest. A force feedback is implemented to inform the human operator of the global deformation of the path rather than using the classical mismatch between desired and executed motion commands. Physically-based simulations, with human/hardware-in-the-loop and a quadrotor UAV as robotic platform, demonstrate the feasibility of the method.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/IROS-2012-Masone.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2012.org/site/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Vilamoura, Portugal}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012)}, ISBN = {978-1-4673-1737-5}, DOI = {10.1109/IROS.2012.6386171}, author = {Masone, C and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, R} } @Inproceedings { RiedelFBR2012, title = {Intercontinental haptic control and advanced supervisory interfaces for groups of multiple UAVs}, year = {2012}, month = {10}, pages = {-}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/HFR-2012-Riedel.pdf}, department = {Department B{\"u}lthoff}, talk_type = {Abstract Talk}, web_url = {http://hfr2012.wordpress.com/}, event_place = {Bruxelles, Belgium}, event_name = {5th Workshop for Young Researchers on Human-Friendly Robotics (HFR 2012)}, author = {Riedel, M and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { GrabeBR2012, title = {Robust Optical-Flow Based Self-Motion Estimation for a Quadrotor UAV}, year = {2012}, month = {10}, pages = {2153-2159}, abstract = {Robotic vision has become an important field of research for micro aerial vehicles in the recent years. While many approaches for autonomous visual control of such vehicles rely on powerful ground stations, the increasing availability of small and light hardware allows for the design of more independent systems. In this context, we present a robust algorithm able to recover the UAV ego-motion using a monocular camera and on-board hardware. Our method exploits the continuous homography constraint so as to discriminate among the observed feature points in order to classify those belonging to the dominant plane in the scene. Extensive experiments on a real quadrotor UAV demonstrate that the estimation of the scaled linear velocity in a cluttered environment improved by a factor of 25\% compared to previous approaches.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/IROS-2012-Grabe.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2012.org/site/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Vilamoura, Portugal}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012)}, ISBN = {978-1-4673-1737-5}, DOI = {10.1109/IROS.2012.6386234}, author = {Grabe, V and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { MasoneFBR2012_2, title = {Shared trajectory planning for human-in-the-loop navigation of mobile robots in cluttered environments}, year = {2012}, month = {10}, pages = {-}, abstract = {The advances made in the last two decades have allowed robotic platforms, and in particular mobile robots, to successfully address a large variety of tasks, albeit mainly repetitive and simple ones. However, real-world applications typically involve complex decision making processes and non structured environments thus requiring a level of perception/world awareness and cognitive capabilities that cannot yet be provided by a robot. For this reason it is convenient, if not mandatory, to have a human supervising the execution. The robot shared control framework (see, e.g., [1], [2]) represents a promising step in this direction, since it allows to merge robots (limited) autonomy and humans cognitive capabilities. Previous studies have applied this idea to mobile robots navigating in cluttered environments, with an emphasis on bilateral shared control architectures with haptic feedback for the human operator. Typically, the operator commands a motion (desired position, reference velocity) to the robot via a haptic device. The robot executes the command while retaining some autonomy in order to, e.g., avoid obstacles or other dangers. Finally, the loop is closed by rendering on the haptic feedback a force that is proportional to the mismatch between commanded and executed motion in order to increase the operator’s situational awareness. Despite being an effective approach, commanding direct motion inputs requires a high commitment of the human, especially when the task is very complex or the environment is highly cluttered. Therefore, we propose an extension to the shared control in which an operator acts at the planning level, in order to modify some characteristics of the task but without the burden of directly driving the robot [3]. We assume that a task scheduler generates an initial trajectory based only on prior information. The trajectory is described as i) a geometric path controls to the set of parameters x, allowing the user to command some global behavior, e.g. translations or rotations of the curve. At the same time, the robot must track the generated trajectory and, whenever needed, modify it in real time in order to avoid collisions or to reach a nearby target. In particular, the robot performs both a reactive deformation of the reference trajectory and a planning of alternative paths. Finally, the bilateral component of the human-robot interaction is realized by feeding back to the operator a force cue informative of the global deformation acting on the desired path rather than on a local mismatch between commanded and executed position/velocity. Summarizing, the novel elements of this approach are: i) broadening the classical shared control approach by endowing the mobile robot with a higher planning autonomy, ii) allowing a human operator to act at the planning level rather than at the motion control level, iii) generating a force cue informative of the global deformation of the desired path rather than of the mismatch between direct motion commands and their execution. The proposed method has been extensively tested with human/hardware in-the-loop simulations, featuring a physically simulated quadrotor aerial vehicle and a haptic device (see Fig. 1).}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/HFR-2012-Masone.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://hfr2012.wordpress.com/}, event_place = {Bruxelles, Belgium}, event_name = {5th International Workshop on Human-Friendly Robotics (HFR 2012)}, author = {Masone, C and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { VenrooijPMvB2012, title = {A practical biodynamic feedthrough model for helicopters}, year = {2012}, month = {9}, pages = {1-13}, abstract = {Biodynamic feedthrough (BDFT) occurs when vehicle vibrations and accelerations feed through the pilot’s body and cause involuntary motion of limbs, resulting in involuntary control inputs. BDFT can severely reduce ride comfort, control accuracy and, above all, safety during the operation of rotorcraft. Furthermore, BDFT can cause and sustain Rotorcraft-Pilot Couplings (RPCs). Despite many studies conducted in past decades – both within and outside of the rotorcraft community – BDFT is still a poorly understood phenomenon. The complexities involved in BDFT have kept researchers and manufacturers in the rotorcraft domain from developing robust ways of dealing with its effects. A practical BDFT pilot model, describing the amount of involuntary control inputs as a function of accelerations, could pave the way to account for adversive BDFT effects. In the current paper, such a model is proposed. Its structure is based on the model proposed by Mayo [1], its accuracy and usability are improved by incorporating insights from recently obtained experimental data. An evaluation of the model performance shows that the model describes the measured data well and that it provides a considerable improvement to the original Mayo model. Furthermore, the results indicate that the neuromuscular dynamics have an important influence on the BDFT model parameters.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/ERF-2012-Venrooij.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://erf2012.nlr.nl/}, event_place = {Amsterdam, Netherlands}, event_name = {38th European Rotorcraft Forum (ERF 2012)}, author = {Venrooij, J and Pavel, MD and Mulder, M and van der Helm, FCT and B{\"u}lthoff, HH} } @Inproceedings { NestiMBRBP2012, title = {Roll rate thresholds and perceived realism in driving simulation}, year = {2012}, month = {9}, pages = {1-6}, abstract = {Due to limited operational space, in dynamic driving simulators it is common practice to implement motion cueing algorithms that tilt the simulator cabin to reproduce sustained accelerations. In order to avoid conflicting inertial cues, the tilt rate is kept below drivers’ perceptual thresholds, which are typically derived from the results of classical vestibular research where additional sensory cues to self-motion are removed. Here we conduct two experiments in order to assess whether higher tilt limits can be employed to expand the user’s perceptual workspace of dynamic driving simulators. In the first experiment we measure detection thresholds for roll in conditions that closely resemble typical driving. In the second experiment we measure drivers’ perceived realism in slalom driving for sub-, near- and supra-threshold roll rates. Results show that detection threshold for roll in an active driving task is remarkably higher than the limits currently used in motion cueing algorithms to drive simulators. Supra-threshold roll rates in the slalom task are also rated as more realistic. Overall, our findings suggest that higher tilt limits can be successfully implemented in motion cueing algorithms to better optimize simulator operational space.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/DSC-2012-Nest.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dsc2010.ensam.eu/}, event_place = {Paris, France}, event_name = {Driving Simulation Conference Europe (DSC 2012)}, author = {Nesti, A and Masone, C and Barnett-Cowan, M and Robuffo Giordano, P and B{\"u}lthoff, HH and Pretto, P} } @Inproceedings { BiegCFRB2012, title = {Einfluss von Ablenkung und Augenbewegungen auf Steuerungsaufgaben}, year = {2012}, month = {8}, pages = {341-344}, abstract = {In der vorliegenden Studie wurde der Einfluss visueller Ablenkung auf Steuerungsaufgaben untersucht. Die Ergebnisse deuten darauf hin, dass bereits eine kurze Verlagerung der Aufmerksamkeit und des Blicks mit einer systematischen Beeinflussung der Steuerungsaufgabe einhergeht. Im Gegenzug findet auch eine systematische Beeinflussung der Augenbewegungen durch die gleichzeitig durchgef{\"u}hrte Steuerungsaufgabe statt. Die Ber{\"u}cksichtigung solcher Interferenzen kann bei der Entwicklung von grafischen On-Board-Informationssystemen f{\"u}r Fahr- oder Flugzeuge von Nutzen sein.}, department = {Department B{\"u}lthoff}, web_url = {http://dl.mensch-und-computer.de/handle/123456789/2907}, editor = {Reiterer, H. , O. Deussen}, publisher = {Oldenbourg}, address = {M{\"u}nchen, Germany}, booktitle = {Mensch \& Computer 2012: 12. fach{\"u}bergreifende Konferenz f{\"u}r interaktive und kooperative Medien}, event_place = {Konstanz, Germany}, event_name = {Mensch \& Computer (M\&C)}, ISBN = {978-3-486-71879-9}, author = {Bieg, H-J and B{\"u}lthoff, HH and Chuang, LL} } @Inproceedings { OlivariNVBP2012, title = {Multi-loop Pilot Behavior Identification in Response to Simultaneous Visual and Haptic Stimuli}, year = {2012}, month = {8}, pages = {1-23}, abstract = {The goal of this paper is to better understand how the neuromuscular system of a pilot, or more generally an operator, adapts itself to di erent types of haptic aids during a pitch control task. A multi-loop pilot model, capable of describing the human behaviour during a tracking task, is presented. Three di erent identi cation techniques were investigated in order to simultaneously identify neuromuscular admittance and the visual response of a human pilot. In one of them, the various frequency response functions that build up the pilot model are identi ed using multi-inputs linear time-invariant models in ARX form. A second method makes use of cross-spectral densities and diagram block algebra to obtain the desired frequency response estimates. The identi cation techniques were validated using Monte Carlo simulations of a closed-loop control task. Both techniques were compared with the results of another identi cation method well known in literature and based on cross-spectral density estimates. All those methods were applied in an experimental setup in which pilots performed a pitch control task with di erent haptic aids. Two di erent haptic aids for tracking task are presented, a Direct Haptic Aid and an Indirect Haptic Aid. The two haptic aids were compared with a baseline condition in which no haptic force was used. The data obtained with the proposed method provide insight in how the pilot adapts his control behavior in relation to di erent haptic feedback schemes. From the experimental results it can be concluded that humans adapt their neuromuscular admittance in relation with di erent haptic aids. Furthermore, the two new identi cation techniques seemed to give more reliable admittance estimates.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/Olivari2012.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2012-4795}, event_place = {Minneapolis, MN, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2012}, ISBN = {978-1-62410-183-0}, DOI = {10.2514/6.2012-4795}, author = {Olivari, M and Nieuwenhuizen, FM and Venrooij, J and B{\"u}lthoff, HH and Pollini, L} } @Inproceedings { ZelazoFABR2012, title = {Rigidity Maintenance Control for Multi-Robot Systems}, year = {2012}, month = {7}, pages = {1-8}, abstract = {Rigidity of formations in multi-robot systems is important for formation control, localization, and sensor fusion. This work proposes a rigidity maintenance gradient controller for a multi-agent robot team. To develop such a controller, we first provide an alternative characterization of the rigidity matrix and use that to introduce the novel concept of the rigidity eigenvalue. We provide a necessary and sufficient condition relating the positivity of the rigidity eigenvalue to the rigidity of the formation. The rigidity maintenance controller is based on the gradient of the rigidity eigenvalue with respect to each robot position. This gradient has a naturally distributed structure, and is thus amenable to a distributed implementation. Additional requirements such as obstacle and inter-agent collision avoidance, as well as typical constraints such as limited sensing/communication ranges and line-of-sight occlusions, are also explicitly considered. Finally, we present a simulation with a group of seven quadrotor UAVs to demonstrate and validate the theoretical results.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012g-ZelFraAlgBueRob-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.roboticsproceedings.org/rss08/index.html}, booktitle = {Robotics: Science and Systems VIII}, event_place = {Sydney, Australia}, event_name = {2012 Robotics: Science and Systems Conference}, ISBN = {9780262519687}, author = {Zelazo, D and Franchi, A and Allg{\"o}wer, P and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { CognettiSFOB2012, title = {3-D Mutual Localization with Anonymous Bearing Measurements}, year = {2012}, month = {5}, pages = {791-798}, abstract = {We present a decentralized algorithm for estimating mutual 3-D poses in a group of mobile robots, such as a team of UAVs. Our algorithm uses bearing measurements reconstructed, e.g., by a visual sensor, and inertial measurements coming from the robot IMU. Since identification of a specific robot in a group would require visual tagging and may be cumbersome in practice, we simply assume that the bearing measurements are anonymous. The proposed localization method is a non-trivial extension of our previous algorithm for the 2-D case [1], and exhibits similar performance and robustness. An experimental validation of the algorithm has been performed using quadrotor UAVs.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/2012c-CogSteFraOriBue.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {St. Paul, MN, USA}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2012)}, DOI = {10.1109/ICRA.2012.6225288}, author = {Cognetti, M and Stegagno, P and Franchi, A and Oriolo, G and B{\"u}lthoff, HH} } @Inproceedings { BrowatzkiTMBW2012, title = {Active Object Recognition on a Humanoid Robot}, year = {2012}, month = {5}, pages = {2021-2028}, abstract = {Interaction with its environment is a key requisite for a humanoid robot. Especially the ability to recognize and manipulate unknown objects is crucial to successfully work in natural environments. Visual object recognition, however, still remains a challenging problem, as three-dimensional objects often give rise to ambiguous, two-dimensional views. Here, we propose a perception-driven, multisensory exploration and recognition scheme to actively resolve ambiguities that emerge at certain viewpoints. We define an efficient method to acquire two-dimensional views in an object-centered task space and sample characteristic views on a view sphere. Information is accumulated during the recognition process and used to select actions expected to be most beneficial in discriminating similar objects. Besides visual information we take into account proprioceptive information to create more reliable hypotheses. Simulation and real-world results clearly demonstrate the efficiency of active, multisensory exploration over passive, visiononly recognition methods.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/ICRA-2012-Browatzki.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {St. Paul, MN, USA}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2012)}, DOI = {10.1109/ICRA.2012.6225218}, author = {Browatzki, B and Tikhanoff, V and Metta, G and B{\"u}lthoff, HH and Wallraven, C} } @Inproceedings { SecchiFBP2012, title = {Bilateral teleoperation of a group of UAVs with communication delays and switching topology}, year = {2012}, month = {5}, pages = {4307-4314}, abstract = {In this paper, we present a passivity-based decentralized approach for bilaterally teleoperating a group of UAVs composing the slave side of the teleoperation system. In particular, we explicitly consider the presence of time delays, both among the master and slave, and within UAVs composing the group. Our focus is on analyzing suitable (passive) strategies that allow a stable teloperation of the group despite presence of delays, while still ensuring high flexibility to the group topology (e.g., possibility to autonomously split or join during the motion). The performance and soundness of the approach is validated by means of human/hardware-in-the-loop simulations (HHIL).}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/ICRA-2012-Secchi.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {St. Paul, MN, USA}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2012)}, DOI = {10.1109/ICRA.2012.6225304}, author = {Secchi, C and Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { RyllBR2012_2, title = {Modeling and Control of a Quadrotor UAV with Tilting Propellers}, year = {2012}, month = {5}, pages = {4606-4613}, abstract = {Standard quadrotor UAVs possess a limited mobility because of their inherent underactuation, i.e., availability of 4 independent control inputs (the 4 propeller spinning velocities) vs. the 6 dofs parameterizing the quadrotor position/ orientation in space. As a consequence, the quadrotor pose cannot track an arbitrary trajectory over time (e.g., it can hover on the spot only when horizontal). In this paper, we propose a novel actuation concept in which the quadrotor propellers are allowed to tilt about their axes w.r.t. the main quadrotor body. This introduces an additional set of 4 control inputs which provides full actuation to the quadrotor position/orientation. After deriving the dynamical model of the proposed quadrotor, we formally discuss its controllability properties and propose a nonlinear trajectory tracking controller based on dynamic feedback linearization techniques. The soundness of our approach is validated by means of simulation results.}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {St. Paul, MN, USA}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2012)}, DOI = {10.1109/ICRA.2012.6225129}, author = {Ryll, M and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { JumpPPWFFZSSBDSMHNB2011, title = {MyCopter: Enabling Technologies for Personal Air Transport Systems}, year = {2012}, month = {5}, pages = {336-347}, abstract = {This paper describes the European Commission (EC) Framework 7 funded project myCopter (2011-2014). The project is still at an early stage so the paper starts with the current transportation issues faced by developed countries and describes a means to solve them through the use of personal aerial transportation. The concept of personal air vehicles (PAV) is briefly reviewed and how this project intends to tackle the problem from a different perspective described. It is argued that the key reason that many PAV concepts have failed is because the operational infrastructure and socio-economic issues have not been properly addressed; rather, the start point has been the design of the vehicle itself. Some of the key aspects that would make a personal aerial transport system (PATS) viable include the required infrastructure and associated technologies, the skill levels and machine interfaces needed by the occupant or pilot and the views of society as a whole on the acceptability of such a proposition. The myCopter project will use these areas to explore the viability of PAVs within a PATS. The paper reports upon the early progress made within the project. An initial reference set of PAV requirements has been collated. A non-physical flight simulation model capable of providing a wide range of handling qualities characteristics has been developed and its function has undergone limited verification. Results from this exercise show that the model behaves as intended and that it can deliver a predictable range of vehicle dynamics. The future direction of the themes of work described within the paper are then described.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/ERF2011_122.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.erf2011.org/}, publisher = {Curran}, address = {Red Hook, NY, USA}, event_place = {Vergiate, Gallarate, Italy}, event_name = {37th European Rotorcraft Forum (ERF 2011)}, ISBN = {978-1-61839-626-6}, author = {Jump, M and Perfect, P and Padfield, GD and White, MD and Floreano, D and Fua, P and Zufferey, J-C and Schill, F and Siegwart, R and Bouabdallah, S and Decker, M and Schippl, J and Mayer, S and H{\"o}finger, M and Nieuwenhuizen, FM and B{\"u}lthoff, HH} } @Inproceedings { GrabeBR2012_2, title = {On-board velocity estimation and closed-loop control of a quadrotor UAV based on optical flow}, year = {2012}, month = {5}, pages = {491-497}, abstract = {Robot vision became a field of increasing importance in micro aerial vehicle robotics with the availability of small and light hardware. While most approaches rely on external ground stations because of the need of high computational power, we will present a full autonomous setup using only on-board hardware. Our work is based on the continuous homography constraint to recover ego-motion from optical flow. Thus we are able to provide an efficient fall back routine for any kind of UAV (Unmanned Aerial Vehicles) since we rely solely on a monocular camera and on on-board computation. In particular, we devised two variants of the classical continuous 4-point algorithm and provided an extensive experimental evaluation against a known ground truth. The results show that our approach is able to recover the ego-motion of a flying UAV in realistic conditions and by only relying on the limited on-board computational power. Furthermore, we exploited the velocity estimation for closing the loop and controlling the motion of the UAV online.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/ICRA2012-Grabe.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2012.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {St. Paul, MN, USA}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2012)}, ISBN = {978-1-4673-1403-9}, DOI = {10.1109/ICRA.2012.6225328}, author = {Grabe, V and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { HongBS2012, title = {Experimental Design for the Evaluation of a Multi-Modal Feedback in Multi-Robot Teleoperation}, year = {2012}, month = {4}, pages = {-}, department = {Department B{\"u}lthoff}, web_url = {http://conference.icros.org/}, publisher = {Institute of Control, Robotics and Systems}, address = {Bucheon, South Korea}, event_name = {27th ICROS Annual Conference (ICROS 2012)}, author = {Hong, A and B{\"u}lthoff, HH and Son, HI} } @Inproceedings { AlexandrovaRBTKBM2012, title = {Enhancing Medical Communication Training Using Motion Capture, Perspective Taking and Virtual Reality}, year = {2012}, month = {2}, pages = {16-22}, abstract = {The aim of this work is to increase the effectiveness of real world medical training simulations by helping trainees gain a better understanding of the importance of communication and teamwork. Therefore we develop an online application which can be used together with real world simulations to improve training. To produce the online application we reconstructed two real world scenarios (one with students and one with practitioners) in an immersive virtual environment. Our application enables the trainees to view the scenario from different perspectives or to freely explore the environment. We aim to integrate it into the medical student curriculum at the University of T{\"u}bingen.}, department = {Department B{\"u}lthoff}, web_url = {http://www.nextmed.com/index.html}, editor = {Westwood, J.D. , S.W. Westwood, L. Fell{\"a}nder-Tsai, R.S. Haluck, R.A. Robb, S. Senger, K.G. Vosburgh}, publisher = {IOS Press}, address = {Amsterdam, Netherlands}, booktitle = {Medicine Meets Virtual Reality 19: NextMed}, event_place = {Newport Beach, CA, USA}, event_name = {19th Medicine Meets Virtual Reality Conference (MMVR 2012)}, ISBN = {978-1-61499-021-5}, DOI = {10.3233/978-1-61499-022-2-16}, author = {Alexandrova, IV and Rall, M and Breidt, M and Tullius, G and Kloos, C and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { FranchiRB2011, title = {Distributed Online Leader Selection in the Bilateral Teleoperation of Multiple UAVs}, year = {2011}, month = {12}, pages = {3559-3565}, abstract = {For several applications like data collection, surveillance, search and rescue and exploration of wide areas, the use of a group of simple robots rather than a single complex robot has proven to be very effective and promising, and the problem of coordinating a group of agents has received a lot of attention over the last years. In this paper, we consider the challenge of establishing a bilateral force-feedback teleoperation channel between a human operator (the master side) and a remote multi-robot system (the slave side) where a special agent, the leader, is selected and directly controlled by the master. In particular, we study the problem of distributed online optimal leader selection, i.e., how to choose, and possibly change, the leader online in order to maximize some suitable criteria related to the tracking performance of the whole group w.r.t. the master commands. Human/hardware-in-the-loop simulation results with a group of UAVs support the theoretical claims of the paper.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CDC-ECC-2011-Franchi.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://control.disp.uniroma2.it/cdcecc2011/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Orlando, FL, USA}, event_name = {50th IEEE Conference on Decision and Control and European Control Conference (CDC - ECC 2011)}, DOI = {10.1109/CDC.2011.6160944}, author = {Franchi, A and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { BrowatzkiFGBW2011, title = {Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset}, year = {2011}, month = {11}, pages = {1189-1195}, abstract = {Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies, such as consumer-level range sensors, new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper, we introduce a novel, large dataset containing 18 categories of objects found in typical household and office environments-we envision this dataset to be useful in many applications ranging from robotics to computer vision. The second part of the paper presents computational experiments on object categorization with classifiers exploiting both two-dimensional and three-dimensional information. We evaluate categorization performance for both modalities in separate and combined representations and demonstrate the advantages of using range data for object and shape processing skills.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CD4CV-2011-Browatzki.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.vision.ee.ethz.ch/CDC4CV/index.html}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, booktitle = {2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)}, event_place = {Barcelona, Spain}, event_name = {1st ICCV Workshop on Consumer Depth Cameras in Computer Vision (CD4CV2011)}, ISBN = {978-1-467-30062-9}, DOI = {10.1109/ICCVW.2011.6130385}, author = {Browatzki, B and Fischer, J and Graf, B and B{\"u}lthoff, HH and Wallraven, C} } @Inproceedings { NieuwenhuizenJPWPFSZFBSMSDGHB2011, title = {myCopter: Enabling Technologies for Personal Aerial Transportation Systems}, year = {2011}, month = {11}, pages = {1-8}, abstract = {Current road transportation systems throughout the European Union suffer from severe congestion problems. A solution can be to move towards a Personal Aerial Transportation System, in which vehicles would also have vertical space at their disposal. In the myCopter project, funded by the European Union under the 7th Framework Programme, the viability of such a system will be investigated. It is argued that this should be done by taking into account the required operational infrastructure, instead of starting with the design of a vehicle. By investigating human-machine interfaces and training, automation technologies, and socio-economic impact, the myCopter project aims to provide a basis for a transportation system based on Personal Aerial Vehicles. In this paper, an outline of the project is given. Early research results are detailed and provide a basis for the remainder of the project.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/HeliWorld-2011-Nieuwenhuizen.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.airtec.aero/index.php?id=55}, event_place = {Frankfurt a.M.}, event_name = {3rd International HELI World Conference 2011 ''Helicopter Technologies and Operations'' (HeliWorld 2011)}, author = {Nieuwenhuizen, FM and Jump, M and Perfect, P and White, MD and Padfield, GD and Floreano, D and Schill, F and Zufferey, J-C and Fua, P and Bouabdallah, S and Siegwart, R and Meyer, S and Schippl, J and Decker, M and Gursky, B and H{\"o}finger, M and B{\"u}lthoff, HH} } @Inproceedings { VenrooijMvABM2011, title = {Cancelling biodynamic feedthrough requires a subject and task dependent approach}, year = {2011}, month = {10}, pages = {1670-1675}, abstract = {Vehicle accelerations may feed through the human body, causing involuntary limb motions which may lead to involuntary control inputs. This phenomenon is called biodynamic feedthrough (BDFT). Signal cancellation is a possible way of mitigating biodynamic feedthrough. It makes use of a BDFT model to estimate the involuntary control inputs. The BDFT effects are removed by subtracting the modeled estimate of the involuntary control input from the total control signal, containing both voluntary and involuntary components. The success of signal cancellation hinges on the accuracy of the BDFT model used. In this study the potential of signal cancellation is studied by making use of a method called optimal signal cancellation. Here, an identified BDFT model is used off-line to generate an estimate of the involuntary control inputs based on the accelerations present. Results show that reliable signal cancellation requires BDFT models that are both subject and task dependent. The task dependency is of particular importance: failing to adapt the model to changes in the operator's neuromuscular dynamics dramatically decreases the quality of cancellation and can even lead to an increase in unwanted effects. As a reliable and fast on-line identification method of the neuromuscular dynamics of the human operator currently does not exist, real-time signal cancellation is currently not feasible.}, department = {Department B{\"u}lthoff}, web_url = {http://www.smc2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Anchorage, AK, USA}, event_name = {IEEE International Conference on Systems, Man and Cybernetics (SMC 2011)}, ISBN = {978-1-4577-0652-3}, DOI = {10.1109/ICSMC.2011.6083911}, author = {Venrooij, J and Mulder, M and van Paassen, MM and Abbink, DA and B{\"u}lthoff, HH and Mulder, M} } @Inproceedings { SonCKB2011, title = {Haptic Feedback Cues Can Improve Human Perceptual Awareness in Multi-Robots Teleoperation}, year = {2011}, month = {10}, pages = {1323-1328}, abstract = {The availability of additional force cues in haptic devices are often expected to improve control performance, over conditions that only provide visual feedback. However, there is little empirical evidence to show this to be true for the teleoperation control of remote vehicles (i.e., multiple unmanned aerial vehicles (UAVs)). In this paper, we show that force cues can increase one's sensitivity in discerning the presence of obstacles in the remote multi-UAVs' environment. Significant benefits, relative to a purely visual scenario, were achieved only when force cues were sufficiently amplified by large gains. In addition, force cues tended to provide stronger benefits when they were based on the UAVs' velocity information.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6106130}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Gyeonggi-do, Korea}, event_name = {11th International Conference on Control, Automations and Systems (ICCAS 2011)}, ISBN = {978-1-4577-0835-0}, author = {Son, HI and Chuang, L and Kim, J and B{\"u}lthoff, HH} } @Inproceedings { FranchiMBR2011, title = {Bilateral teleoperation of multiple UAVs with decentralized bearing-only formation control}, year = {2011}, month = {9}, pages = {2215-2222}, abstract = {We present a decentralized system for the bilateral teleoperation of groups of UAVs which only relies on relative bearing measurements, i.e., without the need of distance information or global localization. The properties of a 3D bearing-formation are analyzed, and a minimal set of bearings needed for its definition is provided. We also design a novel decentralized formation control almost globally convergent and able to maintain bounded and non-vanishing inter-distances among the agents despite the absence of direct distance measurements. Furthermore, we develop a multi-master/ multi-slave teleoperation setup in order to control the overall behavior of the group and to convey to the human operator suitable force cues, while ensuring stability in presence of delays and packet losses over the master-slave communication channel. The theoretical framework is validated by means of extensive human/hardware in-the-loop simulations using two force-feedback devices and a group of quadrotors.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/IROS-2011-Franchi.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2011.org/}, editor = {Amato, N.M.}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {San Francisco, CA, USA}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)}, ISBN = {978-1-61284-454-1}, DOI = {10.1109/IROS.2011.6094525}, author = {Franchi, A and Masone, C and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { 6845, title = {Evaluation of Direct and Indirect Haptic Aiding in an Obstacle Avoidance Task for Tele-Operated Systems}, journal = {Proceedings of the 18th World Congress of the International Federation of Automatic Control (IFAC 2011)}, year = {2011}, month = {9}, pages = {6472-6477}, abstract = {The sense of telepresence is very important in teleoperation environments in which the operator is physically separated from the vehicle. It appears reasonable, and it has already been shown in the literature, that extending the visual feedback with force feedback is able to complement the visual information (when missing or limited) through the sense of touch and allows the operator to better perceive information from the remote environment and its constraints, hopefully preventing dangerous collisions. This paper focuses on a novel concept of haptic cueing for an airborne obstacle avoidance task; the novel cueing algorithm was designed in order to appear “natural” to the operator, and to improve the human-machine interface without directly acting on the actual aircraft commands. An experimental evaluation of two different Haptic aiding concepts for obstacle avoidance is presented. An existing and widely used approach, belonging to what we called the Direct Haptic Aid (DHA) class, and a novel one based on the Indirect Haptic Aid (IHA) class. The two haptic aids were compared with a baseline condition in which no haptic force was associated to the obstacles. Test results show that a net improvement in terms of performance (i.e. the number of collisions) is provided by employing the IHA haptic cue instead of both the DHA haptic cue and the visual cue only. Most participants of the experiment reported the strongest force feeling, the most necessary effort and also the most helpful sensation with DHA and IHA conditions with respect to the baseline condition. This paper shows that the IHA philosophy is a valid alternative to the other commonly used, and published in the scientific literature, approaches which fall in the DHA category.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/IFAC-2011-Alaimo.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ifac2011.org/}, editor = {Bittanti, S. , A. Cenedese, S. Zampieri}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Milano, Italy}, event_name = {18th World Congress of the International Federation of Automatic Control (IFAC WC 2011)}, language = {en}, ISBN = {978-1-618-39122-3}, DOI = {10.3182/20110828-6-IT-1002.02790}, author = {Alaimo, SMC and Pollini, L and Bresciani, J-P and B{\"u}lthoff, HH} } @Inproceedings { RobuffoGiordanoFSB2011_2, title = {Experiments of passivity-based bilateral aerial teleoperation of a group of UAVs with decentralized velocity synchronization}, year = {2011}, month = {9}, pages = {163-170}, abstract = {In this paper, we present an experimental validation of a novel decentralized passivity-based control strategy for teleoperating a group of Unmanned Aerial Vehicles (UAVs): the slave side, consisting of the UAVs, is endowed with large group autonomy by allowing time-varying topology and interrobot/obstacle collision avoidance. The master side, represented by a human operator, controls the group motion and receives suitable force feedback cues informing her/him about the remote slave motion status. Passivity theory is exploited for guaranteeing stability of the slave side and of the overall teleoperation channel. Results of experiments involving the use of 4 quadcopters are reported and discussed, confirming the soundness of the paper theoretical claims.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/2011k-RobFraSecBue-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2011.org/}, editor = {Amato, N.M.}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {San Francisco, CA, USA}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)}, ISBN = {978-1-61284-454-1}, DOI = {10.1109/IROS.2011.6094895}, author = {Robuffo Giordano, P and Franchi, A and Secchi, C and B{\"u}lthoff, HH} } @Inproceedings { SonCFKLLBR2011, title = {Measuring an Operator's Maneuverability Performance in the Haptic Teleoperation of Multiple Robots}, year = {2011}, month = {9}, pages = {3039-3046}, abstract = {In this paper, we investigate the maneuverability performance of human teleoperators on multi-robots. First, we propose that maneuverability performance can be assessed by a frequency response function that jointly considers the input force of the operator and the position errors of the multi-robot system that is being maneuvered. Doing so allows us to evaluate maneuverability performance in terms of the human teleoperator's interaction with the controlled system. This allowed us to effectively determine the suitability of different haptic cue algorithms in improving teleoperation maneuverability. Performance metrics based on the human teleoperator's frequency response function indicate that maneuverability performance is best supported by a haptic feedback algorithm which is based on an obstacle avoidance force.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/IROS-2011-Son.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros2011.org/}, editor = {Amato, N.M.}, publisher = {IEEE}, address = {Piscatawy, NJ, USA}, event_place = {San Francisco, CA, USA}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)}, ISBN = {978-1-61284-454-1}, DOI = {10.1109/IROS.2011.6048185}, author = {Son, HI and Chuang, LL and Franchi, A and Kim, J and Lee, D and Lee, S-W and B{\"u}lthoff, HH and Robuffo Giordano, P} } @Inproceedings { NolanBWFBR2011_3, title = {Motion P3 demonstrates neural nature of motion ERPs}, year = {2011}, month = {9}, pages = {3884-3887}, abstract = {The technical challenges of recording electroencephalographic (EEG) data during motion are considerable, but would enable the possibility of investigating neural function associated with balance, motor function and motion perception. The challenges include finding a reliable method of motion stimulus reproduction, removing artifacts, and ensuring that the recordings retain sufficient EEG signal for proper interpretation. This study details the use of the P3 waveform to validate the concept of motion-based EEG data, and discusses some potential future uses in experimental and clinical settings.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6090965}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Boston, MA, USA}, event_name = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2011)}, ISBN = {978-1-4244-4121-1}, DOI = {10.1109/IEMBS.2011.6090965}, author = {Nolan, H and Butler, JS and Whelan, R and Foxe, JJ and B{\"u}lthoff, HH and Reilly, RB} } @Inproceedings { CaniardBMLT2011, title = {Active control does not eliminate motion-induced illusory displacement}, year = {2011}, month = {8}, pages = {101-108}, abstract = {When the sine-wave grating of a Gabor patch drifts to the left or right, the perceived position of the entire object is shifted in the direction of local motion. In the current paper, we explored whether active control of the physical position of the patch can overcome such motion induced illusory displacement. We created a simple computer game and asked participants to continuously guide a Gabor patch along a randomly curving path. When the grating inside the Gabor patch was stationary, participants could perform this task without error. When the grating drifted to either left or right, we observed systematic errors consistent with previous reports of motion-induced illusory displacement. Specifically, when the grating drifted to the right, participants adjusted the global position of the patch to the left of the target line, and when it drifted to the left, errors were to the right of the line. The magnitude of the errors was consistent with previously reported perceptual judgements for centrally presented items, and scaled systematically with the speed of local drift. Importantly, we found no evidence that participants could adapt or compensate for illusory displacement given active control of the target. The current findings could have important implications for interface design, suggesting that local dynamic components of a display could affect perception and action within the more global application environment.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/APGV-2011-caniard.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv11/}, publisher = {ACM Press}, address = {New York, NY, USA}, event_place = {Toulouse, France}, event_name = {8th Symposium on Applied Perception in Graphics and Visualization (APGV 2011)}, ISBN = {978-1-4503-0889-2}, DOI = {10.1145/2077451.2077470}, author = {Caniard, F and B{\"u}lthoff, HH and Mamassian, P and Lee, S-W and Thornton, IM} } @Inproceedings { AlaimoPB2011_2, title = {Admittance-Based Bilateral Teleoperation with Time Delay for an Unmanned Aerial Vehicle involved in an Obstacle Avoidance Task}, year = {2011}, month = {8}, pages = {19-37}, abstract = {The paper focuses on the implementation of an admittance based control scheme in a bilateral teleoperation set-up for an Unmanned Aerial Vehicle (UAV) under time delay. The goal of this study is to assess and improve the stability characteristics of the bilateral teleoperator. Computer simulations were conducted to evaluate the effectiveness of the admittance-based control scheme. A commercial impedance-like haptic device was chosen to simulate the control stick: the master device. The slave system is constituted by the dynamics of the aircraft under control; in order to maximize the pilot attention on its task, only the lateral aircraft dynamics was considered. A virtual environment was displayed during the experiments to produce the visual cues. In order to evaluate the system, we prepared a control task where the aircraft had to be flown in a virtual urban canyon with buildings placed irregularly (non Manhattan-like) along the desired path by avoiding the collisions with them. A repulsive force field was associated to the obstacles and a force was sent back to the operator through the communication link. A compensator capable of flying autonomously the aircraft through the buildings with satisfactory performance was designed first using linear techniques then the haptic augmentation system was derived from the compensator by splitting it in two parts: the actual haptic cueing for the pilot and the simulated the pilot effort. The latter component was used only for the preliminary assessment of the system and was removed in simulations where a real pilot operated the stick (the master device). Experimental results and analytical motivations as well have shown that a haptic force which is simply proportional to the distance from the obstacles cannot stabilize the system: a relevant anticipatory effect or phase lead (as the derivative effect of standard industrial controllers) is needed. In order to manage the degradation of performance and overall stability when a delay is present in the communication paths, an admittance-based controller was designed together with an observer for the force generated by the human operator on the stick. The admittance-based Force Position teleoperation scheme was shown by simulations and tests with real pilots to improve the performance of the system under consideration.}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2011-6243}, publisher = {Curran}, address = {Red Hook, NY, USA}, event_place = {Portland, OR, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2011}, ISBN = {978-1-62410-154-0}, DOI = {10.2514/6.2011-6243}, author = {Alaimo, S and Pollini, L and B{\"u}lthoff, HH} } @Inproceedings { AlaimoPB2011, title = {Experiments of Direct and Indirect Haptic Aiding for Remotely Piloted Vehicles with a Mixed Wind Gust Rejection/Obstacle Avoidance Task}, year = {2011}, month = {8}, pages = {732-749}, abstract = {This paper focuses on a novel concept of haptic cueing developed in order to optimize the performance of an Unmanned Aerial Vehicle (UAV) teleoperator and to improve the human-machine interfaces in a mixed obstacle avoidance/wind gust rejection task. It presents an experimental evaluation of two different Haptic aiding concepts: one based on what we called Direct Haptic Aiding (DHA) approach, and a novel one based on the Indirect Haptic Aiding (IHA) approach. The two haptic aids were compared with a baseline condition in which no haptic force was associated to the obstacles (NoEF condition). It will be shown that IHA-based approach definitely improves the pilots¡¯ performance with respect to the other approaches. A significant difference in performance (i.e. the number of collisions) was noticed between IHA and both DHA and NoEF conditions. The goal of this paper is to show that the IHA philosophy is a valid alternative to the other commonly used, and published in the scientific literature, approaches which fall in the DHA category.}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2011-6242}, publisher = {Curran}, address = {Red Hook, NY, USA}, event_place = {Portland, OR, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference}, ISBN = {978-1-62410-154-0}, DOI = {10.2514/6.2011-6242}, author = {Alaimo, S and Pollini, L and Bresciani, JP and B{\"u}lthoff, HH} } @Inproceedings { McManusBSdBM2011, title = {The influence of avatar (self and character) animations on distance estimation, object interaction and locomotion in immersive virtual environments}, year = {2011}, month = {8}, pages = {37-44}, abstract = {Humans have been shown to perceive and perform actions differently in immersive virtual environments (VEs) as compared to the real world. Immersive VEs often lack the presence of virtual characters; users are rarely presented with a representation of their own body and have little to no experience with other human avatars/characters. However, virtual characters and avatars are more often being used in immersive VEs. In a two-phase experiment, we investigated the impact of seeing an animated character or a self-avatar in a head-mounted display VE on task performance. In particular, we examined performance on three different behavioral tasks in the VE. In a learning phase, participants either saw a character animation or an animation of a cone. In the task performance phase, we varied whether participants saw a co-located animated self-avatar. Participants performed a distance estimation, an object interaction and a stepping stone locomotion task within the VE. We find no impact of a character animation or a self-avatar on distance estimates. We find that both the animation and the self-avatar influenced task performance which involved interaction with elements in the environment; the object interaction and the stepping stone tasks. Overall the participants performed the tasks faster and more accurately when they either had a self-avatar or saw a character animation. The results suggest that including character animations or self-avatars before or during task execution is beneficial to performance on some common interaction tasks within the VE. Finally, we see that in all cases (even without seeing a character or self-avatar animation) participants learned to perform the tasks more quickly and/or more accurately over time.}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv11/}, publisher = {ACM Press}, address = {New York, NY, USA}, event_place = {Toulouse, France}, event_name = {8th Symposium on Applied Perception in Graphics and Visualization (APGV 2011)}, ISBN = {978-1-4503-0889-2}, DOI = {10.1145/2077451.2077458}, author = {McManus, EA and Bodenheimer, B and Streuber, S and de la Rosa, S and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { LeyrerLBKM2011, title = {The influence of eye height and avatars on egocentric distance estimates in immersive virtual environments}, year = {2011}, month = {8}, pages = {67-74}, abstract = {It is well known that eye height is an important visual cue in the perception of apparent sizes and affordances in virtual environments. However, the influence of visual eye height on egocentric distances in virtual environments has received less attention. To explore this influence, we conducted an experiment where we manipulated the virtual eye height of the user in a head-mounted display virtual environment. As a measurement we asked the participants to verbally judge egocentric distances and to give verbal estimates of the dimensions of the virtual room. In addition, we provided the participants a self-animated avatar to investigate if this virtual self-representation has an impact on the accuracy of verbal distance judgments, as recently evidenced for distance judgments accessed with an action-based measure. When controlled for ownership, the avatar had a significant influence on the verbal estimates of egocentric distances as found in previous research. Interestingly, we found that the manipulation of eye height has a significant influence on the verbal estimates of both egocentric distances and the dimensions of the room. We discuss the implications which these research results have on those interested in space perception in both immersive virtual environments and the real world.}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv11/}, publisher = {ACM Press}, address = {New York, NY, USA}, event_place = {Toulouse, France}, event_name = {8th Symposium on Applied Perception in Graphics and Visualization (APGV 2011)}, ISBN = {978-1-4503-0889-2}, DOI = {10.1145/2077451.2077464}, author = {Leyrer, M and Linkenauger, SA and B{\"u}lthoff, HH and Kloos, U and Mohler, B} } @Inproceedings { NieuwenhuizenMvB2011, title = {The Influence of Motion System Characteristics on Pilot Control Behaviour}, year = {2011}, month = {8}, pages = {204-218}, abstract = {Full flight simulators are widely being used for training of pilots as they provide a cost-effective alternative over aircraft. However, a compromise must always be found between the amount of motion cueing that needs to be presented to the pilot for effective training and the available workspace of the simulator. In literature, contradictory reports are found on the effect of motion cues on pilot performance in the simulator. In this paper, the results are presented of an experiment in which the influence of the quality of motion systems was investigated. A model of the MPI Stewart platform was simulated on the SIMONA Research Simulator and the motion system characteristics of both simulators were varied systematically to determine their effects on pilot control behaviour. The time delay and noise characteristics of the simulators did not have an effect in this experimental task. However, it was found that the bandwidth of the motion system had a significant effect on performance and control behaviour. Results indicate that the motion cues were barely used at all in conditions with a low bandwidth, and that participants relied on the visual cues to generate lead needed in their control task.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/AIAA-2011-6321-Nieuwenhuizen.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2011-6321}, publisher = {Curran}, address = {Red Hook, NY, USA}, event_place = {Portland, OR, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2011}, ISBN = {978-1-62410-154-0}, DOI = {10.2514/6.2011-6321}, author = {Nieuwenhuizen, FM and Mulder, M and van Paassen, MM and B{\"u}lthoff, HH} } @Inproceedings { HensonMBM2011, title = {When do we integrate spatial information acquired by walking through environmental spaces?}, year = {2011}, month = {7}, pages = {2764-2769}, abstract = {The present study examined whether spatial information of a novel environment was integrated within a reference frame during initial learning, or only later when required for pointing to other targets. Twenty-two participants repeatedly walked through a multi-corridor virtual environment, presented via a head-mounted display. At several stages within the learning process they were teleported to locations along the route and asked to self-localize and point to other locations. Pointing was faster during later tests as well as for closer targets, both of which might require less integration. Participants tested only after extended exposure (late pointers) took longer than participants who had received testing interspersed throughout the same amount of exposure (early pointers). Pointing latency did not differ between groups when comparing performance on their first pointing test, despite vastly different exposure. These results are inconsistent with the assumption that participants already integrated spatial information within a single reference frame during learning and simply accessed this information during testing. Rather, spatial integration is a time consuming process which is not necessarily undertaken if not required.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CogSci-2011-Henson.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://csjarchive.cogsci.rpi.edu/Proceedings/2011/index.html}, editor = {Carlson, L. , C. Hoelscher, T.F. Shipley}, publisher = {Cognitive Science Society}, address = {Austin, TX, USA}, booktitle = {Expanding the Space of Cognitive Science}, event_place = {Boston, MA, USA}, event_name = {33rd Annual Meeting of the Cognitive Science Society (CogSci 2011)}, author = {Henson, A and Mallot, HA and B{\"u}lthoff, HH and Meilinger, T} } @Inproceedings { SonKCFRLB2011, title = {An Evaluation of Haptic Cues on the Tele-Operator's Perceptual Awareness of Multiple UAVs' Environments}, year = {2011}, month = {6}, pages = {149-154}, abstract = {The use of multiple unmanned aerial vehicles (UAVs) is increasingly being incorporated into a wide range of teleoperation applications. To date, relevant research has largely been focused on the development of appropriate control schemes. In this paper, we extend previous research by investigating how control performance could be improved by providing the teleoperator with haptic feedback cues. First, we describe a control scheme that allows a teleoperator to manipulate the flight of multiple UAVs in a remote environment. Next, we present three designs of haptic cue feedback that could increase the teleoperator's environmental awareness of such a remote environment. These cues are based on the UAVs' i) velocity information, ii) proximity to obstacles, and iii) a combination of these two sources of information. Finally, we present an experimental evaluation of these haptic cue designs. Our evaluation is based on the teleoperator's perceptual sensitivity to the physical environment inhabited by the multiple UAVs. We conclude that a teleoperator's perceptual sensitivity is best served by haptic feedback cues that are based on the velocity information of multiple UAVs.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/WHC-2011-Son.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.haptics2011.org/en/}, editor = {Jones, L. , M. Harders, Y. Yokokohji}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Istanbul, Turkey}, event_name = {IEEE 2011 World Haptics Conference (WHC 2011)}, ISBN = {978-1-4577-0299-0}, DOI = {10.1109/WHC.2011.5945477}, author = {Son, HI and Kim, J and Chuang, LL and Franchi, A and Robuffo Giordano, P and Lee, D and B{\"u}lthoff, HH} } @Inproceedings { RobuffoGiordanoFSB2011, title = {Bilateral Teleoperation of Groups of UAVs with Decentralized Connectivity Maintenance}, year = {2011}, month = {6}, pages = {273-280}, abstract = {In this paper, we present a decentralized passivity-based control strategy for the bilateral teleoperation of a group of Unmanned Aerial Vehicles (UAVs). The human operator at the master side can command the group motion and receive suitable force cues informative about the remote environment. By properly controlling the energy exchanged within the slave side (the UAV group), we guarantee that the connectivity of the group is preserved and we prevent inter-agent and obstacle collisions. At the same time, we allow the behavior of the UAVs to be as flexible as possible with arbitrary split and join maneuvers. The results of the paper are validated by means of human/hardware-in-the-loop (HHIL) simulations.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/RSS-2011-Robuffo.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.roboticsproceedings.org/rss07/p13.html}, editor = {Durrant-Whyte, H.F. , N. Roy, P. Abbeel}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Robotics: Science and Systems VII}, event_place = {Los Angeles, CA, USA}, event_name = {2011 Robotics: Science and Systems Conference}, ISBN = {978-0-262-51779-9}, author = {Robuffo Giordano, P and Franchi, A and Secchi, C and B{\"u}lthoff, HH} } @Inproceedings { JumpPWFZSSBDSHNB2011, title = {myCopter: Enabling Technologies for Personal Air Transport Systems}, year = {2011}, month = {6}, pages = {1-15}, abstract = {This paper describes the European Commission Framework 7 funded project myCopter (2011-2014). The project is still at an early stage so the paper starts with the current transportation issues faced by developed countries and describes a means to solve them through the use of personal aerial transportation. The concept of personal air vehicles (PAV) is briefly reviewed and how this project intends to tackle the problem from a different perspective described. It is argued that the key reason that many PAV concepts have failed is because the operational infrastructure and socio-economic issues have not been properly addressed; rather, the start point has been the design of the vehicle itself. Some of the key aspects that would make a personal aerial transport system (PATS) viable include the required infrastructure and associated technologies, the skill levels and machine interfaces needed by the occupant or pilot and the views of society as a whole on the acceptability of such a proposition. The myCopter project will use these areas to explore the viability of PAVs within a PATS. The paper provides an overview of the project structure, the roles of the partners, and hence the available research resources, and some of the early thinking on each of the key project topic areas.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/RAeS-Spring-2011-Nieuwenhuizen.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.aerosocietychannel.com/events/2011/03/future-rotorcraft/}, publisher = {Royal Aeronautical Society}, address = {London, UK}, booktitle = {The Future Rotorcraft: Enabling Capability through the Application of Technology}, event_place = {London, UK}, event_name = {Royal Aeronautical Society Conference on the Future Rotorcraft (RAeS 2011)}, ISBN = {1-85768-274-2}, author = {Jump, M and Padfield, GD and White, MD and Fua, P and Zufferey, J-C and Schill, F and Siegwart, R and Bouabdallah, S and Decker, M and Schippl, J and H{\"o}finger, M and Nieuwenhuizen, FM and B{\"u}lthoff, HH} } @Inproceedings { FranchiRSSB2011, title = {A Passivity-Based Decentralized Approach for the Bilateral Teleoperation of a Group of UAVs with Switching Topology}, year = {2011}, month = {5}, pages = {898-905}, abstract = {In this paper, a novel distributed control strategy for teleoperating a fleet of Unmanned Aerial Vehicles (UAVs) is proposed. Using passivity based techniques, we allow the behavior of the UAVs to be as flexible as possible with arbitrary split and join decisions while guaranteeing stability of the system. Furthermore, the overall teleoperation system is also made passive and, therefore, characterized by a stable behavior both in free motion and when interacting with unknown passive obstacles. The performance of the system is validated through semi-experiments.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/2011a-FraRobSecSonBue-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Shanghai, China}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2011)}, ISBN = {978-1-61284-386-5}, DOI = {10.1109/ICRA.2011.5980368}, author = {Franchi, A and Robuffo Giordano, P and Secchi, C and Son, HI and B{\"u}lthoff, HH} } @Inproceedings { AlexandrovaRBKTBM2011, title = {Animations of Medical Training Scenarios in Immersive Virtual Environments}, year = {2011}, month = {5}, pages = {9-12}, abstract = {Medical training centers often provide various simulations for students and professionals. Their goal is not only to make trainees practice specific scenarios but also to help them effectively transfer the acquired skills to the real world. Having in mind that virtual environments have already been acknowledged for their potential to improve the medical training process, we propose an approach for rapid generation of animated medical scenarios, which can be used as an additional training tool that fits into the time frame of a semester training program.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CASA-2011-Alexandrova.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.cad.zju.edu.cn/casa2011/program.html}, editor = {Liu, Y. , A. El Rhalibi, L. Li, M. Zhang, Z. Pan}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Hangzhou, Zhejiang, China}, event_name = {2011 Workshop on Digital Media and Digital Content Management (DMDCM)}, ISBN = {978-1-4577-0271-6}, DOI = {10.1109/DMDCM.2011.64}, author = {Alexandrova, IV and Rall, M and Breidt, M and Kloos, U and Tullius, G and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { NolanBWFBR2011_2, title = {Electrophysiological source analysis of passive self-motion}, year = {2011}, month = {5}, pages = {53-56}, abstract = {The neural processes underlying perception of motion are relatively unknown. In this study Electroencephalography (EEG) is used to investigate the neural responses to passive self-motion. A Stewart platform was employed to translate subjects forwards and backwards while high-density EEG data was recorded. Modern source modeling methods were combined with classical waveform and topographic analyses to determine the electrophysiological correlates of motion processing.}, department = {Department B{\"u}lthoff}, web_url = {http://ne2011.embs.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Cancun, Mexico}, event_name = {5th International IEEE/EMBS Conference on Neural Engineering (NER 2011)}, ISBN = {978-1-4244-4140-2}, DOI = {10.1109/NER.2011.5910487}, author = {Nolan, H and Butler, JS and Whelan, R and Foxe, JJ and B{\"u}lthoff, HH and Reilly, RB} } @Inproceedings { DoddsMdSB2011, title = {Embodied Interaction in Immersive Virtual Environments with Real Time Self-animated Avatars}, year = {2011}, month = {5}, pages = {132-135}, abstract = {This paper outlines our recent research that is providing users with a 3D avatar representation, and in particular focuses on studies in which the avatar is self-animated in real time. We use full body motion tracking, so when participants move their hands and feet, these movements are mapped onto the avatar. In a recent study (Dodds et al., CASA 2010), we found that a self-animated avatar aided participants in a communication task in a head-mounted display immersive virtual environment (VE). From the perspective of communication, we discovered it was not only important for the person speaking to be self-animated, but also for the person listening to us. Further, we show the potential of immersive VEs for investigating embodied interaction, and highlight possibilities for future research.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CHI-2011-Dodds.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.antle.iat.sfu.ca/chi2011_EmbodiedWorkshop/}, web_url2 = {http://www.elisevandenhoven.com/publications/antle-chi11wp.pdf}, editor = {Antle A.N. , P. Marshall P, E. Van Den Hoven}, publisher = {ACM Press}, address = {New York, NY, USA}, event_place = {Vancouver, BC}, event_name = {Workshop Embodied Interaction: Theory and Practice in HCI (CHI 2011)}, author = {Dodds, TJ and Mohler, BJ and de la Rosa, S and Streuber, S and B{\"u}lthoff, HH} } @Inproceedings { LeeFRSB2011, title = {Haptic Teleoperation of Multiple Unmanned Aerial Vehicles over the Internet}, year = {2011}, month = {5}, pages = {1341-1347}, abstract = {We propose a novel haptic teleoperation control framework for multiple unmanned aerial vehicles (UAVs) over the Internet, consisting of the three control layers: 1) UAV control layer, where each UAV is abstracted by, and is controlled to follow the trajectory of, its own kinematic virtual point (VP); 2) VP control layer, which modulates each VP's motion according to the teleoperation commands and local artificial potentials (for inter-VP/VP-obstacle collision avoidance and inter-VP connectivity preservation); and 3) teleoperation layer, through which a remote human user can command all (or some) of the VPs' velocity while haptically perceiving the state of all (or some) of the UAVs over the Internet. Master-passivity/slave-stability and some asymptotic performance measures are proved. Semi-experiment results are presented to validate the theory.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/2011b-LeeFraRobSonBue-preprint.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Shanghai, China}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2011)}, ISBN = {978-1-61284-386-5}, DOI = {10.1109/ICRA.2011.5979993}, author = {Lee, D and Franchi, A and Robuffo Giordano, P and Son, HI and B{\"u}lthoff, HH} } @Inproceedings { MasoneRB2011, title = {Mechanical design and control of the new 7-DOF CyberMotion simulator}, year = {2011}, month = {5}, pages = {4935-4942}, abstract = {This paper describes the mechanical and control design of the new 7-DOF CyberMotion Simulator, a redundant industrial manipulator arm consisting of a standard 6-DOF anthropomorphic manipulator plus an actuated cabin attached to the end-effector. Contrarily to Stewart platforms, an industrial manipulator offers several advantages when used as motion simulator: larger motion envelope, higher dexterity, and possibility to realize any end-effector posture within the workspace. In addition to this, the new actuated cabin acts as an additional joint and provides the needed kinematic redundancy to cope with the robot actuator and joint range constraints, which in general can significantly deteriorate the desired motion cues the robot is reproducing. In particular, we will show that, by suitably exploiting the redundancy better results can be obtained in reproducing sustained acceleration cues, a relevant problem when implementing vehicle simulators.}, department = {Department B{\"u}lthoff}, web_url = {http://www.icra2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Shanghai, China}, event_name = {IEEE International Conference on Robotics and Automation (ICRA 2011)}, ISBN = {978-1-61284-386-5}, DOI = {10.1109/ICRA.2011.5980436}, author = {Masone, C and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Inproceedings { 7016, title = {Robust Semantic Analysis by Synthesis of 3D Facial Motion}, journal = {Proceedings of the Ninth IEEE International Conference on Automatic Face and Gesture Recognition (FG 2011)}, year = {2011}, month = {3}, pages = {713-719}, abstract = {Rich face models already have a large impact on the fields of computer vision, perception research, as well as computer graphics and animation. Attributes such as descriptiveness, semantics, and intuitive control are desirable properties but hard to achieve. Towards the goal of building such high-quality face models, we present a 3D model-based analysis-by-synthesis approach that is able to parameterize 3D facial surfaces, and that can estimate the state of semantically meaningful components, even from noisy depth data such as that produced by Time-of-Flight (ToF) cameras or devices such as Microsoft Kinect. At the core, we present a specialized 3D morphable model (3DMM) for facial expression analysis and synthesis. In contrast to many other models, our model is derived from a large corpus of localized facial deformations that were recorded as 3D scans from multiple identities. This allows us to analyze unstructured dynamic 3D scan data using a modified Iterative Closest Point model fitting process, followed by a constrained Action Unit model regression, resulting in semantically meaningful facial deformation time courses. We demonstrate the generative capabilities of our 3DMMs for facial surface reconstruction on high and low quality surface data from a ToF camera. The analysis of simultaneous recordings of facial motion using passive stereo and noisy Time-of-Flight camera shows good agreement of the recovered facial semantics.}, department = {Department B{\"u}lthoff}, web_url = {http://www.fg2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, event_place = {Santa Barbara, CA, USA}, event_name = {Ninth IEEE International Conference on Automatic Face \& Gesture Recognition and Workshops (FG 2011)}, language = {en}, ISBN = {978-1-4244-9140-7}, DOI = {10.1109/FG.2011.5771336}, author = {Breidt, M and B{\"u}lthoff, HH and Curio, C} } @Inproceedings { NethSEKBM2011, title = {Velocity-Dependent Dynamic Curvature Gain for Redirected Walking}, year = {2011}, month = {3}, pages = {151-158}, abstract = {The aim of Redirected Walking (RDW) is to redirect a person along their path of travel in a Virtual Environment (VE) in order to increase the virtual space that can be explored in a given tracked area. Among other techniques, the user is redirected on a curved real-world path while visually walking straight in the VE (curvature gain). In this paper, we describe two experiments we conducted to test and extend RDW techniques. In Experiment 1, we measured the effect of walking speed on the detection threshold for curvature of the walking path. In a head-mounted display (HMD) VE, we found a decreased sensitivity for curvature for the slowest walking speed. When participants walked at 0.75 m/s, their detection threshold was approximately 0.1m-1 (radius of approximately 10m). In contrast, for faster walking speeds (>;1.0m/s), we found a significantly lower detection threshold of approximately 0.036m-1 (radius of approximately 27m). In Experiment 2, we implemented many well known redirection techniques into one dynamic RDW application. We integrated a large virtual city model and investigated RDW for free exploration. Further, we implemented a dynamic RDW controller which made use of the results from Experiment 1 by dynamically adjusting the applied curvature gain depending on the actual walking velocity of the user. In addition, we investigated the possible role of avatars to slow the users down or make them rotate their heads while exploring. Both the dynamic curvature gain controller and the avatar controller were evaluated in Experiment 2. We measured the average distance that was walked before reaching the boundaries of the tracked area. The mean walked distance was significantly larger in the condition where the dynamic gain controller was applied. This distance increased from approximately 15m for static gains to approximately 22m for dynamic gains. This did not come at the cost of an increase in simulator sickness. Applying the avatar cont roller did reveal an effect on walking distance or simulator sickness.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/VR-2011-Neth.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://conferences.computer.org/vr/2011/}, editor = {Hirose, M. , B. Lok, A. Majumder, D. Schmalstieg}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_place = {Singapore}, event_name = {IEEE Virtual Reality Conference (VR 2011)}, ISBN = {978-1-4577-0039-2}, DOI = {10.1109/VR.2011.5759454}, author = {Neth, C and Souman, JL and Engel, D and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { 6996, title = {Face Models from Noisy 3D Cameras}, journal = {Proceedings of the 3rd ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia 2010)}, year = {2010}, month = {12}, pages = {1-2}, abstract = {Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 x 144 ... 320 x 240 pixels) with a high le vel of noise present in the raw data.}, department = {Department B{\"u}lthoff}, web_url = {http://www.siggraph.org/asia2010/}, editor = {Cani, M.-P. , A. Sheffer}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Seoul, Korea}, event_name = {3rd ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia 2010)}, language = {en}, DOI = {10.1145/1899950.1899962}, author = {Breidt, M and B{\"u}lthoff, HH and Curio, C} } @Inproceedings { 6842, title = {Augmented Human-Machine Interface: Providing a Novel Haptic Cueing to the Tele-Operator}, journal = {Proceedings of the 3rd Workshop for Young Researchers on Human-Friendly Robotics (HFR 2010)}, year = {2010}, month = {10}, pages = {1-2}, abstract = {The sense of telepresence is very important in teleoperation environments in which the operator is physically separated from the vehicle. Extending the visual interface to a multi-sensory interface could allow the teleoperator to better perceive information of the environment and its constraints. The use of force feedback would complement the visual information through the sense of touch. This paper focuses on a novel concept of haptic cueing developed in order to optimize the performance of a teleoperator and to improve the human-machine interfaces. A first experiment showed the effectiveness of the newly developed haptic cueing, the Indirect Haptic Aiding, with respect to visual cueing only. In a second experiment, we compared the IHA to an existing haptic concept, the Direct Haptic Aiding. The problem of wind gust rejection in Remotely Piloted Vehicles is used as test bench. The results show the effectiveness of both methods but a better performance of the IHA-based system for pilots without any previous training about the haptic aids. DHA-based system provided instead better results after some pilot training on the experiment. Pilots reported better sensation of the wind gusts with IHA-based feedback. The two haptic aids concepts are going to be compared in an obstacle detection/avoidance task.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/HFR\%202010_6842[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://hfr2010.wordpress.com/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {3rd Workshop for Young Researchers on Human-Friendly Robotics (HFR 2010)}, language = {en}, author = {Alaimo, SMC and Pollini, L and Bresciani, J-P and B{\"u}lthoff, HH} } @Inproceedings { RobuffoGiordanoFSSLB2010, title = {Towards Bilateral Teleoperation of Multi-Robot Systems}, year = {2010}, month = {10}, pages = {1-2}, abstract = {In this paper, we discuss a novel control strategy for the bilateral teleoperation of multi-robot systems, by especially focusing on the case of Unmanned aerial Vehicles (UAVs). Two control schemes are proposed: a top-down approach to maintain a desired topology of the local robots, and a bottomup approach which allows changes of topology based on local robots interactions. In both cases, passivity of overall teleoperation system is formally guaranteed. The haptic cues fed back to the operator reflect the motion status of the multirobot team and inform him about the presence of obstacles. The proposed approaches are validated through semi-experiments.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/HFR-2010-Robuffo.pdf}, department = {Department B{\"u}lthoff}, web_url2 = {http://hfr2010.wordpress.com/}, event_place = {T{\"u}bingen, Germany}, event_name = {3rd Workshop for Young Researchers on Human-Friendly Robotics (HFR 2010)}, author = {Robuffo Giordano, P and Franchi, A and Son, HI and Secchi, C and Lee, D and B{\"u}lthoff, HH} } @Inproceedings { 6682, title = {Virtual Storyteller in Immersive Virtual Environments Using Fairy Tales Annotated for Emotion States}, journal = {Virtual Environments 2010: Joint Virtual Reality Conference of EGVE - 16th Eurographics Symposium on Virtual Environments, EuroVR - the 7th EuroVR (INTUITION) Conference, VEC - the annual Virtual Efficiency Congress}, year = {2010}, month = {10}, pages = {65-68}, abstract = {This paper describes the implementation of an automatically generated virtual storyteller from fairy tale texts which were previously annotated for emotion. In order to gain insight into the effectiveness of our virtual storyteller we recorded face, body and voice of an amateur actor and created an actor animation video of one of the fairy tales. We also got the actor's annotation of the fairy tale text and used this to create a virtual storyteller video. With these two videos, the virtual storyteller and the actor animation, we conducted a user study to determine the effectiveness of our virtual storyteller at conveying the intended emotions of the actor. Encouragingly, participants performed best (when compared to the intended emotions of the actor) when they marked the emotions of the virtual storyteller. Interestingly, the actor himself was not able to annotate the animated actor video with high accuracy as compared to his annotated text. This argues that for future work we must have our actors also annotate their body and facial expressions, not just the text, in order to further investigate the effectiveness of our virtual storyteller. This research is a first step towards using our virtual storyteller in real-time immersive virtual environments.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Alexandrova_JVRC_authors_version_6682[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.interaction-design.org/references/conferences/proceedings_of_the_joint_virtual_reality_conference_of_egve_-_eurovr_-_vec.html}, editor = {Kuhlen, T. , S. Coquillart, V. Interrante}, publisher = {Eurographics Association}, address = {Goslar, Germany}, booktitle = {Virtual Environments 2010}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Stuttgart, Germany}, event_name = {2010 Joint Virtual Reality Conference of EuroVR - EGVE - VEC (JVRC 2010)}, language = {en}, ISBN = {978-3-905674-30-9}, DOI = {10.2312/EGVE/JVRC10/065-068}, author = {Alexandrova, IV and Volkova, EP and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { 6771, title = {A Comparison of Direct and Indirect Haptic Aiding for Remotely Piloted Vehicles}, journal = {Proceedings of the 19th IEEE International Symposium in Robot and Human Interactive Communication (IEEE Ro-Man 2010)}, year = {2010}, month = {9}, pages = {506-512}, abstract = {The paper presents an experimental evaluation of two different Haptic aiding concepts: Direct and Indirect Haptic Aiding. Two Haptic systems were designed and tested using an experimental setup. The problem of wind gust rejection in Remotely Piloted Vehicles is used as test bench. Test results show the effectiveness of both methods but a better performance of the IHA-based system for pilots without any previous training about the experiment. DHA-based system provided instead better results after some pilot training on the experiment. Pilots reported better sensation of the wind gusts with IHA-based feedback.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/0174_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=16167}, editor = {Avizzano, C. A , E. Ruffaldi, M. Fontana, M. Carrozzino, M. Bergamasco}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Viareggio, Italy}, event_name = {19th IEEE International Symposium in Robot and Human Interactive Communication (IEEE Ro-Man 2010)}, language = {en}, DOI = {10.1109/ROMAN.2010.5598647}, author = {Alaimo, SMC and Pollini, L and Bresciani, J-P and B{\"u}lthoff, HH} } @Inproceedings { 6632, title = {Influence of display type and field of view on drivers’ performance in a motion-based driving simulator}, journal = {Proceedings of the Driving Simulation Conference 2010 Europe (DSC Europe 2010)}, year = {2010}, month = {9}, pages = {81-88}, abstract = {Different solutions are used on driving simulators to provide visual feedback. In this study, we investigated the influence of projection technology and field of view on drivers performance in a slalom driving task. We tested a head mounted display against a curved projection system on our CyberMotion simulator, based on an anthropomorphic robot arm. The results showed that drivers performed significantly better using the projection screen than the HMD. The FoV and the motion simulation did not have a measurable influence on the performance.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/DSC2010_Grabe-et-al_6632[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dsc2010.ensam.eu/}, editor = {Kemeny, A. , F. Mérienne, S. Espié}, publisher = {INRETS}, address = {Bron, France}, booktitle = {Trends in driving simulation design and experiments}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Paris, France}, event_name = {Driving Simulation Conference Europe (DSC 2010)}, language = {en}, ISBN = {978-2-85782-685-9}, author = {Grabe, V and Pretto, P and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Inproceedings { 6656, title = {Towards Artificial Systems: What Can We Learn from Human Perception?}, journal = {PRICAI 2010: Trends in Artificial Intelligence}, year = {2010}, month = {9}, pages = {1-3}, abstract = {Research in learning algorithms and sensor hardware has led to rapid advances in artificial systems over the past decade. However, their performance continues to fall short of the efficiency and versatility of human behavior. In many ways, a deeper understanding of how human perceptual systems process and act upon physical sensory information can contribute to the development of better artificial systems. In the presented research, we highlight how the latest tools in computer vision, computer graphics, and virtual reality technology can be used to systematically understand the factors that determine how humans perform in realistic scenarios of complex task-solving.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/PRICAI-62300001\%20(1)_6656[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.pricai2010.org/default.asp}, editor = {Zhang, B.-T. , M. A. Orgun}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {PRICAI 2010: Trends in Artificial Intelligence}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Daegu, South Korea}, event_name = {11th Pacific Rim International Conference on Artificial Intelligence}, language = {en}, ISBN = {978-3-642-15246-7}, DOI = {10.1007/978-3-642-15246-7_1}, author = {B{\"u}lthoff, HH and Chuang, LL} } @Inproceedings { 6715, title = {Implementation and validation of a model of the MPI Stewart platform}, journal = {Proceedings of the 2010 AIAA Modeling and Simulation Technologies Conference}, year = {2010}, month = {8}, pages = {1007-1019}, abstract = {A simulated model of the MPI Stewart platform can be used to identify the influence of motion system characteristics on human control behaviour in active closed-loop control experiments on the SIMONA Research Simulator. In this paper, a previously identified model of the MPI Stewart platform was analysed with describing function measurements, and it was found that a reduced form of the model was sufficient to capture the relevant dynamics. The reduced model was simulated on the SIMONA Research Simulator and describing function measurements were performed with two IMUs. Both IMUs revealed a resonance peak in measurements of response magnitude at the highest frequencies. A reduced time delay was found with the newer IMU. With the describing function measurements, the implementation of the MPI Stewart platform model was validated in terms of the frequency response and the time delay.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Nieuwenhuizen2010_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2010-8217}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Toronto, Canada}, event_name = {AIAA Modeling and Simulation Technologies Conference 2010}, language = {en}, ISBN = {978-1-62410-152-6}, DOI = {10.2514/6.2010-8217}, author = {Nieuwenhuizen, FM and van Paassen, MM and Mulder, M and B{\"u}lthoff, HH} } @Inproceedings { ChuangBBF2010, title = {Measuring unrestrained gaze on wall-sized displays}, year = {2010}, month = {8}, pages = {347-348}, abstract = {Motivation -- Natural gaze involves the coordinated movements of eye, head and torso. This allows access to a wide field of view, up to a range of 260\(^{\circ}\) (Chen, Solinger, Poncet \& Lancet, 1999). The recent increase in large displays places a demand on being able to track a mobile user's gaze over this extensive range. Research approach -- We developed an extensible system for measuring the gaze of users on wall-sized displays. Our solution combines the inputs of a conventional head-mounted eyetracker (Eyelink2©, SR Research) and motion-capture system (Vicon MX©, Vicon), to provide real-time measurements of a mobile user's gaze in 3D space. Findings/Design -- The presented system serves as a single platform for studying user behavior across a wide range of tasks: single-step saccade shifts, free-viewing of natural scenes, visual search and gaze-assisted user interfaces. Importantly, it allows eye- and head-movements to be separately measured without compromising the accuracy of combined gaze measurements. Take away message -- Unrestrained gaze movements on a large display can be accurately measured by suitably combining the inputs of conventional eye- and body-tracking hardware.}, department = {Department B{\"u}lthoff}, web_url = {http://ecce2010.tudelft.nl/}, editor = {Neerincx, W. , W-P Brinkman}, publisher = {ACM Press}, address = {New York, NY, USA}, event_place = {Delft, Netherlands}, event_name = {28th Annual European Conference on Cognitive Ergonomics (ECCE '10)}, ISBN = {978-1-60558-946-6}, DOI = {10.1145/1962300.1962379}, author = {Chuang, LL and Bieg, H-J and B{\"u}lthoff, HH and Fleming, RW} } @Inproceedings { 6426, title = {The Direction Bias and the Incremental Construction of Survey Knowledge}, journal = {Cognition in Flux: Proceedings of the 32nd Annual Conference of the Cognitive Science Society}, year = {2010}, month = {8}, pages = {2500-2505}, abstract = {This study examines how spatial memory acquired from navigation is used to perform a survey task involving pointing. Participants learned a route through a virtual city by walking it multiple times in one direction on an omnidirectional treadmill. After learning, they were teleported to several locations along the route, self-localized and pointed to multiple other locations along the route. Pointing was done away from or towards the current location. Preliminary data show that participants were faster in pointing away. This suggests that pointing was based on an incremental process rather than an all-at-once process which is consistent with mentally walking through a cognitive map or constructing a mental model of currently non-visible areas of the city. On average participants pointed faster to targets located further down the route towards the end than to targets located route upwards towards the start. Analysis of individual performance showed that more participants than expected by chance showed such an effect of target direction also in their pointing accuracy. The direction of this effect differed between participants. These direction biases suggest that at least some participants encoded the environmental space by multiple interconnected locations and used this representation also for pointing.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/COGSCI2010-Meilinger_6426[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://cognitivesciencesociety.org/conference2010/index.html}, editor = {Ohlsson, S. , R. Catrambone}, publisher = {Cognitive Science Society}, address = {Austin, TX, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Portland, OR, USA}, event_name = {32nd Annual Conference of the Cognitive Science Society (CogSci 2010)}, language = {en}, author = {Meilinger, T and B{\"u}lthoff, HH} } @Inproceedings { 6623, title = {Egocentric distance judgments in a large screen display immersive virtual environment}, journal = {Proceedings of the 7th Symposium on Applied Perception in Graphics and Visualization (APGV 2010)}, year = {2010}, month = {7}, pages = {57-60}, abstract = {People underestimate egocentric distances in head-mounted display virtual environments, as compared to estimates done in the real world. Our work investigates whether distances are still compressed in a large screen display immersive virtual environment, where participants are able to see their own body surrounded by the virtual environment. We conducted our experiment in both the real world using a real room and the large screen display immersive virtual environment using a 3D model of the real room. Our results showed a significant underestimation of verbal reports of egocentric distances in the large screen display immersive virtual environment, while the distance judgments of the real world were closer to veridical. Moreover, we observed a significant effect of distances in both environments. In the real world closer distances were slightly underestimated, while further distances were slightly overestimated. In contrast to the real world in the virtual environment participants overestimated closer distanc es (up to 2.5m) and underestimated distances that were further than 3m. A possible reason for this effect of distances in the virtual environment may be that participants perceived stereo cues differently when the target was projected on the floor versus on the front of the large screen.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Alexandrova_APGV_authors_version_6623[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/}, editor = {Guttierez, D. , J. Kearney, M. Banks, K. Mania}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {7th Symposium on Applied Perception in Graphics and Visualization (APGV 2010)}, language = {en}, ISBN = {978-1-4503-0248-7}, DOI = {10.1145/1836248.1836258}, author = {Alexandrova, IV and Teneva, PT and de la Rosa, S and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Inproceedings { 6538, title = {Preliminary Evaluation of a Haptic Aiding Concept for Remotely Piloted Vehicles}, journal = {Haptics: Generating and Perceiving Tangible Sensations (EuroHaptics 2010)}, year = {2010}, month = {7}, pages = {418-425}, abstract = {This paper shows a preliminary experimental evaluation of a novel haptic aiding for Remotely Piloted Vehicles. The aerodynamically-inspired haptic feedback law was named Conventional Aircraft Artificial Feel, and was implemented as a variable stiffness spring. The experimental set-up comprises a fully nonlinear mathematical model of the aircraft, a visual display and a haptic device (a 3 DoF Omega Device). The tests, performed using a set of 18 na{\"i}ve subjects, show the validity of the proposed approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/61920418_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.eurohaptics2010.org/index.shtml}, editor = {Kappers, A.M.L. , J.B.F. Van Erp, W.M. Bergmann Tiest, F.C.T. Van Der Helm}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Haptics: Generating and Perceiving Tangible Sensations}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Amsterdam, Netherlands}, event_name = {EuroHaptics 2010}, language = {en}, ISBN = {978-3-642-14075-4}, DOI = {10.1007/978-3-642-14075-4_62}, author = {Alaimo, SMC and Pollini, L and Magazz{\`u}, A and Bresciani, J-P and Robuffo Giordano, P and Innocenti, M and B{\"u}lthoff, HH} } @Inproceedings { 6541, title = {A Communication Task in HMD Virtual Environments: Speaker and Listener Movement Improves Communication}, journal = {Proceedings of the 23rd Annual Conference on Computer Animation and Social Agents (CASA 2010)}, year = {2010}, month = {6}, pages = {1-4}, abstract = {In this paper we present an experiment which investigates the influence of animated real-time self-avatars in immersive virtual environments on a communication task. Further we investigate the influence of 1st and 3rd person perspectives and the influence of tracked speaker and listener. We find that people perform best in our communication task when both the speaker and the listener have an animated self-avatar and when the speaker is in the 3rd person. The more people move the better they perform in the communication task. These results suggest that when two people in a virtual environment are animated then they do use gestures to communicate.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/casa_final_6541[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://casa2010.inria.fr/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Saint-Malo, France}, event_name = {23rd Annual Conference on Computer Animation and Social Agents (CASA 2010)}, language = {en}, author = {Dodds, TJ and Mohler, BJ and B{\"u}lthoff, HH} } @Inproceedings { 6819, title = {Emotional Perception of Fairy Tales: Achieving Agreement in Emotion Annotation of Text}, journal = {Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text}, year = {2010}, month = {6}, pages = {98-106}, abstract = {Emotion analysis (EA) is a rapidly developing area in computational linguistics. An EA system can be extremely useful in fields such as information retrieval and emotion-driven computer animation. For most EA systems, the number of emotion classes is very limited and the text units the classes are assigned to are discrete and predefined. The question we address in this paper is whether the set of emotion categories can be enriched and whether the units to which the categories are assigned can be more flexibly defined. We present an experiment showing how an annotation task can be set up so that untrained participants can perform emotion analysis with high agreement even when not restricted to a predetermined annotation unit and using a rich set of emotion categories. As such it sets the stage for the development of more complex EA systems which are closer to the actual human emotional perception of text.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/NAACL-HLT-2010-Volkova_6819[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.site.uottawa.ca/\verb=~=diana/naacl2010_EmotionWorkshop.html}, editor = {Inkpen, D. , C. Strapparava}, publisher = {Association for Computational Linguistics}, address = {Morristown, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text}, language = {en}, author = {Volkova, EP and Mohler, BJ and Meurers, D and Gerdemann, D and B{\"u}lthoff, HH} } @Inproceedings { 6247, title = {A Novel Framework for Closed-Loop Robotic Motion Simulation - Part I: Inverse Kinematics Design}, journal = {Proceedings of the 2010 IEEE International Conference on Robotics and Automation (ICRA 2010)}, year = {2010}, month = {5}, pages = {3876-3883}, abstract = {This paper considers the problem of realizing a 6-DOF closed-loop motion simulator by exploiting an anthropomorphic serial manipulator as motion platform. Contrary to standard Stewart platforms, an industrial anthropomorphic manipulator offers a considerably larger motion envelope and higher dexterity that let envisage it as a viable and superior alternative. Our work is divided in two papers. In this Part I, we discuss the main challenges in adopting a serial manipulator as motion platform, and thoroughly analyze one key issue: the design of a suitable inverse kinematics scheme for online motion reproduction. Simulation results are proposed to analyze the effectiveness of our approach. Part II will address the design of a motion cueing algorithm tailored to the robot kinematics, and will provide an experimental evaluation on the chosen scenario: closed-loop simulation of a Formula 1 racing car.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/motsim_part_1_6247[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://icra2010.grasp.upenn.edu/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, event_place = {Anchorage, AS, USA}, event_name = {2010 IEEE International Conference on Robotics and Automation (ICRA 2010)}, language = {en}, ISBN = {978-1-424-45038-1}, DOI = {10.1109/ROBOT.2010.5509647}, author = {Robuffo Giordano, P and Masone, C and Tesch, J and Breidt, M and Pollini, L and B{\"u}lthoff, HH} } @Inproceedings { 6249, title = {A Novel Framework for Closed-Loop Robotic Motion Simulation - Part II: Motion Cueing Design and Experimental Validation}, journal = {Proceedings of the 2010 IEEE International Conference on Robotics and Automation (ICRA 2010)}, year = {2010}, month = {5}, pages = {3896-3903}, abstract = {This paper, divided in two Parts, considers the problem of realizing a 6-DOF closed-loop motion simulator by exploiting an anthropomorphic serial manipulator as motion platform. After having proposed a suitable inverse kinematics scheme in Part I, we address here the other key issue, i.e., devising a motion cueing algorithm tailored to the specific robot motion envelope. An extension of the well-known classical washout filter designed in cylindrical coordinates will provide an effective solution to this problem. The paper will then present a thorough experimental evaluation of the overall architecture (inverse kinematics + motion cueing) on the chosen scenario: closed-loop simulation of a Formula 1 racing car. This will prove the feasibility of our approach in fully exploiting the robot motion capabilities as a motion simulator.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/motsim_part_2_6249[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://icra2010.grasp.upenn.edu/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, event_place = {Anchorage, AS, USA}, event_name = {2010 IEEE International Conference on Robotics and Automation (ICRA 2010)}, language = {en}, DOI = {10.1109/ROBOT.2010.5509945}, author = {Robuffo Giordano, P and Masone, C and Tesch, J and Breidt, M and Pollini, L and B{\"u}lthoff, HH} } @Inproceedings { 6396, title = {Visual-Vestibular Feedback for Enhanced Situational Awareness in Teleoperation of UAVs}, journal = {Proceedings of the American Helicopter Society 66th Annual Forum and Technology Display}, year = {2010}, month = {5}, pages = {2809-2818}, abstract = {This paper presents a novel concept for improving the situational awareness of a ground operator in remote control of a Unmanned Arial Vehicle (UAV). To this end, we propose to integrate vestibular feedback with the usual visual feedback obtained from a UAV onboard camera. We use our motion platform, the CyberMotion simulator, so as to reproduce online the desired motion cues. We test this architecture by flying a small-scale quadcopter and run a detailed performance evaluation on 12 test subjects. We then discuss the results in terms of possible benefits for facilitating the remote control task.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/AHS_FORUM66_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.vtol.org/forum66/forum66.html}, publisher = {AHS International}, address = {Alexandria, VA, USA}, booktitle = {AHS International 66th Annual Forum}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Phoenix, AZ, USA}, event_name = {66th American Helicopter Society International Annual Forum 2010}, language = {en}, ISBN = {978-1-61782-926-0}, author = {Robuffo Giordano, P and Deusch, H and L{\"a}chele, J and B{\"u}lthoff, HH} } @Inproceedings { 6246, title = {Eye and Pointer Coordination in Search and Selection Tasks}, journal = {Proceedings of the Symposium on Eye Tracking Research and Applications (ETRA 2010)}, year = {2010}, month = {3}, pages = {89-92}, abstract = {Selecting a graphical item by pointing with a computer mouse is a ubiquitous task in many graphical user interfaces. Several techniques have been suggested to facilitate this task, for instance, by reducing the required movement distance. Here we measure the natural coordination of eye and mouse pointer control across several search and selection tasks. We find that users automatically minimize the distance to likely targets in an intelligent, task dependent way. When target location is highly predictable, top-down knowledge can enable users to initiate pointer movements prior to target fixation. These findings ques-tion the utility of existing assistive pointing techniques and suggest that alternative approaches might be more effective.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/ETRA2010-Bieg_6246[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://etra.cs.uta.fi/}, editor = {Morimoto, C. H., H. Istance, A. Hyrskykari, Q. Ji}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Austin, TX, USA}, event_name = {Symposium on Eye Tracking Research and Applications (ETRA 2010)}, language = {en}, DOI = {10.1145/1743666.1743688}, author = {Bieg, H-J and Chuang, LL and Fleming, RW and Reiterer, H and B{\"u}lthoff, HH} } @Inproceedings { 6129, title = {Control design and experimental evaluation of the 2D CyberWalk platform}, journal = {Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)}, year = {2009}, month = {10}, pages = {5051-5058}, abstract = {The CyberWalk is a large size 2D omni-directional platform that allows unconstrained locomotion possibilities to a walking user for VR exploration. In this paper we present the motion control design for the platform, which has been developed within the homonymous European research project. The objective is to compensate the intentional motion of the user, so as to keep her/him always close to the platform center while limiting the perceptual effects due to actuation commands. The controller acts at the acceleration level, using suitable observers to estimate the unmeasurable intentional walker‘s velocity and acceleration. A moving reference position is used to limit the accelerations felt by the user in critical transients, e.g., when the walker suddenly stops motion. Experimental results are reported that show the benefit of designing separate control gains in the two orthogonal directions (lateral and sagittal) of a frame attached to the walker.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/IROS09_CyberWalk_submitted_6129[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.iros09.mtu.edu/index.php/IROS_2009:_The_2009_IEEE/RSJ_International_Conference_on_Intelligent_RObots_and_Systems}, publisher = {IEEE Service Center}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, event_place = {St. Louis, MO, USA}, event_name = {2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)}, language = {en}, ISBN = {978-1-424-43803-7}, DOI = {10.1109/IROS.2009.5354610}, author = {De Luca, A and Mattone, R and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Inproceedings { 5899, title = {Markerless 3D Face Tracking (DAGM 2009)}, journal = {Pattern Recognition: 31st DAGM Symposium}, year = {2009}, month = {9}, pages = {41-50}, abstract = {We present a novel algorithm for the markerless tracking of deforming surfaces such as faces. We acquire a sequence of 3D scans along with color images at 40Hz. The data is then represented by implicit surface and color functions, using a novel partition-of-unity type method of efficiently combining local regressors using nearest neighbor searches. Both these functions act on the 4D space of 3D plus time, and use temporal information to handle the noise in individual scans. After interactive registration of a template mesh to the first frame, it is then automatically deformed to track the scanned surface, using the variation of both shape and color as features in a dynamic energy minimization problem. Our prototype system yields high-quality animated 3D models in correspondence, at a rate of approximately twenty seconds per timestep. Tracking results for faces and other objects are presented.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/WalderEtAl_DAGM2009_5899[0].pdf}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, web_url = {http://www.dagm2009.org/index.php/main.html}, editor = {Denzler, J. , G. Notni, H. S{\"u}sse}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Pattern Recognition}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Lecture Nores in Computer Science}, event_place = {Jena, Germany}, event_name = {31. Symposium of the German Association for Pattern Recognition (DAGM 2009)}, language = {en}, ISBN = {978-3-642-03798-6}, DOI = {10.1007/978-3-642-03798-6_5}, author = {Walder, C and Breidt, M and B{\"u}lthoff, HH and Sch{\"o}lkopf, B and Curio, C} } @Inproceedings { 5975, title = {The Effect of Simulator Motion on Pilot Control Behaviour for Agile and Inert Helicopter Dynamics}, journal = {35th European Rotorcraft Forum (ERF 2009)}, year = {2009}, month = {9}, pages = {1051-1063}, abstract = {Even though simulators are often used in flight training, the effects of the different motion components on pilot performance and control behaviour are still not fully understood. In most hexapod motion base simulators the translational motion needs to be reduced significantly to fit within the limited motion space, while the rotational motion might not need attenuation. This paper presents the results of an experiment that investigated the effects of simulator motion in a roll-lateral helicopter control task for both agile and inert helicopter dynamics. The experiment was performed in the MPI Motion Simulator, which has the unique ability of presenting the motion in this task 1-to-1. The results indicate that both roll and lateral motion are important for increasing performance in reducing the roll error. The lateral motion also significantly reduced the lateral tracking errors. Pilots increased their control activity, but had a lower performance in reducing the lateral error for the inert helicopter dynamics. These effects in performance and control activity were caused by a change in the pilots’ control strategy as was observed from the multimodal pilot model parameters. The effects on pilot tracking performance were also apparent from a significant change in the disturbance and target open-loop characteristics.}, department = {Department B{\"u}lthoff}, web_url = {http://www.erf2009.org}, editor = {Lopez, L. , P. Brandt}, publisher = {Deutsche Gesellschaft f{\"u}r Luft- und Raumfahrt}, address = {Bonn, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Deutsche Gesellschaft f{\"u}r Luft- und Raumfahrt}, event_place = {Hamburg, Germany}, event_name = {35th European Rotorcraft Forum (ERF 2009)}, language = {en}, ISBN = {978-3-932182-65-0}, author = {Nieuwenhuizen, FM and Zaal, PMT and Teufel, H and Mulder, M and B{\"u}lthoff, HH} } @Inproceedings { 5861, title = {Does jerk have to be considered in linear motion simulation?}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference (AIAA 2009)}, year = {2009}, month = {8}, pages = {1381-1388}, abstract = {Perceptual thresholds for the detection of the direction of linear motion are important for motion simulation. There are situations in which a subject should not perceive the motion direction as, e.g., during repositioning of a simulator, but also opposite cases where a certain motion percept must intentionally be induced in the subject. The exact dependency of the perceptual thresholds on the time evolution of the presented motion profile is still an open question. Previous studies have found evidence for a sensitivity of the thresholds on the rate of change of acceleration, called jerk. In this study we investigate three motion profiles which differ in their jerk characteristics. We want to evaluate which profile can move people furthest in the horizontal plane in a given time without them noticing the direction. Our results suggest that a profile with a minimum peak jerk value should be chosen.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/AIAA2009-Soyka-kurz.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2009-6245}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Chicago, IL, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2009}, language = {en}, ISBN = {978-1-62410-161-8}, DOI = {10.2514/6.2009-6245}, author = {Soyka, F and Teufel, H and Beykirch, K and Robuffo Giordano, P and Butler, J and Nieuwenhuizen, FM and B{\"u}lthoff, HH} } @Inproceedings { 5709, title = {Spatial Memory for Highly Familiar Environments}, journal = {Proceedings of the 31st Annual Conference of the Cognitive Science Society (CogSci 2009)}, year = {2009}, month = {8}, pages = {2650-2655}, abstract = {In this experiment we examined orientation dependency in human memory for a highly familiar environmental space. Twenty-seven inhabitants living for at least two years in T{\"u}bingen saw a photorealistic virtual model of the city center (Virtual T{\"u}bingen) through a head-mounted display. They were teleported to five different initial locations in Virtual T{\"u}bingen and asked to point towards well-known target locations. This procedure was repeated in twelve different body-orientations for each of the initial locations. Participants pointed more accurately when oriented northwards regardless of the initial location. We also found a small effect of local orientation. The more participants were aligned with the street leading to the target location the better was their pointing performance. Even though the strong alignment effect with a global orientation is predicted by reference direction theory, this theory does not predict that this global orientation is, first, common for almost all participants, and second, t hat this orientation is north. We discuss our results with respect to well-known theories of spatial memory and speculate that the bias we find for north orientation is due to participants relying on memory of a city map of T{\"u}bingen for their pointing response.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/CogSci2009-Frankenstein_5709[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://csjarchive.cogsci.rpi.edu/proceedings/2009/index.html}, editor = {Taatgen, N. , H. Van Rijn}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Amsterdam, Netherlands}, event_name = {31st Annual Conference of the Cognitive Science Society (CogSci 2009)}, language = {en}, ISBN = {978-0-9768318-5-3}, author = {Frankenstein, J and Meilinger, T and Mohler, BJ and B{\"u}lthoff, HH} } @Inproceedings { 6227, title = {Towards Real-Time Aircraft Simulation with the MPI Motion Simulator}, journal = {Proceedings of the 2009 AIAA Modeling and Simulation Technologies Conference}, year = {2009}, month = {8}, pages = {623-632}, abstract = {The paper describes the recent advancements gained on the MPI motion simulator project. The aim of this project is the use of an anthropomorphic robot as actuation system for a motion platform intended for real time flight simulation. Almost all commercially available motion platforms rely on the so called Stewart platform, that is a 6-DOF platform that can bear high payloads and can achieve high accelerations. On the other hand an anthropomorphic manipulator offers a larger range of motion and higher dexterity, that let envisage this novel motion simulator as a viable and superior alternative [1,2]. The paper addresses the use of a new inverse kinematics algorithm capable of keeping joint velocities and accelerations within their limits. Preliminary experimental results performed using the proposed algorithm along with possible further improvements are discussed.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/simulatoronMPIplatform_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2009-5918}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Chicago, IL, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2009}, language = {en}, ISBN = {978-1-62410-161-8}, DOI = {10.2514/6.2009-5918}, author = {Niccolini, M and Pollini, L and Innocenti, M and Robuffo Giordano, P and Teufel, H and B{\"u}lthoff, HH} } @Inproceedings { 5974, title = {Towards Simulating a Mid-size Stewart Platform on a Large Hexapod Simulator}, journal = {Proceedings of the 2009 AIAA Modeling and Simulation Technologies Conference}, year = {2009}, month = {8}, pages = {613-622}, abstract = {For a recent project on the influence of motion system characteristic on human perception and control behaviour, a dynamic model of the MPI Stewart platform was developed. The model parameters were estimated from measurements involving motion along a circular trajectory and frequency sweeps. Simulation results showed that the model response with optimised parameters was very close to the measured platform response. However, additional measurements are required to identify the platform mass and vertical centre of gravity position correctly. Validation of the dynamic model with platform measurements in heave showed favourable results. The dynamic model of the MPI Stewart platform will be validated further in multiple degrees-of-freedom and will be used in active closed-loop experiments.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Nieuwenhuizen2009b_5974[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2009-5917}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Chicago, IL, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference 2009}, language = {en}, ISBN = {978-1-62410-161-8}, DOI = {10.2514/6.2009-5917}, author = {Nieuwenhuizen, FM and van Paassen, MM and Mulder, M and Beykirsch, K and B{\"u}lthoff, HH} } @Inproceedings { 6374, title = {Acquisition of human EEG data during linear self-motion on a Stewart platform}, journal = {Proceedings of the 4th International IEEE/EMBS Conference on Neural Engineering (NER 2009)}, year = {2009}, month = {5}, pages = {585-588}, abstract = {The present study investigated the feasibility of acquiring electroencephalography (EEG) data during self-motion in human subjects. Subjects performed a visual oddball task - designed to evoke a P3 event-related potential - while being passively moved in the fore-aft direction on a Stewart platform. The results of this study indicate that reliable EEG data can be obtained during self-motion on a Stewart platform: this finding is important for the ecological validity of further research into human motion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/IEEE-EMBS-Conf-Neural-Engineering-2009-Nolan_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ne2009.engineering.asu.edu/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, event_place = {Antalya, Turkey}, event_name = {4th International IEEE/EMBS Conference on Neural Engineering (NER 2009)}, language = {en}, ISBN = {978-1-4244-2072-8}, DOI = {10.1109/NER.2009.5109364}, author = {Nolan, H and Whelan, R and Reilly, RB and B{\"u}lthoff, HH and Butler, JS} } @Inproceedings { 5760, title = {Medial Features for Superpixel Segmentation}, journal = {Proceedings of the Eleventh IAPR Conference on Machine Vision Applications (MVA 2009)}, year = {2009}, month = {5}, pages = {248-252}, abstract = {Image segmentation plays an important role in computer vision and human scene perception. Image oversegmentation is a common technique to overcome the problem of managing the high number of pixels and the reasoning among them. Specifically, a local and coherent cluster that contains a statistically homogeneous region is denoted as a superpixel. In this paper we propose a novel algorithm that segments an image into superpixels employing a new kind of shape centered feature which serve as a seed points for image segmentation, based on Gradient Vector Flow fields (GVF) [14]. The features are located at image locations with salient symmetry. We compare our algorithm to state-of-the-art superpixel algorithms and demonstrate a performance increase on the standard Berkeley Segmentation Dataset.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/mva2009_5760[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.mva-org.jp/mva2009/}, publisher = {MVA Organizing Committee}, address = {Tokyo, Japan}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Yokohama, Japan}, event_name = {Eleventh IAPR Conference on Machine Vision Applications (MVA 2009)}, language = {en}, author = {Engel, D and Spinello, L and Triebel, R and Siegwart, R and B{\"u}lthoff, HH and Curio, C} } @Inproceedings { 5818, title = {Does Brief Exposure to a Self-avatar Affect Common Human Behaviors in Immersive Virtual Environments?}, journal = {Eurographics 2009: The 30th Annual Conference of the European Association for Computer Graphics}, year = {2009}, month = {4}, pages = {33-36}, abstract = {A plausible assumption is that self-avatars increase the realism of immersive virtual environments (VEs), because self-avatars provide the user with a visual representation of his/her own body. Consequently having a self-avatar might lead to more realistic human behavior in VEs. To test this hypothesis we compared human behavior in VE with and without providing knowledge about a self-avatar with real human behavior in real-space. This comparison was made for three tasks: a locomotion task (moving through the content of the VE), an object interaction task (interacting with the content of the VE), and a social interaction task (interacting with other social entities within the VE). Surprisingly, we did not find effects of a self-avatar exposure on any of these tasks. However, participant’s VE and real world behavior differed significantly. These results challenge the claim that knowledge about the self-avatar substantially influences natural human behavior in immersive VEs.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/EG2009_5818[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.eurographics2009.de/}, publisher = {European Association for Computer Graphics}, address = {Geneve, Switzerland}, booktitle = {Eurographics 2009}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {M{\"u}nchen, Germany}, event_name = {30th Annual Conference of the European Association for Computer Graphics}, language = {en}, author = {Streuber, S and de la Rosa, S and Trutoiu, LC and B{\"u}lthoff, HH and Mohler, B} } @Inproceedings { 5628, title = {Effect of lateral motion on drivers‘ performance in the MPI motion simulator}, journal = {Proceedings of the Driving Simulation Conference (DSC-Europe 2009)}, year = {2009}, month = {2}, pages = {121-131}, department = {Department B{\"u}lthoff}, web_url = {http://www.ctag.com/ver_evento.htm?event_id=15}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Monte Carlo, Monaco}, event_name = {Driving Simulation Conference Europe (DSC 2009)}, language = {en}, author = {Pretto, P and Nusseck, H-G and Teufel, H and B{\"u}lthoff, HH} } @Inproceedings { 5323, title = {A psychophysically calibrated controller for navigating through large environments in a limited free-walking space}, journal = {Proceedings of the 2008 ACM Symposium on Virtual Reality Software and Technology (VRST 2008)}, year = {2008}, month = {10}, pages = {157-164}, abstract = {Experience indicates that the sense of presence in a virtual environment is enhanced when the participants are able to actively move through it. When exploring a virtual world by walking, the size of the model is usually limited by the size of the available tracking space. A promising way to overcome these limitations are motion compression techniques, which decouple the position in the real and virtual world by introducing imperceptible visual-proprioceptive conflicts. Such techniques usually precalculate the redirection factors, greatly reducing their robustness. We propose a novel way to determine the instantaneous rotational gains using a controller based on an optimization problem. We present a psychophysical study that measures the sensitivity of visual-proprioceptive conflicts during walking and use this to calibrate a real-time controller. We show the validity of our approach by allowing users to walk through virtual environments vastly larger than the tracking space.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/VRST2008-Engel_5323[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://vrst2008.labri.fr/index.php}, editor = {Feiner, S. , D. Thalmann, P. Guitton, B. Fr{\"o}hlich, E. Kruijff, M. Hachet}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bordeaux, France}, event_name = {15th ACM Symposium on Virtual Reality Software and Technology (VRST 2008)}, language = {en}, DOI = {10.1145/1450579.1450612}, author = {Engel, D and Curio, C and Tcheang, L and Mohler, B and B{\"u}lthoff, HH} } @Inproceedings { 5470, title = {LibGaze: Real-time gaze-tracking of freely moving observers for wall-sized displays}, journal = {Vision, Modeling and Visualization 2008: Proceedings (VMV 2008)}, year = {2008}, month = {10}, pages = {101-110}, abstract = {We present a mobile system for tracking the gaze of an observer in real-time as they move around freely and interact with a wall-sized display. The system combines a head-mounted eye tracker with a mo- tion capture system for tracking markers attached to the eye tracker. Our open-source software library libGaze provides routines for calibrating the sys- tem and computing the viewer’s position and gaze direction in real-time. The modular architecture of our system supports simple replacement of each of the main components with alternative technology. We use the system to perform a psychophysical user-study, designed to measure how users visually explore large displays. We find that observers use head move- ments during gaze shifts, even when these are well within the range that can be com- fortably reached by eye movements alone. This suggests that free movement is important in nor- mal gaze behaviour,motivating further applications in which the tracked user is free to move.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/VMV-2008-Herholz.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.inf.uni-konstanz.de/vmv/}, editor = {Deussen, O. , D. Keim}, publisher = {IOS Press}, address = {Amsterdam, Netherlands}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Konstanz, Germany}, event_name = {13th International Fall Workshop on Vision, Modeling, and Visualization (VMV 2008)}, language = {en}, author = {Herholz, S and Chuang, LL and Tanner, TG and B{\"u}lthoff, HH and Fleming, RW} } @Inproceedings { 5517, title = {Virtual Reality as a Valuable Research Tool for Investigating Different Aspects of Spatial Cognition}, journal = {Spatial Cognition VI: Learning, Reasoning, and Talking about Space}, year = {2008}, month = {9}, pages = {1-3}, abstract = {The interdisciplinary research field of spatial cognition has benefited greatly from the use of advanced Virtual Reality (VR) technologies. Such tools have provided the ability to explicitly control specific experimental conditions, manipulate variables not possible in the real world, and provide a convincing, multimodal experience. Here we will first describe several of the VR facilities at the Max Planck Institute (MPI) for Biological Cybernetics that have been developed to optimize scientific investigations related to multi-modal self-motion perception and spatial cognition. Subsequently, we will present some recent empirical work contributing to these research areas.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Bulthoff\%20et\%20al\%20Spatial\%20Cognition\%202008_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://conference.spatial-cognition.de/sc08/}, editor = {Freksa, C. , N. S. Newcombe, P. G{\"a}rdenfors, S. W{\"o}lfl}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Spatial Cognition VI: Learning, Reasoning, and Talking about Space}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Freiburg, Germany}, event_name = {International Conference Spatial Cognition 2008}, language = {en}, ISBN = {978-3-540-87601-4}, DOI = {10.1007/978-3-540-87601-4_1}, author = {B{\"u}lthoff, HH and Campos, JL and Meilinger, T} } @Inproceedings { 5233, title = {A full-body avatar improves egocentric distance judgments in an immersive virtual environment}, journal = {Proceedings of the 5th Symposium on Applied Perception in Graphics and Visualization (APGV 08)}, year = {2008}, month = {8}, pages = {194-197}, abstract = {A number of investigators have reported that distance judgments in virtual environments (VEs) are systematically smaller than distance judgments made in comparably-sized real environments. Many variables that may contribute to this difference have been investigated but none of them fully explain the distance compression. In this paper we asked whether seeing a fully-articulated visual representation of oneself (avatar) within a virtual environment would lead to more accurate estimations of distance. We found that participants who explored near space without the visual avatar underestimated egocentric distance judgments compared to those who similarly explored near space while viewing a fully-articulated avatar. These results are discussed with respect to the perceptual and cognitive mechanisms that may be involved in the observed effects as well as the benefits of visual feedback in the form of an avatar for VE applications.}, department = {Department B{\"u}lthoff}, web_url = {http://apgv.local/archive/apgv08/}, editor = {Creem-Regehr, S. H., K. Myszkowski}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {5th Symposium on Applied Perception in Graphics and Visualization (APGV 2008)}, language = {en}, ISBN = {978-1-59593-981-4}, DOI = {10.1145/1394281.1394323}, author = {Mohler, B and B{\"u}lthoff, HH and Thompson, WB and Creem-Regehr, SH} } @Inproceedings { 5552, title = {Joint and individual walking in an immersive collaborative virtual environment}, journal = {Proceedings of the 5th Symposium on Applied Perception in Graphics and Visualization (APGV 08)}, year = {2008}, month = {8}, pages = {191}, abstract = {The aim of this experiment was to determine to which extent humans optimize their walking behavior in different conditions while navigating in a virtual maze. In two conditions participants either walked individually or jointly connected - carrying a physical stretcher. The results showed that an extra effort due to the task-required cooperation was split evenly within the group, even though the sensory feedback about the physical and social environment was significantly different for leader (e.g. was not able to see the follower) and follower (e.g. was able to see the leader). These results might indicate the emergence of a joint body: a phenomenon in which two individual action-perception loops are tuned towards each other in order to optimize a common goal.}, department = {Department B{\"u}lthoff}, web_url = {http://apgv.local/archive/apgv08/}, editor = {Creem-Regehr, S. H., K. Myszkowski}, publisher = {ACM}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, California}, event_name = {5th Symposium on Applied Perception in Graphics and Visualization (APGV 2008)}, language = {en}, ISBN = {978-1-59593-981-4}, DOI = {10.1145/1394281.1394320}, author = {Streuber, S and Chatziastros, A and Mohler, BJ and B{\"u}lthoff, HH} } @Inproceedings { 5340, title = {Learning System Dynamics: Transfer of Training in a Helicopter Hover Simulator}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2008)}, year = {2008}, month = {8}, pages = {1608-1618}, abstract = {Transfer of training between the simulation of an inert and an agile helicopter dynamic was assessed involving a quasi-transfer design. The focus of this study was to test the ability of flight-na{\"i}ve subjects to successfully acquire and transfer the skills required to perform lateral sidestep hover maneuvers in a helicopter simulation. The experiments were performed using the MPI Motion Simulator with its ability to realize a highly realistic 1:1 motion representation of a simulated helicopter maneuver. As a result, the amount of training needed to stabilize either an agile or an inert helicopter dynamic did not differ. A clear positive transfer effect was found for the acquired skills from the agile to the inert dynamics but not from the inert to the agile dynamics.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/AIAA2008-Nusseck_5340[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2008-7107}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Honolulu, Hawaii}, event_name = {AIAA Modeling and Simulation Technologies Conference 2008}, language = {en}, ISBN = {978-1-60560-811-2}, DOI = {10.2514/6.2008-7107}, author = {Nusseck, H-G and Teufel, HJ and Nieuwenhuizen, FM and B{\"u}lthoff, HH} } @Inproceedings { 5315, title = {Performance Measurements on the MPI Stewart Platform}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2008)}, year = {2008}, month = {8}, pages = {401-411}, abstract = {The report AGARD-AR-144 provides a framework for systematically assessing the dynamic characteristics of flight simulator motion systems. Several measurements defined in the report were performed on the Stewart platform located at the Max Planck Institute for Biological Cybernetics. The measurements were performed with a setup consisting of real-time hardware and an off-the-shelf IMU. Results indicated that the motion platform describing functions were very similar to the standard motion filters implemented by the platform manufacturer, but included a time delay of 100 ms. The total noise of the system mainly consisted of stochastic and high-frequency non-linear components, that were attributed to the IMU. The measurements defined by AGARD-144 proved to provide useful insight into the platform characteristics.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Nieuwenhuizen2008_5315[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2008-6531}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Institute of Aeronautics and Astronautics}, event_place = {Honolulu, Hawaii}, event_name = {AIAA Modeling and Simulation Technologies Conference 2008}, language = {en}, ISBN = {978-1-60560-811-2}, DOI = {10.2514/6.2008-6531}, author = {Nieuwenhuizen, FM and Beykirch, K and Mulder, M and Paassen, MMV and Bonten, JLG and B{\"u}lthoff, HH} } @Inproceedings { 5230, title = {Probing Dynamic Human Facial Action Recognition From The Other Side Of The Mean}, journal = {Proceedings of the 5th Symposium on Applied Perception in Graphics and Visualization (APGV 08)}, year = {2008}, month = {8}, pages = {59-66}, abstract = {Insights from human perception of moving faces have the potential to provide interesting insights for technical animation systems as well as in the neural encoding of facial expressions in the brain. We present a psychophysical experiment that explores high-level after-effects for dynamic facial expressions. We address specifically in how far such after-effects represent adaptation in neural representation for static vs. dynamic features of faces. High-level after-effects have been reported for the recognition of static faces [Webster and Maclin 1999; Leopold et al. 2001], and also for the perception of point-light walkers [Jordan et al. 2006; Troje et al. 2006]. After-effects were reflected by shifts in category boundaries between different facial expressions and between male and female walks. We report on a new after-effect in humans observing dynamic facial expressions that have been generated by a highly controllable dynamic morphable face model. As key element of our experiment, we created dynamic 'anti-expressions' in analogy to static 'anti-faces' [Leopold et al. 2001]. We tested the influence of dynamics and identity on expression-specific recognition performance after adaptation to 'anti-expressions'. In addition, by a quantitative analysis of the optic flow patterns corresponding to the adaptation and test expressions we rule out that the observed changes reflect a simple low-level motion after-effect. Since we found no evidence for a critical role of temporal order of the stimulus frames we conclude that after-effects in dynamic faces might be dominated by adaptation to the form information in individual stimulus frames.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/APGV08_CurioEtal_small_5230[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://apgv.local/archive/apgv08/}, editor = {Creem-Regehr, S. H., K. Myszkowski}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {5th Symposium on Applied Perception in Graphics and Visualization (APGV 2008)}, language = {en}, ISBN = {978-1-59593-981-4}, DOI = {http://doi.acm.org/10.1145/1394281.1394293}, author = {Curio, C and Giese, MA and Breidt, M and Kleiner, M and B{\"u}lthoff, HH} } @Inproceedings { 5626, title = {Tricking people into feeling like they are moving when they are not paying attention}, journal = {Proceedings of the 5th Symposium on Applied Perception in Graphics and Visualization (APGV 08)}, year = {2008}, month = {8}, pages = {190}, abstract = {Vection refers to illusion of self motion in stationary obervers usually by means of moving visual stimuli [Fischer and Kornm{\"u}ller 1930]. Linear vection naturally occurs when seated in a train and observing another train on an adjacent track start moving. The very compelling but brief illusion happens as observers are not paying particular attention to the environment but are rather ''defocused'' from the scene. We studied the effect of two visual attention tasks on the perception of linear vection. The results show a significant decrease in vection onset time with an attention task.}, department = {Department B{\"u}lthoff}, web_url = {http://apgv.local/archive/apgv08/}, editor = {Creem-Regehr, S. H., K. Myszkowski}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {5th Symposium on Applied Perception in Graphics and Visualization (APGV 2008)}, language = {en}, ISBN = {978-1-59593-981-4}, DOI = {10.1145/1394281.1394319}, author = {Trutoiu, LC and Streuber, S and Mohler, BJ and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Inproceedings { 5162, title = {Analyzing perceptual representations of complex, parametrically-defined shapes using MDS}, journal = {Haptics: Perception, Devices and Scenarios (Eurohaptics 2008)}, year = {2008}, month = {6}, pages = {265-274}, abstract = {In this study we show that humans are able to form a perceptual space from a complex, three-dimensional shape space that is highly congruent to the physical object space no matter if the participants explore the objects visually or haptically. The physical object space consists of complex, shell-shaped objects which were generated by varying three shape parameters. In several psychophysical experiments participants explored the objects either visually or haptically and performed similarity ratings. Multidimensional scaling (MDS) analyses showed high congruency of the visual and haptic perceptual space to the physical object space. Additionally, visual and haptic exploration resulted in very similar MDS maps providing evidence for one shared perceptual space underlying both modalities.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Eurohaptics2008-Gaissert_5162[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.disam.upm.es/\verb=~=eurohaptics2008/}, editor = {Ferre, M.}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Haptics: Perception, Devices and Scenarios}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Madrid, Spain}, event_name = {6th International Conference EuroHaptics 2008}, language = {en}, ISBN = {978-3-540-69056-6}, DOI = {10.1007/978-3-540-69057-3_31}, author = {Gaissert, N and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 5042, title = {A Roll-Lateral Helicopter Side-Step Maneuver on the MPI Motion Simulator}, journal = {AHS 64th Annual Forum}, year = {2008}, month = {5}, pages = {834-841}, abstract = {The quality of helicopter pilot training could be improved with increased use of appropriate simulators. A novel design, the MPI Motion Simulator, is evaluated by comparison with a previous study designed to investigate the required motion fidelity for helicopter flight simulation. An experiment simulating a helicopter sidestep maneuver, using roll and lateral motion, was conducted to demonstrate the contribution such a design could have. Favorable results show this setup may indeed play such a role.}, department = {Department B{\"u}lthoff}, web_url = {http://www.proceedings.com/11806.html}, publisher = {American Helicopter Society International}, address = {Alexandria, VA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {American Helicopter Society}, event_place = {Montr{\'e}al, CA}, event_name = {64th American Helicopter Society International Annual Forum (AHS 2008)}, language = {en}, ISBN = {978-1-61782-929-1}, author = {Beykirch, K and Nieuwenhuizen, FM and Teufel, H and Nusseck, H-GG and B{\"u}lthoff, HH} } @Inproceedings { 5199, title = {Effect of the size of the field of view on the perceived amplitude of rotations of the visual scene}, journal = {Proceedings of the 14th Eurographics Symposium on Virtual Environments (EGVE 08)}, year = {2008}, month = {5}, pages = {97-102}, abstract = {Efficient navigation requires a good representation of body position/orientation in the environment and an accurate updating of this representation when the body-environment relationship changes. We tested here whether the visual flow alone - i.e., no landmark - can be used to update this representation when the visual scene is rotated, and whether having a limited horizontal field of view (30 or 60 degrees), as it is the case in most virtual reality applications, degrades the performance as compared to a full field of view. Our results show that (i) the visual flow alone does not allow for accurately estimating the amplitude of rotations of the visual scene, notably giving rise to a systematic underestimation of rotations larger than 30 degrees, and (ii) having more than 30 degrees of horizontal field of view does not really improve the performance. Taken together, these results suggest that a 30 degree field of view is enough to (under)estimate the amplitude of visual rotations when only visual flow information is available, and that landmarks should probably be provided if the amplitude of the rotations has to be accurately perceived.}, department = {Department B{\"u}lthoff}, web_url = {http://www.informatik.uni-trier.de/\verb=~=ley/db/conf/egve/egve2008.html}, editor = {Van Liere, R. , B.J. Mohler}, publisher = {Eurographics Association}, address = {Aire-la-Ville, Switzerland}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Eindhoven, Netherlands}, event_name = {14th Eurographics Symposium on Virtual Environments (EGVE 2008)}, language = {en}, ISBN = {978-3-905674-06-4}, author = {Ogier, M and Mohler, BJ and B{\"u}lthoff, HH and Bresciani, J-P} } @Inproceedings { 5405, title = {Exploring Human Dynamic Facial Expression Recognition with Animation}, journal = {Proceedings of the 2008 International Conference on Cognitive Systems (CogSys 2008)}, year = {2008}, month = {4}, pages = {1-6}, department = {Department B{\"u}lthoff}, web_url = {http://www.cogsys2008.org/index.php}, address = {Karlsruhe, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Karlsruhe, Germany}, event_name = {International Conference on Cognitive Systems (CogSys 2008)}, language = {en}, author = {Curio, C and Giese, MA and Breidt, M and Kleiner, M and B{\"u}lthoff, HH} } @Inproceedings { 5232, title = {Circular, Linear, and Curvilinear Vection in a Large-screen Virtual Environment with Floor Projection}, journal = {IEEE Virtual Reality 2008 (VR 2008)}, year = {2008}, month = {3}, pages = {115-120}, abstract = {Vection is defined as the compelling sensation of illusory self- motion elicited by a moving sensory, usually visual, stimulus. This paper presents collected introspective data on the experience of linear, circular, and curvilinear vection. We evaluate the differences between twelve different trajectories and the influence of the floor projection on the illusion of self-motion. All of the simulated self- motions examined are of a constant velocity, except for a brief simulated initial acceleration. First, we find that linear translations to the left and right are perceived as the least convincing, while linear down is perceived as the most convincing of the linear trajectories. Second, we find that the floor projection significantly improves the introspective measures of linear vection experienced in a photorealistic three-dimensional town. Finally, we find that while linear forward vection is not perceived to be very convincing, curvilinear forward vection is reported to be as convincing as circular vection. Considering our experimental results, our suggestions for simulators and VE applications where vection is desirable is to increase the number of curvilinear trajectories (as opposed to linear ones) and, if possible, add floor projection in order to improve the illusory sense of self-motion.}, department = {Department B{\"u}lthoff}, web_url = {http://conferences.computer.org/vr/2008/prelim/}, editor = {Lin, M. , A. Steed, C. Cruz-Neira}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Reno, NV, USA}, event_name = {IEEE Virtual Reality Conference (VR '08)}, language = {en}, ISBN = {978-1-4244-1971-5}, DOI = {10.1109/VR.2008.4480760}, author = {Trutoiu, LC and Mohler, B and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Inproceedings { 4911, title = {Reading Perception - Perceiving Literature: an Interdisciplinary Approach}, journal = {Proceedings of the 4th International Conference on Enactive Interfaces (ENACTIVE 07)}, year = {2007}, month = {11}, pages = {369-372}, abstract = {This paper presents the results of experiments made within the interdisciplinary project between the Department for Comparative Literature at the University of T{\"u}bingen and Max Planck Institute for Biological Cybernetics. We examined the following three questions using both psychophysical and structuralistic-hermeneutical methods: a) Are there regularities in the judgments of spatial descriptions by different readers? b) Do readers encode the perceptual perspective of characters during reading? c) Are there correspondences between foregrounding effects and the physiological reaction (galvanic skin response) of readers? The results show that a) that the semantic validation of spatial descriptions showed high homogeneity; b) the method actually showed more about literary strategies concerning object occluding and required the development of new experiment approaches to identify the perspective taken by the reader, that c) the emotional response is quite idiosyncratic but can be roughly divided into two schemes (high or low response).}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/Enactive-07-Lampert.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://acroe.imag.fr/enactive07}, editor = {Luciani, A. , C. Cadoz}, publisher = {Association ACROE}, address = {Grenoble, France}, booktitle = {Enactive/07: Enaction_in_Arts}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Grenoble, France}, event_name = {4th International Conference on Enactive Interfaces}, language = {en}, author = {Lampert, A and Nusseck, M and Wertheimer, J and B{\"u}lthoff, HH} } @Inproceedings { 4823, title = {Visualization and (Mis)Perceptions in Virtual Reality}, journal = {Tagungsband 10. Workshop Sichtsysteme}, year = {2007}, month = {11}, pages = {10-14}, abstract = {Virtual Reality (VR) technologies are now being widely adopted for use in areas as diverse as surgical and military training, architectural design, driving and flight simulation, psychotherapy, and gaming/entertainment. A large range of visual displays (from desktop monitors and head-mounted displays (HMDs) to large projection systems) are all currently being employed where each display technology offers unique advantages as well as disadvantages. In addition to technical considerations involved in choosing a VR interface, it is also critical to consider perceptual and psychophysical factors concerned with visual displays. It is now widely recognized that perceptual judgments of particular spatial properties are different in VR than in the real world. In this paper, we will provide a brief overview of what is currently known about the kinds of perceptual errors that can be observed in virtual environments (VEs). Subsequently we will outline the advantages and disadvantages of particular visual displays by foc using on the perceptual and behavioral constraints that are relevant for each. Overall, the main objective of this paper is to highlight the importance of understanding perceptual issues when evaluating different types of visual simulation in VEs.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Visualization_and_Perception_in_VR_workshop_final_[0].pdf}, department = {Department B{\"u}lthoff}, editor = {M{\"o}ller, R.}, publisher = {Shaker}, address = {Aachen, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bremen, Germany}, event_name = {10. Workshop Sichtsysteme: Visualisierung in der Simulationstechnik}, language = {en}, ISBN = {978-3-8322-6684-4}, author = {Campos, JL and Nusseck, H-G and Wallraven, C and Mohler, BJ and B{\"u}lthoff, HH} } @Inproceedings { 4119, title = {From Isovists via Mental Representations to Behaviour: First Steps Toward Closing the Causal Chain}, journal = {Proceedings of Space Syntax and Spatial Cognition Workshop (Spatial Cognition ‘06)}, year = {2007}, month = {9}, pages = {65-80}, abstract = {This study addresses the interrelations between human wayfinding performance, the mental representation of routes, and the geometrical layout of path intersections. The virtual reality based empirical experiment consisted of a route learning and reproduction task and two choice reaction tasks measuring the acquired knowledge of route decision points. In order to relate the recorded behavioural data to the geometry of the environment, a specific adaptation of isovist-based spatial analysis was developed that accounts for directional bias in human spatial perception and representation. Taken together, the applied analyses provided conclusive evidence for correspondences between geometrical properties of environments as captured by isovists and their mental representation.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/isovt_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.space.bartlett.ucl.ac.uk/events/sc06/}, editor = {H{\"o}lscher, C. , R.C. Dalton, A. Turner}, publisher = {Universit{\"a}t Bremen}, address = {Bremen, Germany}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bremen, Germany}, event_name = {Space Syntax and Spatial Cognition Workshop (Spatial Cognition '06)}, language = {en}, ISBN = {978-3-88722-691-7}, author = {Meilinger, T and Franz, G and B{\"u}lthoff, HH} } @Inproceedings { 5497, title = {Perception of Prominence Intensity in audio-visual Speech}, year = {2007}, month = {9}, pages = {1-6}, abstract = {Multimodal prosody carries a wide variety of information Here, we investigated the roles of visual and the auditory information in the production and perception of different emphasis intensities. In a series of video recordings, the intensity, location, and syntactic category of the emphasized word were varied. Physical analyses demonstrated that each speaker produced different emphasis intensities, with a high degree of individual variation in information distribution. In the first psychophysical experiment, observers easily distinguished between the different intensities. Interestingly, the pattern of perceived intensity was remarkably similar across speakers, despite the individual variations in the use of different visual and acoustic modalities. The second experiment presented the recordings visually, acoustically, and audiovisually. Overall, while the audio only condition was very similar to the audiovisual condition, there was a clear influence of visual information. Weak visual information lead to a weaker audiovisual intensity, while stong visual information enhanced audiovisual intensity.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/AVSP-2007-Nusseck.pdf}, department = {Department B{\"u}lthoff}, editor = {Vroomem , J. , M. Swerts, E. Krahmer}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Hilvarenbeek, Netherlands}, event_name = {International Conference on Auditory-Visual Speech Processing 2007 (AVSP2007)}, language = {en}, author = {Nusseck, M and Cunningham, DW and Ruiter, JPD and B{\"u}lthoff, HH} } @Inproceedings { 4717, title = {Control of a Lateral Helicopter Sidestep Maneuver on an Anthropomorphic Robot}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2007)}, year = {2007}, month = {8}, pages = {1-8}, abstract = {Our society relies more and more on flight simulation for pilot training to enhance safety and reduce costs. But to meet the highest level of general technical requirements for simulators set forth by the FAA and EASA requires high-cost equipment. To make simulator use more accessible, reduced costs might be achieved with novel simulator designs and/or through research to improve the performance of existing designs. This report explores the use of such a novel design, based on an anthropomorphic robot arm to reproduce an experiment designed to evaluate flight simulator motion requirement for helicopter pilot training. Results compare promisingly well to those from a large, high-performance facility where the original work was performed.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Beykirch2007_4717[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2007-6801}, publisher = {American Institute of Aeronautics and Astronautics}, address = {Reston, VA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Hilton Head, SC, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference and Exhibit 2007}, language = {en}, ISBN = {978-1-62410-160-1}, DOI = {10.2514/6.2007-6801}, author = {Beykirch, K and Nieuwenhuizen, FM and Teufel, HJ and Nusseck, H-G and Butler, JS and B{\"u}lthoff, HH} } @Inproceedings { 4660, title = {Identification of Pilot Control Behavior in a Roll-Lateral Helicopter Hover Task}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2007)}, year = {2007}, month = {8}, pages = {1-11}, abstract = {This paper focuses on the influence of different forms of motion feedback on the per- ception and control behavior of pilots in a roll-lateral helicopter hover task. To identify this influence, a combined target-following and disturbance-rejection task is carried out where the motion feedback is varied. The participants perform the control task with roll motion only, lateral motion only, combined roll-lateral motion, or with no motion. A cy- bernetic approach is taken to identify multi-loop pilot describing functions and estimate the parameters of a pilot model. Results show that participants perform significantly bet- ter at the control task with feedback of combined roll-lateral motion, and decrease their control activity. For the condition with feedback of roll motion a similar trend is observed. This is explained through the increased amount of information present in the inner roll stabilization loop.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Nieuwenhuizen2007_4660[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2007-6799}, publisher = {American Institute of Aeronautics and Astronautics}, address = {Reston, VA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {AIAA-2007-6799}, event_place = {Hilton Head, SC, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference and Exhibit 2007}, language = {en}, ISBN = {978-1-62410-160-1}, DOI = {10.2514/6.2007-6799}, author = {Nieuwenhuizen, FM and Beykirch, K and Mulder, M and B{\"u}lthoff, HH} } @Inproceedings { 4512, title = {MPI Motion Simulator: Development and Analysis of a Novel Motion Simulator}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2007)}, year = {2007}, month = {8}, pages = {1-11}, abstract = {This paper discusses the technical issues that were required to adapt a KUKA Robocoaster for use as a real-time motion simulator. Within this context, the paper addresses the physical modifications and the software control structure that were needed to have a flexible and safe experimental setup. It also addresses the delays and transfer function of the system. The paper is divided into two sections. The first section describes the control and safety structures of the MPI Motion Simulator. The second section shows measurements of latencies and frequency responses of the motion simulator. The results show that the frequency responses of the MPI Motion Simulator compare favorably with high-end Stewart Platforms, and therefore demonstrate the suitability of robot-based motion simulators for flight simulation.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Teufel2007_4512[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2007-6476}, publisher = {American Institute of Aeronautics and Astronautics}, address = {Reston, VA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Hilton Head, SC, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference and Exhibit 2007}, language = {en}, ISBN = {978-1-62410-160-1}, DOI = {10.2514/6.2007-6476}, author = {Teufel, HJ and Nusseck, H-G and Beykirch, KA and Butler, JS and Kerger, M and B{\"u}lthoff, HH} } @Inproceedings { 4439, title = {Orientation Specificity in Long-Term-Memory for Environmental Spaces}, journal = {Proceedings of the 29th Annual Conference of the Cognitive Science Society (CogSci 2007)}, year = {2007}, month = {8}, pages = {479-484}, abstract = {This study examined orientation specificity in long-term human memory for environmental spaces. Twenty participants learned an immersive virtual environment by walking a multi-segment route in one direction. The environment consisted of seven corridors within which target objects were located. In the testing phase, participants were teleported to different locations in the environment and were asked to identify their location and heading and then point towards previously learned targets. As predicted by viewdependent theory, participants pointed more accurately when oriented in the direction in which they originally learned each corridor. No support was found for a global reference direction underlying the memory of the whole layout or for an exclusive orientation-independent memory. We propose a ''network of reference frames'' theory to integrate elements of the different theoretical positions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/orientation\%20specificity\%20in\%20environmental\%20spaces\%20final_4439[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://csjarchive.cogsci.rpi.edu/proceedings/2007/}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Nashville, TN, USA}, event_name = {29th Annual Conference of the Cognitive Science Society (CogSci 2007)}, language = {en}, ISBN = {978-1-605-60507-4}, author = {Meilinger, T and Riecke, BE and B{\"u}lthoff, HH} } @Inproceedings { 4427, title = {The role of visual cues and whole-body rotations in helicopter hovering control}, journal = {Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit (AIAA 2007)}, year = {2007}, month = {8}, pages = {1-13}, abstract = {Helicopters in flight are unstable, much like an inverse pendulum, and hovering at one spot requires the pilot to do a considerable amount of active control. To date, it is still under discussion which sensory cues helicopter pilots use for this stabilization task, and how these cues are combined. There are several sensory cues a pilot might use for stabilizing a helicopter (hovering at a target spot). The horizon provides visual information for the orientation of the helicopter in pitch and roll. Optic flow provided by movement of visual features in the observer’s view during self-motion can tell the observer about translations and rotations. Apart from vision, pilots can also use force cues of self-motion. Rotations and accelerations of the head can be detected by the vestibular system in the inner ear, and body accelerations are measured by pressure sensors in the skin and by proprioceptive sensors. Here we investigated how cues from different sensory modalities (visual cues and body cues) are used when humans stabilize a simulated helicopter at a target location in a closed perception-action loop.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Berger_AIAA-2007-6798-final_4427[1].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://arc.aiaa.org/doi/abs/10.2514/6.2007-6798}, publisher = {American Institute of Aeronautics and Astronautics}, address = {Reston, VA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Hilton Head, SC, USA}, event_name = {AIAA Modeling and Simulation Technologies Conference and Exhibit 2007}, language = {en}, ISBN = {978-1-62410-160-1}, DOI = {10.2514/6.2007-6798}, author = {Berger, DR and Terzibas, C and Beykirch, K and B{\"u}lthoff, HH} } @Inproceedings { 4544, title = {Gait parameters while walking in a head-mounted display virtual environment and the real world}, journal = {Proceedings of the 13th Eurographics Symposium on Virtual Environments and 10th Immersive Projection Technology Workshop (IPT-EGVE 2007)}, year = {2007}, month = {7}, pages = {85-88}, abstract = {Full-body motion tracking data was collected for six subjects during free walking. Each participant was asked to walk to a previously seen target under four experimental conditions: eyes closed within the real world, eyes closed wearing a head-mounted display (HMD), eyes open in the real world, and eyes open wearing a HMD. We report three gait parameters for each of these four conditions: stride length, walking velocity, and head-trunk angle. This data reveals that these gait parameters within a HMD virtual environment (VE) are different than those in the real world. A person wearing a HMD and backpack walks slower, and takes a shorter stride length than they do in a comparable real world condition. In addition, head-trunk angle while walking to a target on the ground plane is lowest when walking with eyes open in a HMD VE.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Final_EGVR2007_4544[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://nguyendangbinh.org/Proceedings/IPT-EGVE/2007/publications.html}, editor = {Fr{\"o}hlich, B. , R. Blach, R. van Liere}, publisher = {Eurographics Association}, address = {Aire-la-Ville, Switzerland}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Weimar, Germany}, event_name = {13th Eurographics Symposium on Virtual Environments and 10th Immersive Projection Technology Workshop (IPT-EGVE 2007)}, language = {en}, ISBN = {978-1-568-81400-1}, author = {Mohler, B and Campos, J and Weyel, M and B{\"u}lthoff, HH} } @Inproceedings { 4597, title = {Perception and prediction of simple object interactions}, journal = {Proceedings of the 4th Symposium on Applied Perception in Graphics and Visualization (APGV‘07)}, year = {2007}, month = {7}, pages = {27-34}, abstract = {For humans, it is useful to be able to visually detect an object's physical properties. One potentially important source of information is the way the object moves and interacts with other objects in the environment. Here, we use computer simulations of a virtual ball bouncing on a horizontal plane to study the correspondence between our ability to estimate the ball's elasticity and to predict its future path. Three experiments were conducted to address (1) perception of the ball's elasticity, (2) interaction with the ball, and (3) prediction of its trajectory. The results suggest that different strategies and information sources are used for passive perception versus actively predicting future behavior.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv07-27_4597[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.de/}, editor = {Wallraven, C. , V. Sundstedt}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {4th Symposium on Applied Perception in Graphics and Visualization (APGV 2007)}, language = {en}, ISBN = {978-1-59593-670-7}, DOI = {10.1145/1272582.1272587}, author = {Nusseck, M and Lagarde, J and Bardy, B and Fleming, R and B{\"u}lthoff, HH} } @Inproceedings { 4465, title = {Psychophysical investigation of facial expressions using computer animated faces}, journal = {Proceedings of the 4th Symposium on Applied Perception in Graphics and Visualization (APGV‘07)}, year = {2007}, month = {7}, pages = {11-18}, abstract = {The human face is capable of producing a large variety of facial expressions that supply important information for communication. As was shown in previous studies using unmanipulated video sequences, movements of single regions like mouth, eyes, and eyebrows as well as rigid head motion play a decisive role in the recognition of conversational facial expressions. Here, flexible but at the same time realistic computer animated faces were used to investigate the spatiotemporal coaction of facial movements systematically. For three psychophysical experiments, spatiotemporal properties were manipulated in a highly controlled manner. First, single regions (mouth, eyes, and eyebrows) of a computer animated face performing seven basic facial expressions were selected. These single regions, as well as combinations of these regions, were animated for each of the seven chosen facial expressions. Participants were then asked to recognize these animated expressions in the experiments. The findings show that the animated avatar in general is a useful tool for the investigation of facial expressions, although improvements have to be made to reach a higher recognition accuracy of certain expressions. Furthermore, the results shed light on the importance and interplay of individual facial regions for recognition. With this knowledge the perceptual quality of computer animations can be improved in order to reach a higher level of realism and effectiveness.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv07-11_4465[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv07/}, editor = {Wallraven, C. , V. Sundstedt}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {4th Symposium on Applied Perception in Graphics and Visualization (APGV 2007)}, language = {en}, ISBN = {978-1-59593-670-7}, DOI = {10.1145/1272582.1272585}, author = {Griesser, RT and Cunningham, DW and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 4463, title = {Psychophysics for perception of (in)determinate art}, journal = {Proceedings of the 4th Symposium on Applied Perception in Graphics and Visualization (APGV‘07)}, year = {2007}, month = {7}, pages = {115-122}, abstract = {The question of how humans perceive art and how the sensory percept is endowed with aesthetics by the human brain has continued to fascinate psychologists and artists alike. It seems, for example, rather easy for us to classify a work of art as either ''abstract'' or ''representational''. The artist Robert Pepperell recently has produced a series of paintings that seek to defy this classification: his goal was to convey ''indeterminancy'' in these paintings - scenes that at first glance look like they contain an object or belong to a certain genre but that upon closer examination escape a definite determination of their contents. Here, we report results from several psychophysical experiments using these artworks as stimuli, which seek to shed light on the perceptual processing of the degree of abstraction in images. More specifically, the task in these experiments was to categorize a briefly shown image as ''abstract'' or ''representational''. Stimuli included Pepperell‘s paintings each of which was paired with a similar representational work of art from several periods and several artistic genres. The results provide insights into the visual processes determining our perception of art and can also function as a ''objective'' validation for the intentions of the artist.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv07-115_4463[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv07/}, editor = {Wallraven, C. , V. Sundstedt}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {4th Symposium on Applied Perception in Graphics and Visualization (APGV 2007)}, language = {en}, ISBN = {978-1-59593-670-7}, DOI = {10.1145/1272582.1272605}, author = {Wallraven, C and Kaulard, K and K{\"u}rner, C and Pepperell, R and B{\"u}lthoff, HH} } @Inproceedings { 4464, title = {Using 3D computer graphics for perception: The role of local and global information in face processing}, journal = {Proceedings of the 4th Symposium on Applied Perception in Graphics and Visualization (APGV‘07)}, year = {2007}, month = {7}, pages = {19-26}, abstract = {Everyday life requires us to recognize faces under transient changes in pose, expression and lighting conditions. Despite this, humans are adept at recognizing familiar faces. In this study, we focused on determining the types of information human observers use to recognize faces across variations in viewpoint. Of specific interest was whether holistic information is used exclusively, or whether the local information contained in facial parts (featural or component information), as well as their spatial relationships (configural information) is also encoded. A rigorous study investigating this question has not previously been possible, as the generation of a suitable set of stimuli using standard image manipulation techniques was not feasible. A 3D database of faces that have been processed to extract morphable models (Blanz \& Vetter, 1999) allows us to generate such stimuli efficiently and with a high degree of control over display parameters. Three experiments were conducted, modeled after the inter-extra-ortho experiments by B{\"u}lthoff \& Edelman, 1992. The first experiment served as a baseline for the subsequent two experiments. Ten face-stimuli were presented from a frontal view and from a 45\(^{\circ}\) side view. At test, they had to be recognized among ten distractor faces shown from different viewpoints. We found systematic effects of viewpoint, in that the recognition performance increased as the angle between the learned view and the tested view decreased. This finding is consistent with face processing models based on 2D-view interpolation. Experiments 2 and 3 were the same as Experiment 1 expect for the fact that in the testing phase, the faces were presented scrambled or blurred. Scrambling was used to isolate featural from configural information. Blurring was used to provide stimuli in which local featural information was reduced. The results demonstrated that human observers are capable of recognizing faces across different viewpoints on the sole basis of isolated featural information and of isolated configural information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv07-19_4464[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv07/}, editor = {Wallraven, C. , V. Sundstedt}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {4th Symposium on Applied Perception in Graphics and Visualization (APGV 2007)}, language = {en}, ISBN = {978-1-59593-670-7}, DOI = {10.1145/1272582.1272586}, author = {Schwaninger, A and Schumacher, S and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 4466, title = {In the Eye of the Beholder: Perception of Indeterminate Art}, journal = {Computational Aesthetics 2007: Eurographics Workshop on Computational Aesthetics in Graphics, Visualization and Imaging (CAe‘07)}, year = {2007}, month = {6}, pages = {121-128}, abstract = {How do we interpret an object - a scene - a painting? Perception research and art illuminate from different angles how the vast amount of information in our visually perceived environment is processed by the viewer to form a coherent and consistent interpretation of the world. Using drawings and paintings by the artist Robert Pepperell, this work attempts to connect these different world views. Pepperell's paintings at first glance seem to be a baroque fresco, an expressionist still-life, or a cubist collage; taking a closer look, however, this concrete interpretation vanishes and we are left with an indeterminate painting. Using psychophysical experiments and eye tracking measures, in this work we seek to illuminate the visual processing of information in Pepperell's paintings. More specifically, we will investigate how the pattern of fixations - the loci of interest - change as a function of the task (''What is depicted in this scene?'' vs. ''Does this image contain people?'') and of the image content. The interpretation of the experimental results in the context of perceptual research will give first insights into the perception of (indeterminate) art. Conversely, the results are also relevant for art, as they provide a kind of perceptual, measurable ''validation'' of the artist's intentions.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/CAe-2007-Wallraven.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.eg.org/EG/DL/WS/COMPAESTH/COMPAESTH07}, editor = {Cunningham, D. W., G. W. Meyer, L. Neumann, A. Dunning, R. Paricio}, publisher = {Eurographics Association}, address = {Aire-la-Ville, Switzerland}, booktitle = {Computational aesthetics 2007}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Banff, Alberta, Canada}, event_name = {Eurographics Workshop on Computational Aesthetics in Graphics, Visualization and Imaging (CAe '07)}, language = {en}, ISBN = {978-3-905673-43-2}, DOI = {10.2312/COMPAESTH/COMPAESTH07/121-128}, author = {Wallraven, C and Kaulard, K and K{\"u}rner, C and Pepperell, R and B{\"u}lthoff, HH} } @Inproceedings { WallravenB2007, title = {Object Recognition in Humans and Machines}, year = {2007}, pages = {89-104}, abstract = {The question of how humans learn, represent and recognize objects has been one of the core questions in cognitive research. With the advent of the field of computer vision — most notably through the seminal work of David Marr — it seemed that the solution lay in a three-dimensional (3D) reconstruction of the environment (Marr 1982, see also one of the first computer vision systems built by Roberts et al. 1965). The success of this approach, however, was limited both in terms of explaining experimental results emerging from cognitive research as well as in enabling computer systems to recognize objects with a performance similar to humans.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/Wallraven_ObjRec_Bookch_2007.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/978-4-431-73018-7/\#section=33441\&page=3\&locus=0}, editor = {Osaka, N. , I. Rentschler, I. Biederman}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Object Recognition, Attention, and Action}, event_place = {Kyoto, Japan}, event_name = {International Workshop on Object Recognition, Attention, and Action 2004}, ISBN = {978-4-431-73018-7}, DOI = {10.1007/978-4-431-73019-4_7}, author = {Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 4116, title = {Visual Vestibular Interactions for Self Motion Estimation}, journal = {Proceedings of the Driving Simulation Conference Europe (DSC Europe 2006)}, year = {2006}, month = {10}, pages = {1-10}, abstract = {Accurate perception of self-motion through cluttered environments involves a coordinated set of sensorimotor processes that encode and compare information from visual, vestibular, proprioceptive, motor-corollary, and cognitive inputs. Our goal was to investigate the visual and vestibular cues to the direction of linear self-motion (heading direction). In the vestibular experiment, blindfolded participants were given two distinct forward linear translations, using a Stewart Platform, with identical acceleration profiles. One motion was a standard heading direction, while the test heading was randomly varied using the method of constant stimuli. The participants judged in which interval they moved further towards the right. In the visual-alone condition, participants were presented with two intervals of radial optic flow stimuli and judged which of the two intervals represented a pattern of optic flow consistent with more rightward self-motion. From participants’ responses, we compute psychometric functions fo r both experiments, from which we can calculate the participant’s uncertainty in heading direction estimates.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/DSC_2006_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dsc-europe.inrets.fr/}, publisher = {Institut National de Recherche sur les Transports et Leur S{\'e}curit{\'e}}, address = {Arcueil, France}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Paris, France}, event_name = {Driving Simulation Conference Europe (DSC Europe 2006)}, language = {en}, ISBN = {2-85782-641-9}, author = {Butler, JS and Smith, ST and Beykirch, K and B{\"u}lthoff, HH} } @Inproceedings { 3995, title = {Categorization of natural scenes: local vs. global information}, journal = {Proceedings of the 3rd Symposium on Applied Perception in Graphics and Visualization (APGV06)}, year = {2006}, month = {7}, pages = {33-40}, abstract = {Understanding the robustness and rapidness of human scene categorization has been a focus of investigation in the cognitive sciences over the last decades. At the same time, progress in the area of image understanding has prompted computer vision researchers to design computational systems that are capable of automatic scene categorization. Despite these efforts, a framework describing the processes underlying human scene categorization that would enable efficient computer vision systems is still missing. In this study, we present both psychophysical and computational experiments that aim to make a further step in this direction by investigating the processing of local and global information in scene categorization. In a set of human experiments, categorization performance is tested when only local or only global image information is present. Our results suggest that humans rely on local, region-based information as much as on global, configural information. In addition, humans seem to integrate both types of information for intact scene categorization. In a set of computational experiments, human performance is compared to two state-of-the-art computer vision approaches that model either local or global information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/VogSchWalBue2006_3995[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv06/}, editor = {Spencer, S. N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, MA, USA}, event_name = {3rd Symposium on Applied Perception in Graphics and Visualization (APGV 2006)}, language = {en}, ISBN = {1-59593-429-4}, DOI = {10.1145/1140491.1140498}, author = {Vogel, J and Schwaninger, A and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 4047, title = {Characterizing Perceptual Differences Due to Haptic Exploratory Procedures: An MDS Approach}, journal = {Proceedings of the EuroHaptics 2006 International Conference (EH 2006)}, year = {2006}, month = {7}, pages = {11-19}, abstract = {Previous work in real and virtual settings have shown that the way in which we interact with objects critically influences their perceptual representation. This paper provides new, quantitative evidence that the exploratory procedure used in haptic interaction with a set of objects changes the way they are represented in the brain. Subjects rated similarity on a set of nine novel, 3D objects after either following their contours, laterally rubbing their centres, gripping them, or sequentially touching their tips. A multidimensional scaling (MDS) technique was used to analyze the similarity data. The analysis showed that subjects were able to recover the topology of the input parameter space and perceived its dimensions as shape and texture. A large amount of variability in the way subjects weighted dimensions was found for all procedures except lateral motion, in which the texture dimension strongly dominated shape. The results provide clear evidence that using different procedures changes the relative perceptual weighting of object properties, but that even when exploratory procedures are strictly controlled, there can be large individual differences in the weightings of object properties. Our MDS-based analysis framework can be used to visualize and quantify perception under various real-world scenarios. In addition, this paper discusses its use as a benchmarking and validation paradigm for haptic rendering and virtual environments in general.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/cooke_eurohaptics_2006_4047[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://lsc.univ-evry.fr/\verb=~=eurohaptics/index.shtml}, editor = {Kheddar, A. , B. Bayart}, address = {Paris, France}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Paris, France}, event_name = {EuroHaptics International Conference (EH 2006)}, language = {en}, author = {Cooke, T and Wallraven, C and B{\"u}lthoff, H} } @Inproceedings { 3992, title = {Semantic 3D motion retargeting for facial animation}, journal = {Proceedings of the 3rd Symposium on Applied Perception in Graphics and Visualization (APGV06)}, year = {2006}, month = {7}, pages = {77-84}, abstract = {We present a system for realistic facial animation that decomposes facial Motion Capture data into semantically meaningful motion channels based on the Facial Action Coding System. A captured performance is retargeted onto a morphable 3D face model based on a semantically corresponding set of 3D scans. The resulting facial animation reveals a high level of realism by combining the high spatial resolution of a 3D scanner with the high temporal accuracy of motion capture data that accounts for subtle facial movements with sparse measurements. Such an animation system allows us to systematically investigate human perception of moving faces. It offers control over many aspects of the appearance of a dynamic face, while utilizing as much measured data as possible to avoid artistic biases. Using our animation system, we report results of an experiment that investigates the perceived naturalness of facial motion in a preference task. For expressions with small amounts of headmotion, we find a benefit for our part-based generative animation system that is capable of local animation over an example-based approach that deforms the whole face at once.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv06-77_3992[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv06/}, editor = {Spencer, S. N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, MA, USA}, event_name = {3rd Symposium on Applied Perception in Graphics and Visualization (APGV 2006)}, language = {en}, ISBN = {1-59593-429-4}, DOI = {10.1145/1140491.1140508}, author = {Curio, C and Breidt, M and Kleiner, M and Vuong, QC and Giese, MA and B{\"u}lthoff, HH} } @Inproceedings { 3984, title = {The Evaluation of Stylized Facial Expressions}, journal = {Proceedings of the 3rd Symposium on Applied Perception in Graphics and Visualization (APGV06)}, year = {2006}, month = {7}, pages = {85-92}, abstract = {Stylized rendering aims to abstract information in an image making it useful not only for artistic but also for visualization purposes. Recent advances in computer graphics techniques have made it possible to render many varieties of stylized imagery efficiently. So far, however, few attempts have been made to characterize the perceptual impact and effectiveness of stylization. In this paper, we report several experiments that evaluate three different stylization techniques in the context of dynamic facial expressions. Going beyond the usual questionnaire approach, the experiments compare the techniques according to several criteria ranging from introspective measures (subjective preference) to task-dependent measures (recognizability, intensity). Our results shed light on how stylization of image contents affects the perception and subjective evaluation of facial expressions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/p85-wallraven_3984[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.apgv.org/archive/apgv06/}, editor = {Spencer, S. N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, Mass., USA}, event_name = {3rd Symposium on Applied Perception in Graphics and Visualization (APGV 2006)}, language = {en}, ISBN = {1-59593-429-4}, DOI = {10.1145/1140491.1140509}, author = {Wallraven, C and Fischer, J and Cunningham, DW and Bartz, D and B{\"u}lthoff, HH} } @Inproceedings { 3855, title = {Working memory in wayfinding: a dual task experiment in a virtual city}, journal = {Proceedings of the 28th Annual Conference of the Cognitive Science Society (CogSci 2006)}, year = {2006}, month = {7}, pages = {585-590}, abstract = {This study examines the working memory systems involved in human wayfinding. In the learning phase 24 participants learned two routes in a novel photorealistic virtual environment displayed on a 220\(^{\circ}\) screen, while they were disrupted by a visual, a spatial, a verbal or - in a control group - no secondary task. In the following wayfinding phase the participants had to find and to ''virtually walk'' the two routes again. During this wayfinding phase a number of dependent measures were recorded. We show that encoding wayfinding knowledge interfered with the verbal and with the spatial secondary task. These interferences were even stronger than the interference of wayfinding knowledge with the visual secondary task. These findings are consistent with a dual coding approach of wayfinding knowledge.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/working_memory_in_wayfinding_3855[1].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.cogsci.rpi.edu/\verb=~=rsun/cogsci2006/}, editor = {Sun, R.}, publisher = {Curran}, address = {Red Hook, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Vancouver, BC, Canada}, event_name = {28th Annual Conference of the Cognitive Science Society (CogSci 2006)}, language = {en}, ISBN = {978-1-605-60500-5}, author = {Meilinger, T and Knauff, M and B{\"u}lthoff, HH} } @Inproceedings { 3876, title = {Measuring the Discernability of Virtual Objects in Conventional and Stylized Augmented Reality}, journal = {Proceedings of the 12. Eurographics Symposium on Virtual Environments (EGVE 06)}, year = {2006}, month = {5}, pages = {53-61}, abstract = {In augmented reality, virtual graphical objects are overlaid over the real environment of the observer. Conventional augmented reality systems normally use standard real-time rendering methods for generating the graphical representations of virtual objects. These renderings contain the typical artifacts of computer generated graphics, e.g., aliasing caused by the rasterization process and unrealistic, manually configured illumination models. Due to these artifacts, virtual objects look artifical and can easily be distinguished from the real environment. A different approach to generating augmented reality images is the basis of stylized augmented reality [FBS05c]. Here, similar types of artistic or illustrative stylization are applied to the virtual objects and the camera image of the real enviroment. Therefore, real and virtual image elements look significantly more similar and are less distinguishable from each other. In this paper, we present the results of a psychophysical study on the effectiveness of stylized augmented reality. In this study, a number of participants were asked to decide whether objects shown in images of augmented reality scenes are virtual or real. Conventionally rendered as well as stylized augmented reality images and short video clips were presented to the participants. The correctness of the participants' responses and their reaction times were recorded. The results of our study show that an equalized level of realism is achieved by using stylized augmented reality, i.e., that it is significantly more difficult to distinguish virtual objects from real objects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Fischer-2006-Measuring_3876[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.adetti.pt/events/EGVE06/}, editor = {Hubbold, R.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lisboa, Portugal}, event_name = {12. Eurographics Symposium on Virtual Environments (EGVE 06)}, language = {en}, DOI = {10.2312/EGVE/EGVE06/053-061}, author = {Fischer, J and Cunningham, D and Bartz, D and Wallraven, C and B{\"u}lthoff, HH and Strasser, W} } @Inproceedings { 3913, title = {A psychophysical examination of Swinging Rooms, Cylindrical Virtual Reality setups, and characteristic trajectories}, journal = {Proceedings of the IEEE Virtual Reality Conference (VR 2006)}, year = {2006}, month = {3}, pages = {111-118}, abstract = {Virtual Reality (VR) is increasingly being used in industry, medicine, entertainment, education, and research. It is generally critical that the VR setups produce behavior that closely resembles real world behavior. One part of any task is the ability to control our posture. Since postural control is well studied in the real world and is known to be strongly influenced by visual information, it is an ideal metric for examining the behavioral fidelity of VR setups. Moreover, VR-based experiments on postural control can provide fundamental new insights into human perception and cognition. Here, we employ the ''swinging room paradigm'' to validate a specific VR setup. Furthermore, we systematically examined a larger range of room oscillations than previously studied in any single setup. We also introduce several new methods and analyses that were specifically designed to optimize the detection of synchronous swinging between the observer and the virtual room. The results show that the VR setup has a very high behavioral fidelity and that increases in swinging room amplitude continue to produce increases in body sway even at very large room displacements (+/- 80 cm). Finally, the combination of new methods proved to be a very robust, reliable, and sensitive way of measuring body sway.}, department = {Department B{\"u}lthoff}, web_url = {http://conferences.computer.org/vr/2006/}, publisher = {IEEE Operations Center}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Alexandria, VA, USA}, event_name = {IEEE Virtual Reality Conference 2006}, language = {en}, ISBN = {1-4244-0224-7}, DOI = {10.1109/VR.2006.14}, author = {Cunningham, DW and Nusseck, H-G and Teufel, H and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 3489, title = {Measuring Vection in a Large Screen Virtual Environment}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {10}, pages = {103-103}, abstract = {This paper describes the use of a large screen virtual environment to induce the perception of translational and rotational self-motion. We explore two aspects of this problem. Our first study investigates how the level of visual immersion (seeing a reference frame) affects subjective measures of vection. For visual patterns consistent with translation, self-reported subjective measures of self-motion were increased when the floor and ceiling were visible outside of the projection area. When the visual patterns indicated rotation, the strength of the subjective experience of circular vection was unaffected by whether or not the floor and ceiling were visible. We also found that circular vection induced by the large screen display was reported subjectively more compelling than translational vection. The second study we present describes a novel way in which to measure the effects of displays intended to produce a sense of vection. It is known that people unintentionally drift forward if asked to run in place while blindfolded and that adaptations involving perceived linear self-motion can change the rate of drift. We showed for the first time that there is a lateral drift following perceived rotational self-motion and we added to the empirical data associated with the drift effect for translational self-motion by exploring the condition in which the only self-motion cues are visual.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/mohler-etal-apgv-2005_3489[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080421}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {SIGGRAPH}, event_place = {La Coruna, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080421}, author = {Mohler, BJ and Riecke, BE and Thompson, WB and B{\"u}lthoff, HH} } @Inproceedings { 3466, title = {Influence of Auditory Cues on the visually-induced Self-Motion Illusion (Circular Vection) in Virtual Reality}, journal = {Proceedings of 8th international workshop on Presence 2005}, year = {2005}, month = {9}, pages = {49-57}, abstract = {This study investigated whether the visually induced selfmotion illusion (“circular vection”) can be enhanced by adding a matching auditory cue (the sound of a fountain that is also visible in the visual stimulus). Twenty observers viewed rotating photorealistic pictures of a market place projected onto a curved projection screen (FOV: 54\(^{\circ}\)x45\(^{\circ}\)). Three conditions were randomized in a repeated measures within-subject design: No sound, mono sound, and spatialized sound using a generic head-related transfer function (HRTF). Adding mono sound increased convincingness ratings marginally, but did not affect any of the other measures of vection or presence. Spatializing the fountain sound, however, improved vection (convincingness and vection buildup time) and presence ratings significantly. Note that facilitation was found even though the visual stimulus was of high quality and realism, and known to be a powerful vection-inducing stimulus. Thus, HRTF-based auralization using headphones can be employed to improve visual VR simulations both in terms of self-motion perception and overall presence.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Riecke__05_paper4Presence2005_Influence_of_Auditory_Cues_on_the_visually-induced_Self-Motion_Illusion_-Circular_Vection-_in_Virtual_Reality_3466[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.cs.ucl.ac.uk/research/vr/Projects/Presencia/Presence2005/}, editor = {Slater, M.}, publisher = {University College London}, address = {London, UK}, booktitle = {Presence 2005}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {London, UK}, event_name = {Eighth Annual International Workshop on Presence}, language = {en}, ISBN = {0-9551232-0-8}, author = {Riecke, BE and Schulte-Pelkum, J and Caniard, F and B{\"u}lthoff, HH} } @Inproceedings { 3473, title = {A similarity-based approach to perceptual feature validation}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {8}, pages = {59-66}, abstract = {Which object properties matter most in human perception may well vary according to sensory modality, an important consideration for the design of multimodal interfaces. In this study, we present a similarity-based method for comparing the perceptual importance of object properties across modalities and show how it can also be used to perceptually validate computational measures of object properties. Similarity measures for a set of three-dimensional (3D) objects varying in shape and texture were gathered from humans in two modalities (vision and touch) and derived from a set of standard 2D and 3D computational measures (image and mesh subtraction, object perimeter, curvature, Gabor jet filter responses, and the Visual Difference Predictor (VDP)). Multidimensional scaling (MDS) was then performed on the similarity data to recover configurations of the stimuli in 2D perceptual/computational spaces. These two dimensions corresponded to the two dimensions of variation in the stimulus set: shape and texture. In the human visual space, shape strongly dominated texture. In the human haptic space, shape and texture were weighted roughly equally. Weights varied considerably across subjects in the haptic experiment, indicating that different strategies were used. Maps derived from shape-dominated computational measures provided good fits to the human visual map. No single computational measure provided a satisfactory fit to the map derived from mean human haptic data, though good fits were found for individual subjects; a combination of measures with individually-adjusted weights may be required to model the human haptic similarity judgments. Our method provides a high-level approach to perceptual validation, which can be applied in both unimodal and multimodal interface design.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3473.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080413}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {ACM Special Interest Group on Computer Graphics and Interactive Techniques}, event_place = {A Coruna, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080413}, author = {Cooke, T and Steinke, F and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 2995, title = {Predicting experiential qualities of architecture by its spatial properties}, year = {2005}, month = {8}, pages = {157-166}, abstract = {While experiential qualities of rectangular architectural spaces can be effectively predicted from their proportions and area (Franz, von der Heyde, \& B{\"u}lthoff, 2003), these factors obviously cannot be directly transferred on open-plan indoor spaces. We introduce an approach that relates experiential qualities of arbitrarily shaped architectural spaces to their spatial form using isovists (Benedikt, 1979) that allow to generically describe spatial properties. In an exploratory psychological experiment, 33 characteristic values derived from the isovists were tested on their predictive power on experiential qualities by correlating them with averaged affective appraisals. Thirty-four virtual reality simulated indoor scenes were rated by 2x8 participants using the semantic differential. Particularly measurands capturing the qualities spaciousness, openness, complexity, and order turned out to be effective predictor variables. The findings are discussed in terms of evolutionary and information rate related theories of environmental preferences.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/predicting_experiential_qualities_of_architecture_by_its_spatial_properties_2995[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://info.tuwien.ac.at/iaps2004/}, editor = {Martens, B. , A. G. Keul}, publisher = {Hogrefe}, address = {Cambridge, MA}, booktitle = {Designing social innovation: Planning, building, evaluating}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Wien, Austria}, event_name = {18th International Association for People-Environment Studies (IAPS 2004)}, language = {en}, ISBN = {0-88937-291-8}, author = {Franz, G and von der Heyde, M and B{\"u}lthoff, HH} } @Inproceedings { 3541, title = {Psychophysical evaluation of animated facial expressions}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {8}, pages = {17-24}, abstract = {The human face is capable of producing an astonishing variety of expressions - expressions for which sometimes the smallest difference changes the perceived meaning noticably. Producing realistic-looking facial animations that are able to transport this degree of complexity continues to be a challenging research topic in computer graphics. One important question that remains to be answered is: When are facial animations good enough? Here we present an integrated framework in which psychophysical experiments are used in a first step to systematically evaluate the perceptual quality of computer-generated animations with respect to real-world video sequences. The result of the first experiment is an evaluation of several animation techniques in which we expose specific animation parameters that are important for perceptual fidelity. In a second experiment we then use these benchmarked animations in the context of perceptual research in order to systematically investigate the spatio-temporal characteristics of ex pressions. Using such an integrated approach, we are able to provide insights into facial expressions for both the perceptual and computer graphics community.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/wallraven-etal-apgv-2005_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080405}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {ACM Special Interest Group on Computer Graphics and Interactive Techniq}, event_place = {A Coro{\~n}a, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080405}, author = {Wallraven, C and Breidt, M and Cunningham, D and B{\"u}lthoff, HH} } @Inproceedings { 3450, title = {Recognizing novel deforming objects}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {8}, pages = {158-158}, abstract = {Human visual recognition can be improved with object motion (e.g., faces, Lander and Chuang, 2005; rigid objects, Vuong and Tarr, 2004) This improvement suggests that it is not merely shape information that characterizes an object. Rather, human observers may also represent how shape changes over time for recognition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3450.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080438}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, Tuebingen}, event_place = {A Coruna, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080438}, author = {Chuang, L and Vuong, QC and Thornton, IM and B{\"u}lthoff, HH} } @Inproceedings { 3467, title = {Scene Consistency and Spatial Presence Increase the Sensation of Self-Motion in Virtual Reality}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {8}, pages = {111-118}, abstract = {The illusion of self-motion induced by moving visual stimuli (''vection'') has typically been attributed to low-level, bottom-up perceptual processes. Therefore, past research has focused primarily on examining how physical parameters of the visual stimulus (contrast, number of vertical edges etc.) affect vection. Here, we investigated whether higher-level cognitive and top-down processes - namely global scene consistency and spatial presence - also contribute to the illusion. These factors were indirectly manipulated by presenting either a natural scene (the T{\"u}bingen market place) or various scrambled and thus globally inconsistent versions of the same stimulus. Due to the scene scrambling, the stimulus could no longer be perceived as a consistent 3D scene, which was expected to decrease spatial presence and thus impair vection. Twelve naive observers were asked to indicate the onset, intensity, and convincingness of circular vection induced by rotating visual stimuli presented on a curved projection screen (FOV: 54\(^{\circ}\)x45\(^{\circ}\)). Spatial presence was assessed using presence questionnaires. As predicted, scene scrambling impaired both vection and presence ratings for all dependent measures. Neither type nor severity of scrambling, however, showed any clear effect. The data suggest that higher-level information (the interpretation of the globally consistent stimulus as a 3D scene and stable reference frame) dominated over the low-level (bottom-up) information (more contrast edges in the scrambled stimuli, which are known to facilitate vection). Results suggest a direct relation between spatial presence and self-motion perception. We posit that stimuli depicting globally consistent, naturalistic scenes provide observers with a convincing spatial reference frame for the simulated environment which allows them to feel ''spatially present'' therein. We propose that this, in turn, increases the believability of the visual stimuli as a stable ''scene'' with respect to which visual motion is more likely to be judged as self-motion. We propose that not only low-level, bottom-up factors, but also higher-level factors such as the meaning of the stimulus are relevant for self-motion perception and should thus receive more attention. This work has important implications for both our understanding of selfmotion perception and motion simulator design and applications.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3467.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080422}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {ACM Special Interest Group on Computer Graphics and Interactive Techniques}, event_place = {A Coro{\~n}a, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080422}, author = {Riecke, BE and Schulte-Pelkum, J and Avraamides, M and von der Heyde, M and B{\"u}lthoff, HH} } @Inproceedings { 3492, title = {The role of external features for person recognition}, journal = {Proceedings of the 2nd Symposium on Applied Perception in Graphics and Visualization (APGV‘05)}, year = {2005}, month = {8}, pages = {160-160}, abstract = {Face recognition is a remarkable human skill, as we are able to remember many thousands of faces. A great deal of research has investigated how it is possible to achieve such high levels of performance and what kind of information we encode to reach such a level of proficiency [Bruce and Young 1986]. One important distinction that is made in the literature is the distinction between external and internal facial features. Internal facial features refer to the size and outline of the eyes and mouth and their configuration. External facial features rather denote the shape of the face or the hairstyle associated with a particular face [Ellis et al. 1979]. Here, we explore this issue in the context of motion, an area that has only recently begun to concern face researchers [O'Toole et al. 2002; Knappmeyer et al. 2003]. In our displays avatars were animated to approach the observer in depth. Intuitively internal features are likely to play less of a role when a person is far away. Conversely, external features such as gait and clothing are likely to be more important if the person to recognize is further away.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3492.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1080440}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {ACM Special Interest Group on Computer Graphics and Interactive Techniques}, event_place = {A Coro{\~n}a, Spain}, event_name = {2nd Symposium on Applied Perception in Graphics and Visualization (APGV 2005)}, language = {en}, ISBN = {1-59593-139-2}, DOI = {10.1145/1080402.1080440}, author = {Pilz, K and Thornton, IM and B{\"u}lthoff, HH} } @Inproceedings { 3368, title = {A Comparison of Visual and Haptic Object Representations Based on Similarity}, journal = {Proceedings of the 9th International Conference on Information Visualisation (IV‘05)}, year = {2005}, month = {7}, pages = {33-40}, abstract = {Do we judge similarity between two objects to be the same using touch and vision? We investigated this using psychophysical experiments in which subjects rated the similarity between objects presented either visually or haptically. The stimuli were a family of novel, three-dimensional objects whose microgeometry (''texture'') and macrogeometry (''shape'') were parametrically varied. Multidimensional scaling of the similarity data was used to reconstruct haptic and visual perceptual spaces. For both modalities, a two-dimensional perceptual space was found whose dimensions clearly corresponded to shape and texture. Interestingly, shape dominated in visual space, whereas both shape and texture were important in haptic space. Furthermore, stimuli clusters were observed in this space, suggesting the emergence of category structure based on similarity relationships. The same category boundaries were confirmed in a visual free sorting experiment. This study reveals differences in object processing across modality and demonstrates an approach for analyzing such differences in multisensory visualizations.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3368.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=1509056}, editor = {Clapworthy, G.}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {London, England}, event_name = {9th International Conference on Information Visualisation (IV '05)}, language = {en}, ISBN = {0-7695-2397-8}, DOI = {10.1109/IV.2005.6}, author = {Cooke, T and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 3252, title = {Cognitive Influences on Self-Rotation Perception}, journal = {Proceedings of the 1st International Conference on Augmented Cognition}, year = {2005}, month = {7}, pages = {164-173}, abstract = {In this study we examined the types of information that can influence the perception of upright (yaw) rotations. Specifically, we examined the influence of stimulus magnitude, task-induced attention and awareness of inter-sensory conflicts on the weights of visual and body cues. Participants had to reproduce rotations that were presented as simultaneous physical body turns (via a motion platform) and visual turns displayed as a rotating scene. During the active reproduction stage, conflicts between the body and visual rotations were introduced by means of gain factors. Participants were instructed to reproduce either the visual scene rotation or the body rotation. After each trial participants reported whether or not they had perceived a conflict. We found significant influences of the magnitude of the rotation, attention condition (instruction to reproduce platform or scene rotation), and reported awareness of a sensory conflict during the reproduction phase. Attention had a larger influence on the response of the participants when they noticed a conflict compared to when they did not perceive a conflict. Attention biased their response towards the attended modality. Our results suggest that not only the stimulus characteristics, but also cognitive factors play a role in the estimation of the size of a rotation in an active turn reproduction task.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/berger_augcog2005_3252[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.hci-international.org/index.php?module=conference\&CF_op=view\&CF_id=4}, editor = {Schmorrow, D.D.}, publisher = {Erlbaum}, address = {Mahwah, NJ, USA}, booktitle = {Foundations of augmented cognition 11}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Las Vegas, NV, USA}, event_name = {1st International Conference on Augmented Cognition (HCI International 2005)}, language = {en}, ISBN = {0-8058-5806-7}, author = {Berger, D and von der Heyde, M and B{\"u}lthoff, HH} } @Inproceedings { 2784, title = {Machine Learning Applied to Perception: Decision Images for Classification}, journal = {Advances in Neural Information Processing Systems}, year = {2005}, month = {7}, pages = {1489-1496}, abstract = {We study gender discrimination of human faces using a combination of psychophysical classification and discrimination experiments together with methods from machine learning. We reduce the dimensionality of a set of face images using principal component analysis, and then train a set of linear classifiers on this reduced representation (linear support vector machines (SVMs), relevance vector machines (RVMs), Fisher linear discriminant (FLD), and prototype (prot) classifiers) using human classification data. Because we combine a linear preprocessor with linear classifiers, the entire system acts as a linear classifier, allowing us to visualise the decision-image corresponding to the normal vector of the separating hyperplanes (SH) of each classifier. We predict that the female-to-maleness transition along the normal vector for classifiers closely mimicking human classification (SVM and RVM 1) should be faster than the transition along any other direction. A psychophysical discrimination experiment using the decision images as stimuli is consistent with this prediction.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2784.pdf}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, web_url = {http://nips.cc/Conferences/2004/}, editor = {Saul, L. K. , Y. Weiss, L. Bottou}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Advances in Neural Information Processing Systems 17}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Vancouver, BC, Canada}, event_name = {Eighteenth Annual Conference on Neural Information Processing Systems (NIPS 2004)}, language = {en}, ISBN = {0-262-19534-8}, author = {Wichmann, FA and Graf, ABA and Simoncelli, EP and B{\"u}lthoff, HH and Sch{\"o}lkopf, B} } @Inproceedings { 5979, title = {Human-Centered Fidelity Metrics for Virtual Environment Simulations}, journal = {Full-day tutorial at IEEE Virtual Reality 2005}, year = {2005}, month = {3}, day = {12}, pages = {308-308}, abstract = {It is increasingly important to provide fidelity mecrics for rendered images and interactive virtual environments (VEs) targeting transfer of training in real-world task situations. Computational metrics which aim to predict the degree of fidelity of a rendered image can be based on psychophysical observations. For interactive simulations, psychophysical investigations can be carried out into the degree of similarity between the original and a synthetic simulation. Psychophysics comprises a collection of methods used to conduct non-invasive experiments on humans, the purpose of which is to study mappings between events in an environment and levels of sensory responses to those events. This tutorial will present the techniques and principles towards conducting psychophysical studies, for assessing image quality as well as fidelity of a VE simulation and how results from such studies contribute to VE system design as well as to computational image quality metrics. Methods based on experiments for measuring the perceptual equivalence between a real scene and a computer simulation of the same scene will be reported. These methods are presented through the study of human vision and include using photorealistic computer graphics to depict complex environments and works of art. In addition, physical and psychophysical fidelity issues in the assessment of virtual environments will be emphasised. Specifications for correct matching between the psychophysical characteristics of the displays and the human users’ sensory and motor systems will he discussed as well as some examples of the consequences when systems fail to be physically well matched to their users. Complete experimental cycles will be described from the initial idea and design, to pilot study, experimental redesign, data collection, analysis and post-experiment lessons learned. Examples will include research on spatial orientation in Virtual Reality, assessing fidelity of flight simulators, fidelity of simulation of humans and clothing and measuring perceptual sensitivity to latency. This tutorial requires no fundamental prerequisites. It would help if the attendee had some knowledge of experimental design, and of some personal experience of computer graphics and simulation systems. However, the course will be self-contained.}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=1492813}, editor = {Fr{\"o}hlich, B.}, publisher = {IEEE Computer Society}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bonn, Germany}, event_name = {IEEE Conference on Virtual Reality (VR '05)}, language = {en}, ISBN = {0-7803-8929-8}, DOI = {10.1109/VR.2005.39}, author = {Adelstein, B and B{\"u}lthoff, HH and Cunningham, DW and Mania, K and Mourkoussis, N and Swan, E and Thalmann, N and Troscianko, T} } @Inproceedings { 2904, title = {Towards Lean and Elegant Self-Motion Simulation in Virtual Reality}, journal = {Proceedings of IEEE Virtual Reality 2005}, year = {2005}, month = {3}, pages = {131-138}, abstract = {Despite recent technological advances, convincing self-motion simulation in virtual reality (VR) is difficult to achieve, and users often suffer from motion sickness and/or disorientation in the simulated world. Instead of trying to simulate self-motions with physical realism (as is often done for, e.g., driving or flight simulators), we propose in this paper a perceptually oriented approach towards self-motion simulation. Following this paradigm, we performed a series of psychophysical experiments to determine essential visual, auditory, and vestibular/tactile parameters for an effective and perceptually convincing self-motion simulation. These studies are a first step towards our overall goal of achieving lean and elegant self-motion simulation in virtual reality (VR) without physically moving the observer. In a series of psychophysical experiments about the self-motion illusion (circular vection), we found that (i) vection as well as presence in the simulated environment is increased by a consistent, naturalistic visual scene when compared to a sliced, inconsistent version of the identical scene, (ii) barely noticeable marks on the projection screen can increase vection as well as presence in an unobtrusive manner, (iii) physical vibrations of the observer's seat can enhance the vection illusion, and (iv) spatialized 3D audio cues embedded in the simulated environment increase the sensation of self-motion and presence. We conclude that providing consistent cues about self-motion to multiple sensory modalities can enhance vection, even if physical motion cues are absent. These results yield important implications for the design of lean and elegant self-motion simulators.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2904.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.vr2005.org}, editor = {Fr{\"o}hlich, B.}, publisher = {IEEE Computer Society}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bonn, Germany}, event_name = {IEEE Conference on Virtual Reality (VR '05)}, ISBN = {0-7803-8929-8}, DOI = {10.1109/VR.2005.83}, author = {Riecke, BE and Schulte-Pelkum, J and Caniard, F and B{\"u}lthoff, HH} } @Inproceedings { 3233, title = {Perceiving Simulated Ego-Motions in Virtual Reality: Comparing Large Screen Displays with HMDs}, journal = {Proc. SPIE}, year = {2005}, month = {1}, pages = {344-355}, abstract = {In Virtual Reality, considerable systematic spatial orientation problems frequently occur that do not happen in comparable real-world situations. This study investigated possible origins of these problems by examining the influence of visual field of view (FOV) and type of display device (head-mounted display (HMD) vs. projection screens) on basic human spatial orientation behavior. In Experiment 1, participants had to reproduce traveled distances and to turn specified target angles in a simple virtual environment without any landmarks that was projected onto a 180\(^{\circ}\) half-cylindrical projection screen. As expected, distance reproduction performance showed only small systematic errors. Turning performance, however, was unexpectedly almost perfect (gain=0.97), with negligible systematic errors and minimal variability, which is unprecedented in the literature. In Experiment 2, turning performance was compared between a projection screen (FOV 84\(^{\circ}\)\(\times\)63\(^{\circ}\)), an HMD (40\(^{\circ}\)\(\times\)30\(^{\circ}\)), and blinders (40\(^{\circ}\)\(\times\)30\(^{\circ}\)) that restricted the FOV on the screen. Performance was best with the screen (gain 0.77) and worst with the HMD (gain 0.57). We found a significant difference between blinders (gain 0.73) and HMD, which indicates that different display devices can influence ego-motion perception differentially, even if the physical FOVs are equal. We conclude that the type of display device (HMD vs. curved projection screen) seems to be more critical than the FOV for the perception of ego-rotations. Furthermore, large, curved projection screens yielded better performance than HMDs.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3233.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://spiedigitallibrary.org/proceedings/resource/2/psisdg/5666/1/344_1}, editor = {Rogowitz, B. E., T. N. Pappas and S. J. Daly}, publisher = {SPIE}, address = {Bellingham, WA, USA}, series = {Proc. SPIE, Human Vision and Electronic Imaging X}, booktitle = {Human Vision and Electronic Imaging X}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {San Jose, CA, USA}, event_name = {Electronic Imaging: Science and Technology}, ISBN = {0-8194-5639-X}, DOI = {10.1117/12.610846}, author = {Riecke, BE and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Inproceedings { 3058, title = {Multi-viewpoint video capture for facial perception research}, journal = {Captech 2004 - Workshop on modelling and motion capture techniques for virtual environments}, year = {2004}, month = {12}, pages = {55-60}, abstract = {In order to produce realistic-looking avatars, computer graphics has traditionally relied solely on physical realism. Research on cognitive aspects of face perception, however, can provide insights into how to produce believable and recognizable faces. In this paper, we describe a method for automatically manipulating video recordings of faces. The technique involves the use of a custom-built multi-viewpoint video capture system in combination with head motion tracking and a detailed 3D head shape model. We illustrate how the technique can be employed in studies on dynamic facial expression perception by summarizing the results of two psychophysical studies which provide suggestions for creating recognizable facial expressions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3058.pdf}, department = {Department B{\"u}lthoff}, editor = {Thalmann, N. , M. D. Thalmann}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Zermatt, Switzerland}, event_name = {Workshop on Modelling and Motion Capture Techniques for Virtual Environments (CAPTECH 2004)}, language = {en}, author = {Kleiner, M and Wallraven, C and Breidt, M and Cunningham, DW and B{\"u}lthoff, HH} } @Inproceedings { 2864, title = {Enhancing the Visually Induced Self-Motion Illusion (Vection) under Natural Viewing Conditions in Virtual Reality}, journal = {Proceedings of Presence 2004}, year = {2004}, month = {10}, pages = {125-132}, abstract = {The visually induced illusion of ego-motion (vection) is known to be facilitated by both static fixation points [1] and foreground stimuli that are perceived to be stationary in front of a moving background stimulus [2]. In this study, we found that hardly noticeable marks in the periphery of a projection screen can have similar vection-enhancing effects, even without fixating or suppressing the optokinetic reflex (OKR). Furthermore, vection was facilitated even though the marks had no physical depth separation from the screen. Presence ratings correlated positively with vection, and seemed to be mediated by the ego-motion illusion. Interestingly, the involvement/attention aspect of overall presence was more closely related to vection onset times, whereas spatial presence-related aspects were more tightly related to convincingness ratings. This study yields important implications for both presence theory and motion simulator design and applications, where one often wants to achieve convincing ego-motion simulation without restricting eye movements artificially. SUPPORT: EU grant POEMS-IST-2001-39223 (see www.poems-project.info) and Max Planck Society.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2864.pdf}, department = {Department B{\"u}lthoff}, editor = {Alca{\~n}iz Raya, M.}, publisher = {UPV}, address = {Valencia, Spain}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Valencia, Spain}, event_name = {Seventh Annual International Workshop Presence 2004}, ISBN = {84-97056-49-3}, author = {Riecke, BE and Schulte-Pelkum, J and Avraamides, MN and B{\"u}lthoff, HH} } @Inproceedings { 2791, title = {The Perceptual Influence of Spatiotemporal Noise on the Reconstruction of Shape from Dynamic Occlusion}, journal = {DAGM 2004}, year = {2004}, month = {9}, pages = {407-414}, abstract = {When an object moves, it covers and uncovers texture in the background. This pattern of change is sufficient to define the object’s shape, velocity, relative depth, and degree of transparency, a process called Spatiotemporal Boundary Formation (SBF). We recently proposed a mathematical framework for SBF, where texture transformations are used to recover local edge segments, estimate the figure’s velocity and then reconstruct its shape. The model predicts that SBF should be sensitive to spatiotemporal noise, since the spurious transformations will lead to the recovery of incorrect edge orientations. Here we tested this prediction by adding a patch of dynamic noise (either directly over the figure or a fixed distance away from it). Shape recognition performance in humans decreased to chance levels when noise was placed over the figure but was not affected by noise far away. These results confirm the model’s prediction and also imply that SBF is a local process.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2791.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/k8dqpq3ghuwteyb6/fulltext.pdf}, editor = {Rasmussen, C.E. , H.H. B{\"u}lthoff, M. Giese, B. Sch{\"o}lkopf}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Pattern Recognition}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {26th DAGM Symposium on Pattern Recognition (DAGM 2004)}, ISBN = {978-3-540-22945-2}, DOI = {10.1007/978-3-540-28649-3_50}, author = {Cooke, T and Cunningham, DW and B{\"u}lthoff, HH} } @Inproceedings { 2797, title = {Perceiving translucent materials}, journal = {Proceedings of the 1st Symposium on Applied perception in graphics and visualization (APGV‘04)}, year = {2004}, month = {8}, pages = {127-134}, abstract = {Many common materials, including fruit, wax and human skin, are somewhat translucent. What makes an object look translucent or opaque? Here we use a recently developed computer graphics model of subsurface light transport [Jensen, et al., 2001] to study the factors that determine perceived translucency. We discuss how physical factors, such as light-source direction can alter the apparent translucency of an object, finding that objects are perceived to be more translucent when illuminated from behind than in front. We also study the role of a range of image cues, including colour, contrast and blur, in the perception of translucency. Although we learn a lot about images of translucent materials, we find that many simple candidate sources of information fail to predict how translucent an object looks. We suggest that the visual system does not rely solely on these simple image statistics to estimate translucency: the relevant stimulus information remains to be discovered.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2797.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?doid=1012551.1012575}, editor = {Interrante, V. , A. McNamara, H.H. B{\"u}lthoff, H.E. Rushmeier}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {1st Symposium on Applied Perception in Graphics and Visualization (APGV 2004)}, language = {en}, ISBN = {1-58113-914-4}, DOI = {10.1145/1012551.1012575}, author = {Fleming, R and Jensen, HW and B{\"u}lthoff, HH} } @Inproceedings { 2764, title = {Spatial updating in real and virtual environments: contribution and interaction of visual and vestibular cues}, journal = {1st Symposium on Applied Perception in Graphics and Visualization (APGV‘04)}, year = {2004}, month = {8}, pages = {9-17}, abstract = {INTRODUCTION: When we move through the environment, the self-to-surround relations constantly change. Nevertheless, we perceive the world as stable. A process that is critical to this perceived stability is ''spatial updating'', which automatically updates our egocentric mental spatial representation of the surround according to our current self-motion. According to the prevailing opinion, vestibular and proprioceptive cues are absolutely required for spatial updating. Here, we challenge this notion by varying visual and vestibular contributions independently in a high-fidelity VR setup. METHODS: In a learning phase, participants learned the positions of twelve targets attached to the walls of a 5x5m room. In the testing phase, participants saw either the real room or a photo-realistic copy presented via a head-mounted display (HMD). Vestibular cues were applied using a motion platform. Participants' task was to point ''as accurately and quickly as possible'' to four targets announced consecutively via headphones after rotations around the vertical axis into different positions. RESULTS: Automatic spatial updating was observed whenever useful visual information was available: Paticipants had no problem mentally updating their orientation in space, irrespective of turning angle. Performance, quantified as response time, configuration error, and pointing error, was best in the real world condition. However, when the field of view was limited via cardboard blinders to match that of the HMD (40 \(\times\) 30\(^{\circ}\)), performance decreased and was comparable to the HMD condition. Presenting turning information only visually (through the HMD) hardly altered those results. In both the real world and HMD conditions, spatial updating was obligatory in the sense that it was significantly more difficult to ignore ego-turns (i.e., ''point as if not having turned'') than to update them as usual. CONCLUSION: The rapid pointing paradigm proved to be a useful tool for quantifying spatial updating. We conclude that, at least for the limited turning angles used (<60\(^{\circ}\)), the Virtual Reality simulation of ego-rotation was as effective and convincing (i.e., hard to ignore) as its real world counterpart, even when only visual information was presented. This has relevant implications for the design of motion simulators for, e.g., architecture walkthroughs.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2764.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1012553}, editor = {Interrante, V. , A. McNamara, H.H. B{\"u}lthoff, H.E. Rushmeier}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, California, USA}, event_name = {1st Symposium on Applied Perception in Graphics and Visualization (APGV 2004)}, language = {en}, ISBN = {1-58113-914-4}, DOI = {10.1145/1012551.1012553}, author = {Riecke, BE and B{\"u}lthoff, HH} } @Inproceedings { 2865, title = {The components of conversational facial expressions}, journal = {Proceedings of the 1st Symposium on Applied perception in graphics and visualization (APGV‘04)}, year = {2004}, month = {8}, pages = {143-149}, abstract = {Conversing with others is one of the most central of human behaviours. In any conversation, humans use facial motion to help modify what is said, to control the flow of a dialog, or to convey complex intentions without saying a word. Here, we employ a custom, image-based, stereo motion-tracking algorithm to track and selectively ''freeze'' portions of an actor or actress's face in video recordings in order to determine the necessary and sufficient facial motions for nine conversational expressions. The results show that most expressions rely primarily on a single facial area to convey meaning, with different expressions using different facial areas. The results also show that the combination of rigid head, eye, eyebrow, and mouth motion is sufficient to produce versions of these expressions that are as easy to recognize as the original recordings. Finally, the results show that the manipulation technique introduced few perceptible artifacts into the altered video sequences. The use of advanced computer graphics techniques provided a means to systematically examine real facial expressions. This provides not only fundamental insights into human perception and cognition, but also yields the basis for a systematic description of what needs to be animated in order to produce realistic, recognizable facial expressions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2865.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1012578}, editor = {Interrante, V. , A. McNamara, H.H. B{\"u}lthoff, H.E. Rushmeier}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {1st Symposium on Applied Perception in Graphics and Visualization (APGV 2004)}, language = {en}, ISBN = {1-58113-914-4}, DOI = {10.1145/1012551.1012578}, author = {Cunningham, DW and Kleiner, M and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 2866, title = {View dependence of complex versus simple facial motions}, journal = {Proceedings of the 1st Symposium on Applied perception in graphics and visualization (APGV‘04)}, year = {2004}, month = {8}, pages = {181-181}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apgv04-181_2866[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=1012603}, editor = {Interrante, V. , A. McNamara, H.H. B{\"u}lthoff, H.E. Rushmeier}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {1st Symposium on Applied Perception in Graphics and Visualization (APGV 2004)}, language = {en}, ISBN = {1-58113-914-4}, DOI = {10.1145/1012551.1012603}, author = {Wallraven, C and Cunningham, DW and Breidt, M and B{\"u}lthoff, HH} } @Inproceedings { 2272, title = {Learning from humans: computational modeling of face recognition}, journal = {Proceedings of the Early Cognitive Vision Workshop (ECOVISION‘04)}, year = {2004}, month = {6}, pages = {1-4}, abstract = {In this paper we propose a computational architecture of face recognition based on evidence from cognitive research. Using an implementation of this architecture we were able to model aspects of human performance, which were found in psychophysical studies. Furthermore, results from additional recognition experi ments show that our framework is able to achieve excellent recognition performance even under large view rotations. Thus, our study is an example of how results from cognitive research can be used to construct recognition systems with better performance. Finally, our results also make new experimental predictions, which can be tested in further psychophysical studies thus closing the loop between experiment and modeling.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2272.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Skye, Scotland, UK}, event_name = {Early Cognitive Vision Workshop (ECOVISION '04)}, language = {en}, author = {Wallraven, C and Schwaninger, A and B{\"u}lthoff, HH} } @Inproceedings { 656, title = {Drivers steer in their direction of gaze}, journal = {Vision in Vehicles IX, Aug. 2001, Brisbane, Australia}, year = {2004}, pages = {-}, abstract = {Instructions given to novices learning certain tasks of applied navigation often suggest that gazedirection (?line of sight?) should preview the path the operator desires to take (e.g., Bondurant \& Blakemore, 1998; Motorcycle Safety Foundation, 1992; Morris, 1990), presumably because looking behavior can ultimately affect steering control through hand, arm, or leg movements that could lead to undesired path deviations. Here, we control participants? gaze-direction while driving an automobile in virtual reality, and find that gaze-eccentricity has a large, systematic effect on steering and lane-position. Moreover, even when head-position and postural effects of the driver are controlled, there remains a significant bias to drive in the direction of fixation, indicating the existence of a perceptual, and not merely motor, phenomenon.}, department = {Department B{\"u}lthoff}, editor = {Gale, A.C. , M.H. Freeman, C.H. Halsgrave}, publisher = {Elsevier}, address = {Amsterdam, Netherlands}, booktitle = {Vision in Vehicles IX}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Brisbane, Australia}, event_name = {9th International Conference Vision in Vehicles (VIV 2001)}, author = {Readinger, WO and Chatziastros, A and Cunningham, DW and Cutting, JE and B{\"u}lthoff, HH} } @Inproceedings { 2320, title = {Combining 3D Scans and Motion Capture for Realistic Facial Animation}, journal = {Proceedings der Eurograph 2003}, year = {2003}, month = {9}, pages = {63-66}, abstract = {We present ongoing work on the development of new methods for highly realistic facial animation. One of the main contributions is the use of real-world, high-precision data for both the timing of the animation and the deformation of the face geometry. For animation, a set of morph shapes acquired through a 3D scanner is linearly morphed according to timing extracted from point tracking data recorded with an optical motion capture system.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/Eurographics-2003-Breidt.pdf}, department = {Department B{\"u}lthoff}, editor = {Flores, J. , P. Cano}, publisher = {Eurographics Association}, address = {Aire-la-Ville, Switzerland}, booktitle = {Eurographics 2003}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Granada, Spain}, event_name = {24th Annual Conference of the European Association for Computer Graphics}, author = {Breidt, M and Wallraven, C and Cunningham, DW and B{\"u}lthoff, HH} } @Inproceedings { 2366, title = {Environmental variables in the ''moth effect''}, journal = {Vision in Vehicles X, Sep. 2003}, year = {2003}, month = {9}, pages = {1-6}, abstract = {The ''moth effect'' represents the tendency drivers show to steer in the direction of their fixation, often at night, toward vehicles parked on the roadside. It has been hypothesized that this phenomenon is responsible for a high number of vehicular accidents. Here, this issue is addressed with regard to the nature of the environment and the object of fixation. Prior work was based on a textured, but empty, visual landscape, and a fixation point at one particular location on the viewing screen. Building on this, two experiments were carried out in a driving simulator. Participants were instructed to steer down the center of a straight road, while maintaining fixation, which was controlled at -15, 0, or +15 degrees from center screen. In the first experiment, the richness of the environment was manipulated with the addition of numerous trees on the roadside, thus potentially providing the driver with increased optical flow, depth ordering, and velocity information. In the second experiment, the fixation point was changed from a location in screen coordinates, resembling gaze at an object in the interior of a car (e.g. a spot on the windshield), to a location in the environment. Participants thus fixated an object which was located in the car‘s exterior and drew nearer over the course of a trial. The dependent measure of interest was lateral position on the road. The results confirmed previous findings that drivers exhibit a systematic tendency to steer towards their looking direction (p < 0.05), independent of whether the target of observation was planted in the car‘s interior or exterior. However, we found that the addition of trees to the environment resulted in an attenuation of the ''moth effect'' (p < 0.05), indicating a compensatory role of a rich visual environment. Currently, we are investigating whether this result may alternatively be explained by a different gaze behavior or reduced fixation time on the target in crowded environments. The present data and eye-movement analyses will be discussed in terms of environmental conditions and driver safety.}, department = {Department B{\"u}lthoff}, web_url = {http://visionscience.com/pipermail/visionlist/2002/000319.html}, publisher = {Applied Research Institute}, address = {Loughborough, UK}, booktitle = {Vision in Vehicles X}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Granada, Spain}, event_name = {10th International Conference on Vision in Vehicles (VIV 2003)}, author = {Chatziastros, A and Readinger, W and B{\"u}lthoff, HH} } @Inproceedings { 2230, title = {Object Shape in Basic Level Categorisation}, year = {2003}, month = {9}, pages = {390}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2230.pdf}, department = {Department B{\"u}lthoff}, editor = {Schmalhofer, F. , R. Young, G. Katz}, publisher = {Erlbaum}, address = {Mahwah, NJ, USA}, booktitle = {EuroCogSci 03}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Osnabr{\"u}ck, Germany}, event_name = {European Cognitive Science Conference 2003}, ISBN = {0-8058-5005-8}, author = {Graf, M and B{\"u}lthoff, HH} } @Inproceedings { 2096, title = {The inaccuracy and insincerity of real faces}, journal = {Proceedings of Visualization, Imaging, and Image Processing 2003}, year = {2003}, month = {9}, pages = {7-12}, abstract = {Since conversation is a central human activity, the synthesis of proper conversational behavior for Virtual Humans will become a critical issue. Facial expressions represent a critical part of interpersonal communication. Even with the most sophisticated, photo-realistic head model, an avatar who's behavior is unbelievable or even uninterpretable will be an inefficient or possibly counterproductive conversational partner. Synthesizing expressions can be greatly aided by a detailed description of which facial motions are perceptually necessary and sufficient. Here, we recorded eight core expressions from six trained individuals using a method-acting approach. We then psychophysically determined how recognizable and believable those expressions were. The results show that people can identify these expressions quite well, although there is some systematic confusion between particular expressions. The results also show that people found the expressions to be less than convincing. The pattern of confusions and believability ratings demonstrates that there is considerable variation in natural expressions and that even real facial expressions are not always understood or believed. Moreover, the results provide the ground work necessary to begin a more fine-grained analysis of the core components of these expressions. As some initial results from a model-based manipulation of the image sequences shows, a detailed description of facial expressions can be an invaluable aid in the synthesis of unambiguous and believable Virtual Humans.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2096.pdf}, department = {Department B{\"u}lthoff}, editor = {Hamza, H.M.}, publisher = {Acta Press}, address = {Anaheim, CA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Benalm{\'a}dena, Spain}, event_name = {3rd IASTED International Conference on Visualization, Imaging, and Image Processing (VIIP 2003)}, ISBN = {0-88986-382-2}, author = {Cunningham, DW and Breidt, M and Kleiner, M and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 2508, title = {Cross-modal perception of actively explored objects}, journal = {Proceedings EuroHaptics 2003}, year = {2003}, month = {7}, pages = {291-299}, abstract = {Many objects in our world can be picked up and freely manipulated, thus allowing information about an object to be available to both the visual and haptic systems. However, we understand very little about how object information is shared across the modalities. Under constrained viewing cross-modal object recognition is most efficient when the same surface of an object is presented to the visual and haptic systems [5]. Here we tested cross modal recognition of novel objects under active manipulation and unconstrained viewing of the objects. These objects were designed such that each surface of the object provided unique information. In Experiment 1, participants were allowed 30 seconds to learn the objects visually or haptically. Haptic learning resulted in relatively poor haptic recognition performance relative to visual recognition. In Experiment 2, we increased the learning time for haptic exploration and found equivalent haptic and visual recognition, but a cost in cross modal recognition. In Experiment 3, participants learned the objects using both modalities together, vision alone or haptics alone. Recognition performance was tested using both modalities together. We found that recognition performance was significantly better when objects were learned by both modalities than either of the modalities alone. Our results suggest that efficient cross modal performance depends on the spatial correspondence of object surface information across modalities.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/cross_modal_perception_of_actively_explored_objects_2508[0].pdf}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://www.eurohaptics.org/}, editor = {Oakley, I. , S. O'Modhrain, F. Newell}, publisher = {Trinity College Dublin}, address = {Dublin, Ireland}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max-Planck-Institut f{\"u}r Biologische Kybernetik}, event_place = {Dublin, Ireland}, event_name = {EuroHaptics International Conference 2003}, language = {en}, author = {Newell, F and B{\"u}lthoff, HH and Ernst, M} } @Inproceedings { 2022, title = {How believable are real faces? Towards a perceptual basis for conversational animation}, journal = {Computer Animation and Social Agents 2003}, year = {2003}, month = {5}, pages = {23-29}, abstract = {Regardless of whether the humans involved are virtual or real, well-developed conversational skills are a necessity. The synthesis of interface agents that are not only understandable but also believable can be greatly aided by knowledge of which facial motions are perceptually necessary and sufficient for clear and believable conversational facial expressions. Here, we recorded several core conversational expressions (agreement, disagreement, happiness, sadness, thinking, and confusion) from several individuals, and then psychophysically determined the perceptual ambiguity and believability of the expressions. The results show that people can identify these expressions quite well, although there are some systematic patterns of confusion. People were also very confident of their identifications and found the expressions to be rather believable. The specific pattern of confusions and confidence ratings have strong implications for conversational animation. Finally, the present results provide the information necessary to begin a more fine-grained analysis of the core components of these expressions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2022.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8541}, publisher = {IEEE}, address = {Los Alamitos, CA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {New Brunswick, NJ, USA}, event_name = {16th International Conference on Computer Animation and Social Agents (CASA 2003)}, ISBN = {0-7695-1934-2}, DOI = {10.1109/CASA.2003.1199300}, author = {Cunningham, DW and Breidt, M and Kleiner, M and Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 2070, title = {Automatic synthesis of sequences of human movements by linear combination of learned example patterns}, journal = {Biologically motivated computer vision LNCS2525}, year = {2002}, month = {11}, pages = {538-547}, abstract = {We present a method for the synthesis of sequences of realistically looking human movements from learned example patterns. We apply this technique for the synthesis of dynamic facial expressions. Sequences of facial movements are decomposed into individual movement elements which are modeled by linear combinations of learned examples. The weights of the linear combinations define an abstract pattern space that permits a simple modification and parameterization of the style of the individual movement elements. The elements are defined in a way that is suitable for a simple automatic resynthesis of longer sequences from movement elements with different styles. We demonstrate the efficiency of this technique for the animation of a 3D head model and discuss how it can be used to generate spatio-temporally exaggerated sequences of facial expressions for psychophysical experiments on caricature effects.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/eery7ene3vkt3nwk/fulltext.pdf}, editor = {B{\"u}lthoff, H.H. , S.W. Lee, T.A. Poggio, C. Wallraven}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Biologically Motivated Computer Vision}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {Second International Workshop on Biologically Motivated Computer Vision (BMCV 2002)}, ISBN = {3-540-36181-2}, DOI = {10.1007/3-540-36181-2_54}, author = {Giese, MA and Knappmeyer, B and B{\"u}lthoff, HH} } @Inproceedings { 2509, title = {Combining sensory Information to Improve Visualization}, journal = {Proceedings of the Conference on Visualization ‘02 (VIS ‘02)}, year = {2002}, month = {11}, pages = {571-574}, abstract = {Seemingly effortlessly the human brain reconstructs the three-dimensional environment surrounding us from the light pattern striking the eyes. This seems to be true across almost all viewing and lighting conditions. One important factor for this apparent easiness is the redundancy of information provided by the sensory organs. For example, perspective distortions, shading, motion parallax, or the disparity between the two eyes' images are all, at least partly, redundant signals which provide us with information about the three-dimensional layout of the visual scene. Our brain uses all these different sensory signals and combines the available information into a coherent percept. In displays visualizing data, however, the information is often highly reduced and abstracted, which may lead to an altered perception and therefore a misinterpretation of the visualized data. In this panel we will discuss mechanisms involved in the combination of sensory information and their implications for simulations using computer displays, as well as problems resulting from current display technology such as cathode-ray tubes.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/combining_sensory_information_to_improve_visualization_2509[0].pdf}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, department3 = {Research Group Ernst}, web_url = {http://dl.acm.org/citation.cfm?id=602202\&bnc=1}, editor = {Moorhead, R. , M. Joy}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, MA, USA}, event_name = {IEEE Conference on Visualization 2002 (VIS '02)}, language = {en}, ISBN = {0-7803-7498-3}, author = {Ernst, MO and Banks, MS and Wichmann, FA and Maloney, L and B{\"u}lthoff, HH} } @Inproceedings { 1987, title = {View-based recognition of faces in man and machine: Re-visiting Inter-Extra-Ortho}, journal = {Proceedings of the Second International Workshop on Biologically Motivated Computer Vision (BMCV 2002)}, year = {2002}, month = {11}, pages = {651-660}, abstract = {For humans, faces are highly overlearned stimuli, which are encountered in everyday life in all kinds of poses and views. Using psychophysics we investigated the effects of viewpoint on human face recognition. The experimental paradigm is modeled after the inter-extra-ortho experiment using unfamiliar objects by B{\"u}lthoff and Edelman [5]. Our results show a strong viewpoint effect for face recognition, which replicates the earlier findings and provides important insights into the biological plausibility of view-based recognition approaches (alignment of a 3D model, linear combination of 2D views and view-interpolation). We then compared human recognition performance to a novel computational view-based approach [29] and discuss improvements of view-based algorithms using local part-based information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1987.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/8gxurj83nth46f27/fulltext.pdf}, editor = {B{\"u}lthoff, H.H. , S.W. Lee, T.A. Poggio, C. Wallraven}, publisher = {Springer}, address = {Berlin, Germany}, series = {Lecture Notes in Computer Science}, booktitle = {Biologically Motivated Computer Vision}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {T{\"u}bingen, Germany}, event_name = {Second International Workshop on Biologically Motivated Computer Vision (BMCV 2002)}, language = {en}, ISBN = {3-540-00174-3}, DOI = {10.1007/3-540-36181-2_65}, author = {Wallraven, C and Schwaninger, A and Schumacher, S and B{\"u}lthoff, HH} } @Inproceedings { 1825, title = {Behavior-oriented vision for biomimetic flight control}, journal = {Proceedings of the EPSRC/BBSRC International Workshop on Biologically Inspired Robotics: The Legacy of W. Grey Walter, 14-16 August 2002, HP Labs Bristol, UK}, year = {2002}, month = {8}, pages = {196-203}, abstract = {Most flying insects extract information about their spatial orientation and self-motion from visual cues such as global patterns of light intensity or optic flow. We present an insect-inspired neuronal filter model and show how optimal receptive fields for the detection of flight-relevant input patterns can be derived directly from the local receptor signals during typical flight behavior. Using a least squares principle, the receptive fields are optimally adapted to all behaviorally relevant, invariant properties of the agent and the environment. In closed-loop simulations in a highly realistic virtual environment we show that four independent, purely reactive mechanisms based on optimized receptive fields for attitude control, course stabilization, obstacle avoidance and altitude control, are sufficient for a fully autonomous and robust flight stabilization with all six degrees of freedom.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1825.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://users.ecs.soton.ac.uk/rid/wgw02/home.html}, editor = {Arbib, M.}, address = {Bristol, UK}, booktitle = {Biologically-inspired Robotics: The Legacy of W. Grey Walter}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bristol, UK}, event_name = {EPSRC/BBSRC International Workshop on Biologically Inspired Robotics (WGW '02)}, author = {Neumann, TR and B{\"u}lthoff, HH} } @Inproceedings { 1496, title = {View-based dynamic object recognition based on human perception}, journal = {ICPR 2002}, year = {2002}, month = {8}, pages = {768-776}, abstract = {Psychophysical studies have shown that humans actively exploit temporal information such as contiguity of images in object recognition. We have recently developed a recognition system which uses temporal contiguity to learn extensible representations of objects on-line. The system performs well both on real-world and synthetic data and shows robustness under illumination changes. In this paper, we present results which compare the proposed representation against simple image-based representations of the same complexity using Minkowski minimum distance classifiers and support vector machine classifiers. Recognition results for all classifiers show large improvements with incorporated temporal information.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1496.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1048105\&tag=1}, editor = {Kasturi, R. , D. Laurndeau, C.Y. Suen, N. Ayache}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Quebec, Canada}, event_name = {16th International Conference on Pattern Recognition (ICPR 2002)}, ISBN = {0-7695-1695-X}, DOI = {10.1109/ICPR.2002.1048105}, author = {B{\"u}lthoff, HH and Wallraven, C and Graf, A} } @Inproceedings { 647, title = {The use of splay angle and optical flow in steering a central path}, journal = {Vision in Vehicles VIII, Aug. 1999, Boston, USA}, year = {2002}, pages = {-}, abstract = {In the present experiment we investigated the importance of velocity information during a lane-centering task between the walls of a simulated tunnel. We varied both simulated velocity and the spatial frequency content of the walls' surfaces, in order to address the influence of each parameter on steering performance. Further, this performance was compared to the effectiveness of lateral control using lane border information. We found that drivers used both velocity and spatial frequency information to maintain a centered position on a path, and that the presence of lane borders improved accuracy. The results suggest that multiple sources of visual information, rather than mere demarcating lines, are used for lateral control on a straight path.}, department = {Department B{\"u}lthoff}, editor = {Gale, A.G. , I.D. Brown, C.M. Haslegrave, S.P. Taylor}, publisher = {Elsevier}, address = {Amsterdam, Netherlands}, booktitle = {Vision in Vehicles VIII}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, MA, USA}, event_name = {8th International Conference on Vision in Vehicles (VIV 1999)}, author = {Chatziastros, A and Wallis, GM and B{\"u}lthoff, HH} } @Inproceedings { 952, title = {Automatic acquisition of exemplar-based representations for recognition from image sequences}, journal = {CVPR 2001 - Workshop on Models vs. Exemplars}, year = {2001}, month = {12}, pages = {1-9}, abstract = {We present an exemplar-based object recognition system which is capable of on-line learning of representations of scenes and objects from image sequences. Local appearance features are used in a tracking framework to find `key-frames' of the input sequence during learning. The representation of the stored sequences which are used for recognition of novel images consists only of the appearance features in these key-frames and contains no further a-priori assumptions about the underlying sequences. The system is able to create sparse and extendable representations and shows good recognition performance in a variety of viewing conditions for databases of natural and synthetic image sequences.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf952.pdf}, department = {Department B{\"u}lthoff}, editor = {Kanade, T. , T. Sim}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Kauai, HI, USA}, event_name = {CVPR 2001 Workshop on Models versus Exemplars in Computer Vision}, author = {Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 951, title = {View-based recognition under illumination changes using local features}, journal = {CVPR 2001 - Workshop on Identifying Objects Across Variations in Lighting:  Psychophysics and Computation}, year = {2001}, month = {12}, pages = {1-8}, abstract = {We present a view-based face recognition system which combines elements from both feature-based and appearance-based approaches to increase recognition performance under illumination changes. It uses corners and their local neighborhood at several scales to construct local features which form the representation of each face image. Matching feature sets takes into account both configurational and appearance-based similarity. We present recognition results on a highly realistic synthetic face-database demonstrating the system's ability to tolerate illumination changes. In addition, the proposed framework agrees well with current findings from psychophysics.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf951.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Kauai, HI, USA}, event_name = {CVPR 2001 Workshop on Identifying Objects Across Variations in Lighting: Psychophysics and Computation}, author = {Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 1010, title = {Acquiring Robust Representations for Recognition from Image Sequences}, journal = {DAGM-Symposium M{\"u}nchen 2001}, year = {2001}, month = {9}, pages = {216-222}, abstract = {We present an object recognition system which is capable of on-line learning of representations of scenes and objects from natural image sequences. Local appearance features are used in a tracking framework to find ‘key-frames’ of the input sequence during learning. In addition, the same basic framework is used for both learning and recognition. The system creates sparse representations and shows good recognition performance in a variety of viewing conditions for a database of natural image sequences.}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/qr56716n4w448168/}, editor = {Radig, B. , S. Florczyk}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Pattern Recognition}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {M{\"u}nchen, Germany}, event_name = {23rd DAGM Symposium}, ISBN = {3-540-45404-7}, DOI = {10.1007/3-540-45404-7_29}, author = {Wallraven, C and B{\"u}lthoff, HH} } @Inproceedings { 1204, title = {Insect Inspired Visual Control of Translatory Flight}, journal = {Advances in Artificial Life: 6th European Conference, ECAL 2001}, year = {2001}, month = {1}, pages = {627-636}, abstract = {Flying insects use highly efficient visual strategies to control their self-motion in three-dimensional space. We present a biologically inspired, minimalistic model for visual flight control in an autonomous agent. Large, specialized receptive fields exploit the distribution of local intensities and local motion in an omnidirectional field of view, extracting the information required for attitude control, course stabilization, obstacle avoidance, and altitude control. In open-loop simulations, recordings from each control mechanism robustly indicate the sign of attitude angles, self rotation, obstacle dircetion and altitude deviation, respectively. Closed-loop experiments show that these signals are sufficient for three-dimensional flight stabilization with six degrees of freedom.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1204.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/fexvekv94gxp/?p=04a1d65d382549bf8caeba3f9fd0fd3e\&pi=0}, editor = {Kelemen, J. , P. Sosik}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Advances in Artificial Life}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Praha, Czech Republic}, event_name = {6th European Conference on Artificial Life (ECAL 2001)}, language = {en}, ISBN = {3-540-44811-X}, DOI = {10.1007/3-540-44811-X_71}, author = {Neumann, TR and B{\"u}lthoff, HH} } @Inproceedings { 1305, title = {Vision and Action in Virtual Environments: Modern Psychophysics in Spatial Cognition Research}, year = {2001}, month = {1}, pages = {233-252}, abstract = {The classical psychophysical approach to human perception has been to study isolated aspects of perception using well-controlled and strongly simplified laboratory stimuli. This so-called cue reduction technique has successfully led to the identification of numerous perceptual mechanisms, and has in many cases guided the uncoverage of neural correlates (see chapters elsewhere in this volume). Its limitation, however, lie in the almost complete ignorance of the intimate relation-ship among action, perception, and the environment in which we live. Real world situations are so different from the stimuli used in classical psychophysics and the context in which they arte presented that applying laboratory results to daily life situations often become impractical, if not impossible. At the Max-Planck-Institute for Biological Cybernetics in T{\"u}bingen, we pursue a behavioural approach to human action and perception that proves especially well suited for studying more complex cognitive functions, such as object recognition and spatial cognition. The recent availability of high-fidelity ''virtual reality'' environments enables us to provide subjects a level of sensory realism and dynamic sensory feedback that approaches their experiences in the real world. At the same time, we can keep the ultimate control over all stimulus aspects that are required by the rules of psychophysics. In this chapter, we take a closer look at these developments in spatial cognition research and present results from several different experimental studies that we have conducted using this approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/vision_and_action_in_virtual_environment_modern_psychophysics_in_spatial_cognition_research_1305[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springer.com/medicine/ophthalmology/book/978-0-387-95058-7}, editor = {Jenkin, M. , L. Harris}, publisher = {Springer}, address = {New York, NY, USA}, booktitle = {Vision and Attention}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Toronto, Canada}, event_name = {Fifth Conference of the York Centre for Vision Research}, ISBN = {978-0-387-95058-7}, author = {B{\"u}lthoff, HH and van Veen, H-J} } @Inproceedings { 1207, title = {Biologically motivated visual control of attitude and altitude in translatory flight}, journal = {Proceedings in Artificial Intelligence: Proceedings of the 3rd Workshop Dynamische Perzeption (Eds. G. Baratoff and H. Neumann)}, year = {2000}, month = {11}, pages = {135-140}, abstract = {Flying insects use highly efficient visual strategies for stabilizing their motion in three-dimensional space. We present a flight control model that uses a combination of biologically inspired, visual feed-forward mechanisms for stabilizing attitude (i.e. pitch and roll angles) and altitude during translatory motion. The attitude sensor exploits the position invariant vertical intensity gradient that exists in most natural open environments to orient the upper surface of a flying agent towards the region of maximum brightness (dorsal light response). Altitude is controlled using distance information contained in the frontoventral translatory optic flow (motion parallax). Our results from open-loop computer simulations show that the signals produced by these mechanisms robustly indicate the direction of deviation from a certain attitude angle or ground distance. We argue that in a closed control loop, these qualitative signals can be sufficient for flight stabilization. We present closed-loop trajectories of a simulated agent equipped with both mechanisms, flying over a textured, uneven surface. The agent shows robust flight behavior with six degrees of freedom.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1207.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.aka-verlag.com/de/detail;jsessionid=1s6hvyfdxoci0ls4eklauflc9?ean=978-3-89838-020-1}, editor = {Baratoff, G. , H. Neumann}, publisher = {Akademische Verlags-Gesellschaft}, address = {Berlin, Germany}, booktitle = {Dynamische Perzeption: Workshop der GI-Fachgruppe 1.0.4 Bildverstehen}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Ulm, Germany}, event_name = {3rd Workshop Dynamische Perzeption}, ISBN = {978-3-89838-020-1}, author = {Neumann, TR and B{\"u}lthoff, HH} } @Inproceedings { 169, title = {Measuring Visual Shape using Computer Graphics Psychophysics}, year = {2000}, month = {6}, pages = {1-10}, abstract = {This paper reviews recent psychophysical methods that have been developed for measuring the perceived shape of objects. We discuss two types of shape ambiguities that exist for many objects - a depth reversal ambiguity and an affine ambiguity. We show that people perceptually resolve these shape ambiguities by making strong prior assumptions the object.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf169.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dl.acm.org/citation.cfm?id=732136}, editor = {P{\'e}roche, B. , H. Rushmeier}, publisher = {Springer}, address = {Wien, Austria}, booktitle = {Rendering Techniques 2000}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Brno, Czech Republic}, event_name = {11th Eurographics Workshop on Rendering Techniques}, ISBN = {3-211-83535-0}, author = {Langer, MS and B{\"u}lthoff, HH} } @Inproceedings { 166, title = {The Perception of Spatial Layout in a Virtual World}, journal = {Biologically Motivated Computer Vision: Proceedings of the First IEEE International Workshop (BMCV 2000)}, year = {2000}, month = {1}, pages = {1-22}, abstract = {The perception and recognition of spatial layout of objects within a three-dimensional setting was studied using a virtual reality (VR) simulation. The subjects’ task was to detect the movement of one of several objects across the surface of a tabletop after a retention interval during which time all objects were occluded from view. Previous experiments have contrasted performance in this task after rotations of the observers’ observation point with rotations of just the objects themselves. They found that subjects who walk or move to new observation points perform better than those whose observation point remains constant. This superior performance by mobile observers has been attributed to the influence of non-visual information derived from the proprioceptive or vestibular systems. Our experimental results show that purely visual information derived from simulated movement can also improve subjects’ performance, although the performance differences manifested themselves primarily in improved response times rather than accuracy of the responses themselves.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/the_perception_of_spatial_layout_in_a_virtual_world_166[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://image.korea.ac.kr/BMCV2000/}, editor = {Lee, S.-W. , H.H. B{\"u}lthoff, T. Poggio}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Biologically Motivated Computer Vision}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Seol, Korea}, event_name = {First IEEE International Workshop on Biologically Motivated Computer Vision (BMCV 2000)}, language = {en}, ISBN = {3-540-45482-9}, DOI = {10.1007/3-540-45482-9_2}, author = {B{\"u}lthoff, HH and Christou, CG} } @Inproceedings { 648, title = {The effect of field of view and surface texture on driver steering performance}, journal = {In: Vision in Vehicles VII, (Eds.) A.G. Gale, I.D. Brown, C.M. Haslegrave, S.P. Taylor. Elsevier, Amsterdam}, year = {1999}, pages = {253-259}, abstract = {In the present study we investigated steering accuracy in terms of our ability to keep to the middle of a lane in a fixed-base driving simulator. In particular, we studied the dependence of steering accuracy on the visibility of different road sections, on the assumption that performance reflects the importance of different road sections in guiding steering. Other influences on steering accuracy - including the presence of textural cues, in the form of a textured road surface, and the horizontal field of view - were also investigated. We found that textural cues can improve accuracy in lateral lane control, presumably by providing strong optical flow, and that driving accuracy is little affected by increasing the horizontal field of view from 40 deg to a full field of 180 deg.}, department = {Department B{\"u}lthoff}, web_url = {http://www.elsevier.com/wps/find/bookdescription.print/620575/description\#description}, editor = {Gale, A.G. , I.D. Brown, C.M. Haslegrave, S.P. Taylor}, publisher = {Elsevier}, address = {Amsterdam, Netherlands}, booktitle = {Vision in Vehicles VII}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Marseille, France}, event_name = {7th International Conference on Vision in Vehicles (VIV 1997)}, ISBN = {0-08-043671-4}, author = {Chatziastros, A and Wallis, GM and B{\"u}lthoff, HH} } @Inproceedings { 157, title = {Navigation mit Schnappsch{\"u}ssen}, journal = {Mustererkennung 1998. Proceedings of the 20th DAGM-Symposium,(Eds.) P. Levi, R.-J. Ahlers, F. May, M. Schanz. Springer, Berlin}, year = {1998}, month = {10}, pages = {421-428}, abstract = {Es wird ein biologisch inspirierter Algorithmus vorgestellt, mit dem sich ein Ort wiederfinden l{\"a}sst, an dem vorher eine 360-Grad-Ansicht der Umgebung aufgenommen wurde. Die Zielrichtung wird aus der Verschiebung der Bildposition der umgebenden Landmarken im Vergleich zum Schnappschuss berechnet. Die Konvergenzeigenschaften des Algorithmus werden mathematisch untersucht und auf mobilen Robotern getestet.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf157.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dl.acm.org/citation.cfm?id=755616\&CFID=86271708\&CFTOKEN=17835895}, editor = {Levi, P. , R.-J. Ahlers, F. May, M. Schanz}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Mustererkennung 1998}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Stuttgart, Germany}, event_name = {20th DAGM-Symposium}, ISBN = {3-540-64935-2}, author = {Franz, MO and Sch{\"o}lkopf, B and Mallot, HA and B{\"u}lthoff, HH and Zell, A} } @Inproceedings { 152, title = {Navigation in real and virtual environments: Judging orientation and distance in a large-scale landscape}, journal = {In: Virtual Environment 98: Proceedings of the Eurographics Workshop in Stuttgart, Germany, June 16-18, 1998, (Eds.) M. Goebel, U. Lang, J. Landauer, M. Walper. Springer, Wien}, year = {1998}, month = {6}, pages = {124-133}, department = {Department B{\"u}lthoff}, web_url = {http://diglib.eg.org/EG/Publications/Data/eg98ve}, editor = {G{\"o}bel, M. , U. Lang, J. Landauer, M. Walper}, publisher = {Springer}, address = {Wien, Austria}, booktitle = {Virtual Environments '98}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Stuttgart, Germany}, event_name = {Eurographics Workshop}, ISBN = {3-211-83233-5}, author = {Distler, HK and van Veen, HAHC and Braun, SJ and Heinz, W and Franz, MO and B{\"u}lthoff, HH} } @Inproceedings { 233, title = {Tele-Experiments: Experiments on spatial cognition using VRML-based multimedia}, journal = {Proceedings of VRML98: Third symposium on the virtual reality modeling language,16-19 February 1998. ACM Press, Monterey USA 1998}, year = {1998}, month = {2}, pages = {101-105}, abstract = {This paper describes an application of VRML-based multimedia to the domain of spatial cognition experiments. Typically, such experiments involve human subjects that are presented with graphical stimuli in a laboratory setup. Larger numbers of subjects and stimuli give more weight to the outcomes of the experiment, but in practice the number of subjects is limited by practicalities like time constraints. This paper describes a way to overcome this limitation: use the internet to bring the experiment to the subject instead of the other way around. We are developing a web page with psychophysical experiments, using VRML as a means for presenting three-dimensional graphics to simulate the conditions of a laboratory experiment. While using the web for psychological experiments is not a novel idea, combining that with VRML is new and extends the possibilities for experiments. In this paper we outline the power of using the web and describe an experiment using VRML, highlighting technical aspects of the problems encountered and the solutions taken to overcome them.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf233.pdf}, department = {Department B{\"u}lthoff}, editor = {Spencer, S.N.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Monterey, CA, USA}, event_name = {Third Symposium on the Virtual Reality Modeling Language (VRML 98)}, ISBN = {1-58113-022-8}, DOI = {10.1145/271897.279546}, author = {Givaty, G and van Veen, HAHC and Christou, C and B{\"u}lthoff, HH} } @Inproceedings { 237, title = {Simulation and robot implementation of visual orientation behaviors of flies}, journal = {Proceedings of the 5th International Conference on Simulation of Adaptive Behavior, (Eds.) R. Pfeiffer, B. Blumberg, J.-A. Meyer, S. Wilson. MIT Press, Cambridge}, year = {1998}, month = {1}, pages = {77-85}, abstract = {Flies have developed visuomotor programs for tasks like course stabilization, fixation and approach towards stationary objects, tracking of moving objects, and landing, which are based on the analysis of visual motion information. Theoretical and experimental results suggest that the visuomotor control for course stabilization as well as fixation and approach towards stationary objects may be realized at least partially by one common sensory circuit In order to test this hypothesis we designed simulated agents, with a control architecture that is based on results from fly research. We present agents with a visuomotor controller that regulates the two behaviors of course stabilization and object fixation. To test this controller under real world conditions, we implemented it on a miniature robot. We can show that besides course stabilization and object fixation, the robot additionally approaches stationary objects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/simulation_and_robot_implementation_of_visual_orientation_behaviors_of_flies_237[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=299965}, editor = {Pfeifer, R. , B. Blumberg, J.-A. Meyer, S.W. Wilson}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {From Animals to Animats 5}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Z{\"u}rich, Switzerland}, event_name = {5th International Conference on Simulation of Adaptive Behavior}, ISBN = {0-262-66144-6}, author = {Huber, S and B{\"u}lthoff, HH} } @Inproceedings { 373, title = {Minimalistic approach to 3D obstacle avoidance behavior from simulated evolution}, journal = {Proceedings of the 7th International Conference on Artificial Neural Networks ICANN 1997 (Eds. W. Gerstner, A. Germond, M. Hasler and J.-D. Nicoud)}, year = {1997}, month = {10}, pages = {715-720}, abstract = {We present a minimalistic approach to establish obstacle avoidance and course stabilization behavior of a simulated flying autonomous agent in a 3D virtual world. The agent uses visual cues, and its sensory and motor components are based on biological principles found in flies. A simple neural network is used for coupling the receptor and effector systems of the agent. In order to achieve appropriate reactions to sensory input, the connection weights are adjusted by a genetic algorithm under a closed loop action-perception condition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf373.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/wqu03w5xq3854173/fulltext.pdf}, editor = {Gerstner, W. , A. Germond, M. Hasler, J.-D. Nicoud}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Artificial Neural Networks: ICANN '97}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {7th International Conference on Artificial Neural Networks}, ISBN = {3-540-63631-5}, DOI = {10.1007/BFb0020238}, author = {Neumann, TR and Huber, SA and B{\"u}lthoff, HH} } @Inproceedings { 363, title = {Modeling obstacle avoidance behavior of flies using an adaptive autonomous agent}, journal = {Proceedings of the 7th International Conference on Artificial Neural Networks, ICANN 97, Lausanne, Switzerland, (Eds.) W. Gerstner et al. Springer Lecture Notes in Science, Berlin 1997}, year = {1997}, month = {10}, pages = {709-714}, abstract = {In the course of evolution flies have developed specialized visuomotor programs for tasks like compensating for course deviations, obstacle avoidance, and tracking, which are based on the analysis of visual motion information. In order to test models of the obstacle avoidance behavior in flies, we use computer-simulated agents that evolve parts of their sensor system and sensorimotor coupling with genetic algorithms. During a simulated evolution, these agents specialize a visuomotor program that enables the agents to avoid obstacles.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/modeling_obstacle_avoidance_behavior_of_flies_using_an_adaptive_autonomous_agent_363[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/ml2388231u7v5153/fulltext.pdf}, editor = {Gerstner, W. , A. Germond, M. Hasler, J.-D. Nicoud}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Artificial Neural Networks: ICANN '97}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {7th International Conference on Artificial Neural Networks}, ISBN = {3-540-63631-5}, DOI = {10.1007/BFb0020237}, author = {Huber, S and B{\"u}lthoff, HH} } @Inproceedings { 414, title = {The view-graph approach to visual navigation and spatial memory}, journal = {Proceedings of the 7th International Conference on Artificial Neural Networks, ICANN 97, Lausanne, Switzerland (Eds.) W. Gerstner et al. Springer Lecture Notes in Computer Science, Berlin 1997}, year = {1997}, month = {10}, pages = {751-756}, abstract = {This paper describes a purely visual navigation scheme based on two elementary mechanisms (piloting and guidance) and a graph structure combining individual navigation steps controlled by these mechanisms. In robot experiments in real environments, both mechanisms have been tested, piloting in an open environment and guidance in a maze with restricted movement opportunities. The results indicate that navigation and path planning can be brought about with these simple mechanisms. We argue that the graph of local views (snapshots) is a general and biologically plausible means of representing space and integrating the various mechanisms of map behaviour.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf414.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/m852hu70g8th7267/fulltext.pdf}, editor = {Gerstner, W. , A. Germond, M. Hasler, J.-D. Nicoud}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Artificial Neural Networks: ICANN '97}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {7th International Conference on Artificial Neural Networks}, ISBN = {3-540-63631-5}, DOI = {10.1007/BFb0020244}, author = {Mallot, HA and Franz, MO and Sch{\"o}lkopf, B and B{\"u}lthoff, HH} } @Inproceedings { 357, title = {Homing by parameterized scene matching}, journal = {Proceedings of the 4th European Conference on Artificial Life, (Eds.) P. Husbands, I. Harvey. MIT Press, Cambridge 1997}, year = {1997}, month = {7}, pages = {236-245}, abstract = {In visual homing tasks, animals as well as robots can compute their movements from the current view and a snapshot taken at a home position. Solving this problem exactly would require knowledge about the distances to visible landmarks, information, which is not directly available to passive vision systems. We propose a homing scheme that dispenses with accurate distance information by using parameterized disparity fields. These are obtained from an approximation that incorporates prior knowledge about perspective distortions of the visual environment. A mathematical analysis proves that the approximation does not prevent the scheme from approaching the goal with arbitrary accuracy. Mobile robot experiments are used to demonstrate the practical feasibility of the approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf357.pdf}, department = {Department B{\"u}lthoff}, editor = {Husbands, P. , I. Harvey}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Brighton, UK}, event_name = {4th European Conference on Artificial Life (ECAL97)}, ISBN = {0-262-58157-4}, author = {Franz, MO and Sch{\"o}lkopf, B and B{\"u}lthoff, HH} } @Inproceedings { 358, title = {Learning view graphs for robot navigation}, journal = {Proceedings of the 1st Intl. Conf. on Autonomous Agents}, year = {1997}, month = {2}, pages = {138-147}, abstract = {We present a purely vision-based scheme for learning a parsimonious representation of an open environment. Using simple exploration behaviours, our system constructs a graph of appropriately chosen views. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. Simulations and robot experiments demonstrate the feasibility of the proposed approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf358.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://portal.acm.org/citation.cfm?id=267687}, editor = {Johnson, W.L.}, publisher = {ACM Press}, address = {New York, NY, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Marina del Rey, CA, USA}, event_name = {First International Conference on Autonomous Agents (AGENTS '97)}, ISBN = {0-89791-877-0}, DOI = {10.1145/267658.267687}, author = {Franz, MO and Sch{\"o}lkopf, B and Georg, P and Mallot, HA and B{\"u}lthoff, HH} } @Inproceedings { 604, title = {Aktives Erwerben eines Ansichtsgraphen zur diskreten Repr{\"a}sentation offener Umwelten}, year = {1996}, month = {9}, pages = {138-147}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf604.pdf}, department = {Department B{\"u}lthoff}, editor = {Thielscher , M. , S.-E. Bornscheuer}, publisher = {Dresden University Press}, address = {Dresden, Germany}, booktitle = {Fortschritte der K{\"u}nstlichen Intelligenz KI 96)}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Dresden, Germany}, event_name = {20. Deutsche Jahrestagung f{\"u}r K{\"u}nstliche Intelligenz}, author = {Franz, MO and Sch{\"o}lkopf, B and Mallot, HA and B{\"u}lthoff, HH} } @Inproceedings { 445, title = {Comparison of view-based object recognition algorithms using realistic 3D models}, journal = {Artificial Neural Networks, Proceedings of the International Conference on Artificial Neural Networks, (Eds.) C. von der Malsburg, W. von Seelen, J.-C. Vorbr{\"u}ggen, B. Sendhoff. Springer Lecture Notes in Computer Science, Bochum 1996}, year = {1996}, month = {7}, pages = {251-256}, abstract = {Two view-based object recognition algorithms are compared: (1) a heuristic algorithm based on oriented filters, and (2) a support vector learning machine trained on low-resolution images of the objects. Classification performance is assessed using a high number of images generated by a computer graphics system under precisely controlled conditions. Training- and test-images show a set of 25 realistic three-dimensional models of chairs from viewing directions spread over the upper half of the viewing sphere. The percentage of correct identification of all 25 objects is measured.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf445.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/p936668278821327/fulltext.pdf}, editor = {von der Malsburg, C. , W. von Seelen, J. C. Vorbr{\"u}ggen and B. Sendhoff}, publisher = {Springer}, address = {Berlin, Germany}, series = {Lecture Notes in Computer Science}, booktitle = {Artificial Neural Networks: ICANN 96}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bochum, Germany}, event_name = {6th International Conference on Artificial Neural Networks}, ISBN = {3-540-61510-5}, DOI = {10.1007/3-540-61510-5_45}, author = {Blanz, V and Sch{\"o}lkopf, B and B{\"u}lthoff, HH and Burges, C and Vapnik, V and Vetter, T} } @Inproceedings { 519, title = {Evolution of the sensorimotor control in an autonomous agent}, journal = {From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior}, year = {1996}, month = {7}, pages = {449-457}, abstract = {Visually guided agents are introduced, that evolve their sensor orientations and sensorimotor coupling in a simulated evolution. The work builds on neurobiological results from various aspects of insect navigation and the architecture of the ``Vehicles‘‘ of Braitenberg (1984). Flies have specialized visuomotor programs for tasks like compensating for deviations from the course, tracking, and landing, which involve the analysis of visual motion information. We use genetic algorithms to evolve the obstacle avoidance behavior. The sensor orientations and the transmission weights between sensor input and motor output evolve with the sensors and motors acting in a closed loop of perception and action. The influence of the crossover and mutation probabilities on the outcome of the simulations, specifically the maximum fitness and the convergence of the population are tested.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/evolution_of_the_sensorimotor_control_in_an_autonomous_agent_519[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.isab.org/confs/sab96.php}, editor = {Maes, P. , M. Mataric, J.-A. Mataric, J. Pollack, S. Wilson}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {From Animals to Animats 4}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {North Falmouth, MA, USA}, event_name = {Fourth International Conference on Simulation of Adaptive Behavior (SAB '96)}, ISBN = {0-262-63178-4}, author = {Huber, S and Mallot, HA and B{\"u}lthoff, HH} } @Inproceedings { 518, title = {Using evolutionary algorithms for the optimization of the sensorimotor control in an autonomous agent}, journal = {Proceedings of the 6th International Conference IPMU, Granada/Spain}, year = {1996}, month = {7}, pages = {1241-1246}, abstract = {Autonomous agents that evolve visually-guided control mechanisms using genetic algorithms (GA) and evolutionary strategies (ES) are introduced. These agents are situated in simulated environments and are designed based on the neurobiological principles of various aspects of insect navigation. They generate behavioral modules for obstacle avoidance and the compensation for rotations caused by external disturbances. The sensor positions and the visuomotor coupling evolve with the sensors and motors acting in a closed loop of perception and action. The probabilities for the genetic operations mutation and crossover are optimized and the results of the two optimization techniques genetic algorithms and evolutionary strategies are compared.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/using_evolutionary_algorithms_for_the_optimization_of_the_sensorimotor_control_in_an_autonomous_agent_518[0].pdf}, department = {Department B{\"u}lthoff}, editor = {Bouchon-Meunier, B.}, publisher = {Universidad de Granada}, address = {Granada, Spain}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Granada, Spain}, event_name = {6th International Conference Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 1996)}, ISBN = {84-8254-076-9}, author = {Huber, S and Mallot, HA and B{\"u}lthoff, HH} } @Inproceedings { 528, title = {Computational neuroethology and artificial life (Introductory Remarks)}, year = {1996}, month = {5}, pages = {231-233}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/computtational_neuroethology_and_artificial_life_528[0].pdf}, department = {Department B{\"u}lthoff}, editor = {Elsner, N. , H.-U. Schnitzler}, publisher = {Thieme}, address = {Stuttgart, Germany}, booktitle = {Brain and Evolution}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {G{\"o}ttingen, Germany}, event_name = {24th G{\"o}ttingen Neurobiology Conference}, ISBN = {3-13-107381-0}, author = {Mallot, HA and B{\"u}lthoff, HH} } @Inproceedings { 603, title = {A Bayesian framework for the integration of visual modules}, year = {1996}, month = {1}, pages = {49-70}, abstract = {the Bayesian approach to vision provides a fruitful theoretical framework both for modeling individual cues, such as stereo, shading, texture, and occlusion, and for integrating their information / in this formalism [the authors] represent the viewed scene by one, or more, surfaces using prior assumptions about the surface shapes and material properties / on theoretical grounds, the less information available to the cues (and the less accurate it is), the more important these assumptions become / this suggests that visual illusions, and biased perceptions, will arise for scenes for which the prior assumptions are not appropriate / describe psychophysical experiments which are consistent with these ideas.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/a_bayesian_framework_for_the_integration_of_visual_models_603[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://psycnet.apa.org/psycinfo/1996-98459-002}, editor = {Inui, T. , J. McClelland}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Attention and performance XVI: information integration in perception and communication}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Kyoto, Japan}, event_name = {Sixteenth International Symposium on Attention and Performance}, ISBN = {0-262-09033-3}, author = {B{\"u}lthoff, HH and Yuille, AL} } @Inproceedings { 668, title = {View-based cognitive map learning by an autonomous robot}, journal = {Proceedings International Conference on Artificial Neural Networks (ICANN}, year = {1995}, month = {10}, pages = {381-386}, abstract = {This paper presents a view-based approach to map learning and navigation in mazes. By means of graph theory we have shown that the view-graph is a sufficient representation for map behaviour such as path planning. A neural network for unsupervised learning of the view-graph from sequences of views is constructed. We use a modified Kohonen (1988) learning rule that transforms temporal sequence (rather than featural similarity) into connectedness. In the main part of the paper, we present a robot implementation of the scheme. The results show that the proposed network is able to support map behaviour in simple environments.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf668.pdf}, department = {Department B{\"u}lthoff}, editor = {Fogelman-Souli{\'e}, F.}, publisher = {EC2}, address = {Paris, France}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Paris, France}, event_name = {Conf{\'e}rence Internationale sur les R{\'e}seaux de Neurones Artificiels (ICANN '95)}, ISBN = {2-910085-18-X}, author = {Mallot, HA and B{\"u}lthoff, HH and Georg, P and Sch{\"o}lkopf, B and Yasuhara, K} } @Inproceedings { 669, title = {Face Recognition across Large Viewpoint Changes}, journal = {Proceedings of the Intern. Workshop on Automatic Face- and Gesture Recognition, (Ed.) M. Bichsel. MultiMedia Lab. Computer Science Dept. Univ., Z{\"u}rich}, year = {1995}, month = {6}, pages = {326-331}, abstract = {We describe a computational model of face recog­ nition that makes use of the overlapping texture and shape information visible in different views of faces. The model operates on view dependent data from three­dimensional laser scans of human heads, which were registered onto a three­dimensional head model. We show that the overlapping visible regions of heads can support accurate recognition even with pose dif­ ferences of as much as 90 degrees (full face to profile view) between the learning and testing view.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf669.pdf}, department = {Department B{\"u}lthoff}, editor = {Bichsel, M.}, publisher = {University of Zurich Department of Computer Science Multimedia Laboratory}, address = {Z{\"u}rich, Switzerland}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Z{\"u}rich, Switzerland}, event_name = {International Workshop on Automatic Face- and Gesture Recognition}, author = {O'Toole, AJ and B{\"u}lthoff, HH and Troje, NF and Vetter, T} } @Inproceedings { 2545, title = {Evaluating Object recognition Theories by Computer Graphics Psychophysics}, year = {1993}, month = {1}, pages = {139-164}, abstract = {Computational or information-processing theories of vision describe object recognition in terms of a comparison between the input image and a set of stored models that represent known objects. The nature of these representations is reflected in the performance of the visual system and may be studied experimentally, by presenting subjects with computer graphics simulations of three-dimensional objects (with precisely controlled shape cues), and by analyzing the ensuing patterns of response time and error rate. We discuss a series of psychophysical experiments that explore different aspects of the problem of subordinate-level object recognition and representation in human vision. Contrary to the paradigmatic view which holds that the representations are three-dimensional and object-centered, the results consistently support the notion of view-specific representations that include at most partial depth information. In simulated experiments that involved the same stimuli that were shown to the human subjects, computational models built around two-dimensional multiple-view representations replicated psychophysical results concerning the observed pattern of generalization errors. We argue that extensions of the multiple-view theory based on the notion of a hierarchy of spatial and nonspatial features could lead to a unification of theoretical accounts of a wide range of phenomena in human object recognition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/evaluating_object_recognition_theories_by_computer_graphics_psychophysics_2545[0].pdf}, editor = {Glaser, D. , T. Poggio}, publisher = {Wiley}, address = {Chichester, Great Britain}, series = {Dahlem Workshop reports : Life sciences research report ; 52}, booktitle = {Exploring Brain Functions: Models in Neuroscience}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Berlin, Germany}, event_name = {Workshop on Exploring Brain Functions: Models in Neuroscience}, ISBN = {0-471-93602-2}, author = {B{\"u}lthoff, HH and Edelman, S} } @Inproceedings { 692, title = {Group report: Vision - a case study in brain function}, year = {1993}, month = {1}, pages = {204-222}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/vision_a_case_study_in_brain_function_692[0].pdf}, editor = {Glaser, D. , T. Poggio}, publisher = {Wiley}, address = {Chichester, Great Britain}, series = {Dahlem Workshop reports : Life sciences research report ; 52}, booktitle = {Exploring Brain Functions: Models in Neuroscience}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Berlin, Germany}, event_name = {Workshop on Exploring Brain Functions: Models in Neuroscience}, ISBN = {0-471-93602-2}, author = {Hurlbert, AC and B{\"u}lthoff, HH and Glaser, DA and Hepp, K and Logothetis, NK and Martin, KAC and Maunsell, JHR and Mumford, DB and Singer, W and Sporns, O and Ullman, S and von der Malsburg, C} } @Inproceedings { 705, title = {A Model of the Acquisition of Object Representations in Human 3D Visual Recognition}, journal = {Proc. NATO Advanced Research Workshop on Robots and Biological Systems, P. Aebischer Eds., Springer Verlag}, year = {1993}, pages = {99-118}, abstract = {A common approach to the study of visual recognition postulates that there exist in the visual system representations of familiar objects and scenes. To recognize an object, the system compares it with each of the stored models. Such a comparison would appear possible only after the input image and the stored representations are brought to a common form. Consequently, the nature of representation must be reflected in the performance of the system [7].}, web_url = {http://www.springerlink.com/content/w2q5854718805182/fulltext.pdf}, editor = {Dario, P. , G. Sandini, P. Aebischer}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Robots and Biological Systems: Towards a New Bionics?}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {II Ciocco, Italy}, event_name = {NATO Advanced Research Workshop on Robots and Biological Systems 1989}, ISBN = {978-3-642-58069-7}, DOI = {10.1007/978-3-642-58069-7_6}, author = {Edelman, S and Weinshall, D and B{\"u}lthoff, HH and Poggio, T} } @Inproceedings { 698, title = {Modeling Human Visual Object Recognition}, journal = {Proc. Internat. Joint Conf. on Neural Networks}, year = {1992}, month = {6}, pages = {37-42}, abstract = {The topics discussed here are network models of object recognition; a computational theory of recognition; psychophysical support for a view-interpolation model: and an open issue, features of recognition. The authors survey a successful replication of central characteristics of performance in 3-D object recognition by a computational model based on interpolation among a number of stored views of each object. Network models of 3-D object recognition based on interpolation among specific stored views behave in several respects similarly to human observers in a number of recognition tasks. Even closer replication of human performance in recognition should be expected, once the issue of the features used to represent object views is resolved.}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=227292}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Baltimore, MD, USA}, event_name = {International Joint Conference on Neural Networks (IJCNN '92)}, ISBN = {0-7803-0559-0}, DOI = {10.1109/IJCNN.1992.227292}, author = {Edelmann, S and B{\"u}lthoff, HH} } @Inproceedings { 695, title = {3D Object Recognition Using Unsupervised Feature Extraction}, year = {1992}, month = {4}, pages = {368-377}, abstract = {Intrator (1990) proposed a feature extraction method that is related to recent statistical theory (Huber, 1985; Friedman, 1987) and is based on a biologically motivated model of neuronal plasticity (Bienenstock et al., 1982). This method has been recently applied to feature extraction in the context of recognizing 3D objects from single 2D views (Intrator and Gold, 1991). Here we describe experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/3d_object_recognition_using_unsupervised_feature_extraction_695[0].pdf}, web_url = {http://books.nips.cc/nips04.html}, editor = {Moody, J.E.}, publisher = {Kaufmann}, address = {San Mateo, CA, USA}, booktitle = {Advances in Neural Information Processing Systems 4}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Denver, CO, USA}, event_name = {Fifth Conference on Neural Information Processing Systems - Natural and Synthetic (NIPS 1991)}, ISBN = {1-558-60222-4}, author = {Intrator, N and Gold, JI and B{\"u}lthoff, HH and Edelman, S} } @Inproceedings { 722, title = {Three-Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features}, journal = {Proc. 8th Israeli AICV Conference, Y. Feldman and A. Bruckstein Eds., Elsevier}, year = {1991}, pages = {113-123}, abstract = {A novel method for feature extraction has been applied to a problem of three-dimensional object recognition (Intrator and Gold, 1991). The method is related to recent statistical theory (Huber, 1985; Friedman, 1987) and is derived from a biologically motivated computational theory (Bienenstock, Cooper and Munro, 1982). Results of an initial study replicating recent psychophysical experiments (Bulthoff and Edelman 1991) demonstrated the utility of the proposed method for feature extraction. We describe further experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/Israeli-AICV-8-Buelthoff_01.pdf}, editor = {Feldman, Y. , A. Bruckstein}, publisher = {Elsevier}, address = {Amsterdam, Netherlands}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_name = {8th Israeli Conference on AICV}, author = {Intrator, N and Gold, JI and B{\"u}lthoff, HH and Edelman, S} } @Inproceedings { 737, title = {A self-organizing multiple-view representation of 3D objects}, journal = {Neural Information Processing Systems}, year = {1990}, month = {11}, pages = {274-281}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/NIPS-1989-Weinshall.pdf}, web_url = {http://books.nips.cc/nips02.html}, editor = {Touretzky, D.S.}, publisher = {Kaufmann}, address = {San Mateo, CA, USA}, booktitle = {Advances in Neural Information Processing Systems 2}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Denver, CO, USA}, event_name = {1989 IEEE Conference on Neural Information Processing Systems}, ISBN = {1-55860-100-7}, author = {Weinshall, D and Edelman, S and B{\"u}lthoff, HH} } @Inproceedings { 749, title = {Shape-from-X: psychophysics and computation}, journal = {Proceedings of the SPIE}, year = {1990}, month = {11}, pages = {235-246}, abstract = {The Bayesian approach to vision provides a fruitful theoretical framework for integrating different depth modules. In this formulation depth can be represented by one or more surfaces. Prior probabilities, corresponding to natural constraints, can be defined on these surfaces to avoid the ill-posedness of vision. We advocate strong coupling between different depth cues, so that the different modules can interact during computation. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration, by the use of binary decision units. These units can be interpreted in terms of robust statistics. A number of existing psychophysical experiments can be understood within this framework.}, web_url = {http://spiedigitallibrary.org/proceedings/resource/2/psisdg/1383/1/235_1}, editor = {Schenker, P.S.}, publisher = {SPIE}, address = {Bellingham, WA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Boston, MA, USA}, event_name = {Sensor Fusion III: 3-D Perception and Recognition}, ISBN = {0-8194-0450-0}, DOI = {10.1117/12.25259}, author = {B{\"u}lthoff, HH and Yuille, A} } @Inproceedings { 739, title = {Adaptation of a parallel correlation-based optical flow scheme}, year = {1990}, month = {7}, pages = {79-82}, editor = {Thellier, N.}, publisher = {Kluwer}, address = {Dordrecht, Netherlands}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Paris, France}, event_name = {International Neural Network Conference (INNC 90)}, ISBN = {0-7923-0831-X}, author = {Bohrer, S and B{\"u}lthoff, HH and Mallot, HA} } @Inproceedings { 744, title = {Integration of Stereo, Shading and Texture}, year = {1990}, month = {5}, pages = {119-146}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/integration_of_sterei_shading_and_texture_744[0].pdf}, editor = {Blake, A. , T. Troscianko}, publisher = {Wiley}, address = {Chichester, Great Britain}, booktitle = {AI and the Eye}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Bristol, Great Britain}, event_name = {11th European Conference on Visual Perception}, ISBN = {0-471-92194-7}, author = {B{\"u}lthoff, HH and Mallot, HA} } @Inproceedings { 751, title = {Stereo Integration, Mean Field Theory and Psychophysics}, journal = {Proceedings of the First European Conference on Computer Vision, Antibes, France}, year = {1990}, month = {4}, pages = {165-172}, abstract = {We describe a theoretical formulation for stereo in terms of the Markov Random Field and Bayesian approach to vision. This formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We treat the correspondence problem and surface interpolation as different aspects of the same problem and solve them simultaneously, unlike most previous theories. We use techniques from statistical physics to compute properties of our theory and show how it relates to previous work. These techniques also suggest novel algorithms for stereo which are argued to be preferable to standard algorithms on theoretical and experimental grounds. It can be shown (Yuille, Geiger and B{\"u}lthoff 1989) that the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.}, web_url = {http://www.springerlink.com/content/m0240386841p0qv2/fulltext.pdf}, editor = {Barstow, D. , W. Brauer, P. Brinch Hansen, D. Gries, D. Luckham, C. Moler, A. Pnueli, G. Seegm{\"u}ller, J. Stoer, N. Wirth}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Computer Vision: ECCV 90}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Antibes, France}, event_name = {First European Conference on Computer Vision (ECCV 90)}, ISBN = {3-540-52522-X}, DOI = {10.1007/BFb0014852}, author = {Yuille, A and Geiger, D and B{\"u}lthoff, HH} } @Inproceedings { 745, title = {Motion Detection by Correlation and Voting}, year = {1990}, month = {1}, pages = {471-474}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/motion_detection_by_correlation_and_voting_745[0].pdf}, editor = {Eckmiller, R. , G. Hartman, G. Hauske}, publisher = {North-Holland}, address = {Amsterdam, Netherlands}, booktitle = {Parallel Processing Neural Systems and Computers}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {D{\"u}sseldorf, Germany}, event_name = {International Conference on Parallel Processing in Neural Systems and Computers (ICNC-90)}, ISBN = {0-444-88390-8}, author = {Bohrer, S and B{\"u}lthoff, HH and Mallot, HA} } @Inproceedings { 742, title = {Generalization of object recognition in human vision across stimulus transformations and deformations}, journal = {Proc. 7th Israeli AICV Conference}, year = {1990}, pages = {479-487}, publisher = {Elsevier}, address = {Amsterdam, Netherlands}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_name = {7th Israeli Conference on AICV}, author = {Edelman, S and B{\"u}lthoff, HH} } @Inproceedings { 756, title = {A Parallel Motion Algorithm Consistent with Psychophysics and Physiology}, journal = {IEEE Motion Workshop, on Visual Motion}, year = {1989}, month = {3}, pages = {165-172}, abstract = {The authors describe a simple, parallel algorithm that successfully computes an optical flow from sequences of real images, is consistent with human psychophysics, and suggests a plausible physiological model. Regularizing optical flow computation leads to a formulation which minimizes matching error and, at the same time, maximizes smoothness of the optical flow. The authors develop an approximation to the full regularization computation in which corresponding points are found by comparing local patches of images. Selection among competing matches is performed using a winner-take-all scheme. The algorithm is independent of the types of features used for matching. Experiments with natural images show that the scheme is effective and robust against noise. The algorithm shows several of the same `illusions' that humans perceive. A natural physiological implementation of the model is consistent with data from cortical areas V1 and MT.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/a_parallel_motion_algorithm_consistent_with_psychophysics_and_physiology_756[0].pdf}, publisher = {IEEE Computer Society Press}, address = {Washington, DC, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Irvine, CA, USA}, event_name = {IEEE Workshop on Visual Motion: Analysis, Motion}, ISBN = {0-8186-1903-1}, DOI = {10.1109/WVM.1989.47106}, author = {Little, J and B{\"u}lthoff, HH and Poggio, T} } @Inproceedings { 834, title = {Migrierende Myozyten bei experimenteller Arteriosklerose}, journal = {Verh. Dtsch. AG. Arterioskleroseforschung}, year = {1989}, pages = {59-62}, editor = {Hoffmeister, H.E. , E. Betz}, publisher = {Attempto Verlag}, address = {T{\"u}bingen, Germany}, booktitle = {Sekund{\"a}rpr{\"a}vention der Arteriosklerose}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Blaubeuren, Germany}, event_name = {Arbeitstagung des T{\"u}binger Arbeitskreises f{\"u}r Gef{\"a}sserkrankungen e.V.}, ISBN = {3-89308-025-2}, author = {Czempiel, P and Schlote, W and Betz, E and B{\"u}lthoff, HH} } @Inproceedings { 778, title = {Parallel Optical Flow Using Local Voting}, journal = {Proceedings of the 2nd International Conference on Computer Vision}, year = {1988}, month = {12}, pages = {454-459}, abstract = {We describe a parallel algorithm for computing optical flow from short-range motion. Regularizing optical flow computation leads to a forruulation which minimizes matching error and, at the same time, maximises smoothness of the optical flow. We develop an approximation to the full regularization computation in which corresponding points are found by comparing local patches of the images. Selection aniong competing matches is performed using a winner-take-all scheme. The algorithm accommodates many different image transformations uniformly, with siniilar results, from brightness to edges. The optical flow computed froni different image transformations, such as edge detection and direct brightness computation, can be simply combined. The algorithm is easily implemented using local operations on a finegrained computer, and has been implemented on a Connection Machine. Experiments with natural images show that the scheme is effective and robust against noise. The algorithm leads to dense optical flow fields ; in addition, inforniation from matching facilitates segmentation.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf778.pdf}, publisher = {IEEE Computer Society Press}, address = {Washington, DC, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Tampa, FL, USA}, event_name = {2nd International Conference on Computer Vision (ICCV 1988)}, ISBN = {0-8186-0883-8}, DOI = {10.1109/CCV.1988.590023}, author = {Little, J and B{\"u}lthoff, HH and Poggio, T} } @Inproceedings { 782, title = {The MIT Vision Machine}, journal = {Proceedings Image Understanding Workshop}, year = {1988}, month = {4}, pages = {177-198}, publisher = {Morgan Kaufmann}, address = {San Mateo, CA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Cambridge, MA, USA}, event_name = {1988 DARPA Image-Understanding Workshop}, ISBN = {0-934613-68-0}, author = {Poggio, T and Little, J and Gamble, E and Gillet, W and Geiger, D and Weinshall, D and Villalba, M and Larson, N and Cass, T and B{\"u}lthoff, HH and Drumheller, M and Oppenheimer, P and Yang, W and Hurlbert, A} } @Inproceedings { 826, title = {Interaction of different modules in depth perception}, journal = {Proceedings of the 1st International Conference on Computer Vision}, year = {1987}, month = {6}, pages = {295-305}, abstract = {The interaction of modules for depth perception was studied psychophysically by measuring the perceived depth of computer generated images showing simple solid objects with different combinations of depth cues. Accumulation and information from shading and stereo and vetoing of depth from shading by edge information have been found. Cooperativity and other types of interactions are discussed. If intensity edges are missing, as in smooth-shaded surfaces, the image intensities themselves could be used for stereo matching. Matching primitives other than edges were studied in additional experiments. The results are compared with computer vision algorithms for both single modules and their integration for 3D-vision.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf826.pdf}, editor = {Brady, J.M. , A. Rosenfeld}, publisher = {IEEE Computer Society Press}, address = {Washington, DC, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {London, Great Britain}, event_name = {First IEEE International Conference on Computer Vision}, ISBN = {0-8186-0777-7}, author = {B{\"u}lthoff, HH and Mallot, HA} } @Inproceedings { 830, title = {Parallel Optical Flow Computation}, year = {1987}, month = {2}, pages = {915-920}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf830.pdf}, publisher = {Kaufmann}, address = {Los Altos, CA, USA}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Los Angeles, CA, USA}, event_name = {DARPA Image Understanding Workshop}, ISBN = {0-934613-36-2}, author = {Little, J and Poggio, T and B{\"u}lthoff, HH} } @Inbook { MohlerdB2012, title = {Multisensory contributions to spatial perception}, year = {2012}, month = {10}, pages = {81-97}, department = {Department B{\"u}lthoff}, editor = {Waller, D. , L. Nadel}, publisher = {American Psychological Association}, address = {Washington, DC, USA}, booktitle = {Handbook of Spatial Cognition}, ISBN = {978-1-433-81204-0}, author = {Mohler, BJ and Di Luca, M and B{\"u}lthoff, HH} } @Inbook { CamposB2011, title = {Multimodal Integration during Self-Motion in Virtual Reality}, year = {2012}, month = {1}, pages = {603-628}, abstract = {This chapter begins by a brief description of some of the different types of simulation tools and techniques that are being used to study self-motion perception, along with some of the advantages and disadvantages of the different interfaces. Subsequently, some of the current empirical work investigating multisensory self-motion perception using these technologies will be summarized, focusing mainly on visual, proprioceptive, and vestibular influences during full-body self-motion through space. Finally, the implications of this research for several applied areas will be briefly described.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/Campos-Buelthoff-MultisensorySelfMotion.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.crcnetbase.com/doi/abs/10.1201/b11092-38}, editor = {Murray, M. M. , M. T. Wallace}, publisher = {CRC Press}, address = {Boca Raton, FL, USA}, series = {Frontiers in Neuroscience}, booktitle = {The neural bases of multisensory processes}, ISBN = {978-1-4398121-7-4}, DOI = {10.1201/b11092-38}, author = {Campos, JL and B{\"u}lthoff, HH} } @Inbook { 5961, title = {Markerless tracking of dynamic 3D scans of faces}, year = {2010}, month = {12}, pages = {255-276}, department = {Department B{\"u}lthoff}, department2 = {Department Sch{\"o}lkopf}, web_url = {http://mitpress.mit.edu/catalog/item/default.asp?ttype=2\&tid=12290}, editor = {Curio, C. , H. H. B{\"u}lthoff, M. A. Giese}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Dynamic Faces: Insights from Experiments and Computation}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {978-0-262-01453-3}, author = {Walder, C and Breidt, M and B{\"u}lthoff, HH and Sch{\"o}lkopf, B and Curio, C} } @Inbook { 5960, title = {Recognition of Dynamic Facial Action Probed by Visual Adaptation}, year = {2010}, month = {12}, pages = {47-65}, department = {Department B{\"u}lthoff}, web_url = {http://mitpress.mit.edu/catalog/item/default.asp?ttype=2\&tid=12290}, editor = {Curio, C. , H. H. B{\"u}lthoff, M. A. Giese}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Dynamic Faces: Insights from Experiments and Computation}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {978-0-262-01453-3}, author = {Curio, C and Giese, MA and Breidt, M and Kleiner, M and B{\"u}lthoff, HH} } @Inbook { 5211, title = {Perceptual Robotics}, year = {2008}, month = {5}, pages = {1481-1498}, abstract = {Perceptual functions are central to many applications in robotics and for the construction of efficient human–robot interfaces. The study of perception in biological systems has revealed important information-processing principles that have been converted to powerful applications in robotics and computer vision. The chapter first discusses two central theories of object recognition: model- and exemplar-based theories. A review of experimental results from the study of object recognition in biological systems suggests that exemplar-based approaches capture important properties of object recognition in the brain. We then discuss how very similar principles have been realized in highly efficient technical systems for object recognition and detection, including realizations that are based on biologically inspired neural architectures. Principles for the efficient processing of complex shapes can be extended to the representation of complex movements and actions. We illustrate this by first reviewing some properties of the cortical mechanisms of the recognition of complex movements and actions, focusing on principles that are useful for robotics applications. Again, exemplar-based approaches seem to capture important properties of motion recognition in the brain, and at the same time provide a powerful approach for building technical movement recognition systems. Finally, it is shown that the example-based framework is not only useful for recognition, but also provides the basis for powerful synthesis methods. As one example we discuss the synthesis of photorealistic three-dimensional (3-D) models of faces, exploiting correspondencebetween training examples. Related approaches have been developed for spatiotemporal patterns. We review a class of algorithms that permit the accurate modeling of movements and movement styles by interpolation between example trajectories with high relevance for the synthesis of movements, e.g., in humanoid robotics.}, department = {Department B{\"u}lthoff}, web_url = {http://springerlink.com/content/uj33g816678163pu/?p=04a41c4f43c840e187edf772a2d29536\&amp;amp;pi=63}, editor = {Siciliano, B. , O. Khatib}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Springer Handbook of Robotics, Part G}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {978-3-540-23957-4}, DOI = {10.1007/978-3-540-30301-5_64}, author = {B{\"u}lthoff, HH and Wallraven, C and Giese, MA} } @Inbook { 1929, title = {Funktionelle Prinzipien der Objekt- und Gesichtserkennung}, year = {2006}, pages = {107-116}, abstract = {Objekterkennung ist ein sehr komplexes Problem. Neben der Tatsache, dass Objekte von unterschiedlichen Ansichten aus unterschiedlich aussehen, aber trotzdem zu einem Objekt zusammengeh{\"o}ren, besteht noch das unterbestimmte und damit eigentlich unl{\"o}sbare Problem von einer zweidimensionalen Abbildung auf die dreidimen sionale Struktur des Objekts zu schliessen. Dies wird erst dadurch m{\"o}glich, dass wir Vorwissen {\"u}ber unsere Welt besitzen und damit die Interpretationsm{\"o}glichkeiten drastisch einschr{\"a}nken. Objekterkennung umfasst sowohl die Kategorisierung von Objekten in eine Kategorie, als auch die Identifikation eines bestimmten Objektes. Die Anforderungen an das System sind deshalb kontr{\"a}r: Neben der Generalisierung steht die Spezifit{\"a}t. Man unterscheidet 3 Hierarchieebenen, auf denen Objekterkennung statt fin den kann. Die derzeit diskutierten Objekterkennungsmodelle unterscheiden sich vor allem darin, ob eine dreidimensionale Rekonstruktion des gesehenen Objekts stattfindet oder nicht. In dem hier favorisierten Modell werden Objekte durch eine Anzahl von spezifischen Ansichten repr{\"a}sentiert, dadurch werden gemessene Reaktionszeitunterschiede und Fehlerraten auf unterschiedlichen Hierarchieebenen am besten erkl{\"a}rt.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/funktionelle_prinzipien_der_objekt_und_gesichtserkennung_1929[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/v01347538j824rp3/fulltext.pdf}, editor = {Karnath, H.-O. , P. Thier}, publisher = {Springer}, address = {Berlin, Germany}, series = {Springer-Lehrbuch}, edition = {2. ed.}, booktitle = {Neuropsychologie}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-540-28449-4}, DOI = {10.1007/3-540-28449-4_10}, author = {B{\"u}lthoff, HH and Ruppertsberg, A} } @Inbook { 3351, title = {Objektwahrnehmung}, year = {2006}, pages = {165-172}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Handbuch_der_allgemeinen_Psychologie_165-172_middle_3351[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://books.google.de/books/about/Handbuch_der_Allgemeinen_Psychologie_Kog.html?id=cY0QAQAAIAAJ\&redir_esc=y}, editor = {Funke, J. , P. A. Frensch}, publisher = {Hogrefe}, address = {G{\"o}ttingen, Germany}, series = {Handbuch der Psychologie ; 5}, booktitle = {Handbuch der Allgemeinen Psychologie: Kognition}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {de}, ISBN = {978-3-8017-1846-6}, author = {B{\"u}lthoff, I and B{\"u}lthoff, HH} } @Inbook { 2822, title = {Die Welt in unseren K{\"o}pfen}, year = {2004}, month = {1}, pages = {59-77}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/die_welt_in_unseren_koepfen_2822[0].pdf}, department = {Department B{\"u}lthoff}, editor = {Weitze, M.-D.}, publisher = {M{\"u}nchen, Germany}, address = {Deutsches Museum}, series = {Wissenschaft f{\"u}r Jedermann ; 3}, booktitle = {Von Molek{\"u}len, Spinnen und Menschen: was leistet die Evolution?}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-924183-93-7}, author = {B{\"u}lthoff, HH} } @Inbook { BulthoffR2003, title = {Funktionelle Prinzipien der Objekt- und Gesichtserkennung}, year = {2003}, pages = {95-106}, department = {Department B{\"u}lthoff}, editor = {Karnath, H.-O.}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Neuropsychologie}, ISBN = {3-540-67359-8}, author = {B{\"u}lthoff, HH and Ruppertsberg, AI} } @Inbook { 1132, title = {Image-based recognition of biological motion, scenes and objects}, year = {2003}, pages = {146-172}, abstract = {In this chapter we will review experiments using both explicit and implicit tasks to investigate object recognition using familiar objects (faces), unusual renderings of familiar objects (point-light walker), and novel scenes. While it is unlikely that participants would have already seen the particular renderings of familiar objects used in an experiment, they have definitely seen similar objects. For this reason, unfamiliar objects are used in many experiments to circumvent the problem of uncontrolled variations in prior exposure to objects. Another reason for using unfamiliar objects is that they allow us precise control over the types of features that are available for discrimination. How our visual system represents familiar and unfamiliar three-dimensional objects for the purpose of recognition is a difficult and passionately discussed issue. At the theoretical level a key question that any representational scheme has to address is how much the internal model depends on the viewing parameters. We will present 2 types of models regarding this issue and also address the question of whether the recognition process is more analytic or more holistic.}, department = {Department B{\"u}lthoff}, web_url = {http://psycnet.apa.org/psycinfo/2003-88086-006}, editor = {Peterson, M.A. , G. Rhodes}, publisher = {Oxford University Press}, address = {New York, NY, USA}, booktitle = {Perception of Faces, Objects, and Scenes: Analytic and Holistic Processes}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-19-516538-1}, author = {B{\"u}lthoff, I and B{\"u}lthoff, HH} } @Inbook { 2009, title = {Object recognition, neurophysiology}, year = {2002}, month = {11}, pages = {792-796}, abstract = {As viewing distance, viewing angle or lighting conditions change, so too does the image of an object which we see. Despite the seemingly endless variety of images that objects can project, the human visual system remains able to rapidly and reliably identify them across huge changes in appearance. Understanding how humans achieve this feat of recognition has long been a source of debate. Despite a concerted e ort, researchers are still undecided even about the most fundamental questions of how objects are represented in cortex. This chapter gives a brief overview of some theoretical approaches in the context of mainly neurophysiological evidence. It also considers the related question of objects within a physical context, that is the analysis of visual scenes. Scene analysis is relevant to the question of object recognition because scenes are initially recognised at a holistic, object-like level, providing a context or `gist' which itself in uences the speed and accuracy of recognition of the constituent objects (Rensink, 2000). A precise characterisation of gist remains elusive, but it may well include information such as global color patterns, spatial frequency content, correlational structure, anything which is useful for categorising or recognising the scene.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2009.pdf}, department = {Department B{\"u}lthoff}, editor = {Arbib, M. A.}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, series = {A Bradford book}, edition = {2. ed.}, booktitle = {The Handbook of Brain Theory and Neural Networks}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-262-01197-2}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Inbook { 1951, title = {Visuomotor control in flies and behavior-based agents}, year = {2002}, volume = {109}, pages = {89-117}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1951.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dl.acm.org/citation.cfm?id=832325}, editor = {Duro, R. J. , J. Santos, M. Grana}, publisher = {Physica-Verlag}, address = {Heidelberg, Germany}, series = {Studies in fuzziness and soft computing}, booktitle = {Biologically inspired robot behavior engineering}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-7908-1513-6}, author = {Huber, SA and B{\"u}lthoff, HH} } @Inbook { 167, title = {Using Realistic Virtual Environments in the Study of Spatial Encoding}, year = {2000}, month = {1}, pages = {317-332}, abstract = {Computer generated virtual environments have reached a level of sophistication and ease of production that they are readily available for use in the average psychology laboratory. The potential benefits include cue control, incorporation of interactivity and novelty of environments used. The draw-backs include limitations in realism and lack of fidelity. In this chapter we describe our use of virtual environments to study how 3D space is encoded in humans with special emphasis on realism and interactivity. We describe the computational methods used to implement this realism and give examples from studies concerning spatial memory for object form, spatial layout and scene recognition.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/using_realistic_virtual_environment_in_167[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/f91gweny8yc421p5/fulltext.pdf}, editor = {Freksa, C. , C. Habel, W. Brauer, C., K.F. Wender}, publisher = {Springer}, address = {Berlin, Germany}, series = {Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence}, booktitle = {Spatial Cognition II: Integrating Abstract Theories, Empirical Studies, Formal Methods, and Practical Applications}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-540-45460-8}, DOI = {10.1007/3-540-45460-8_23}, author = {Christou, C and B{\"u}lthoff, HH} } @Inbook { 631, title = {Visual Homing is possible without Landmarks: A Path Integration Study in Virtual Reality}, year = {2000}, pages = {97-134}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf631.pdf}, department = {Department B{\"u}lthoff}, editor = {von der Heyde, M. , H.H. B{\"u}lthoff}, publisher = {Max-Planck-Institute for Biological Cybernetics}, address = {T{\"u}bingen, Germany}, booktitle = {Perception and action in virtual environments: selected papers from the Cognitive and Computational Psychophysics Department, 1997 - 2000}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, author = {Riecke, BE and van Veen, HAHC and B{\"u}lthoff, HH} } @Inbook { 343, title = {Behavioral experiments in spatial cognition using virtual reality}, year = {1998}, volume = {1404}, pages = {447-467}, abstract = {Virtual reality is used as a novel tool for behavioral experiments on humans. Two environments, Hexatown and Virtual T{\"u}bingen, are presented. Experiments on cognitive maps carried out in the Hexatown environment are reported in this paper. Results indicate that subjects are able to acquire configuration knowledge of the virtual town even in the absence of physical movement. Simpler mechanisms such as associations of views with movements are also present. We discuss the results in relation to a graph-theoretic approach to cognitive maps.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/behavioral_experiments_in_spatial_cognition_using_vr_343[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.springerlink.com/content/h93unqrgb7mn5pjl/fulltext.pdf}, editor = {Freksa, C. , C. Habel, K. F. Wender}, publisher = {Springer}, address = {Berlin, Germany}, series = {Lecture notes in computer science : Lecture notes in artificial intelligence}, booktitle = {Spatial Cognition: An interdisciplinary approach to representing and processing spatial knowledge}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-540-64603-5}, DOI = {10.1007/3-540-69342-4_21}, author = {Mallot, HA and Gillner, S and van Veen, H-J and B{\"u}lthoff, HH} } @Inbook { 336, title = {Untersuchung komplexer Wahrnehmungs- und Verhaltensleistungen des Menschen in virtuellen Welten}, year = {1998}, volume = {9}, pages = {158-172}, department = {Department B{\"u}lthoff}, web_url = {http://www.lit-verlag.de/isbn/3-8258-3850-1}, editor = {R{\"u}gge, I. , B. Robben, E.Hornecker, F.W. Bruns}, publisher = {Lit Verlag}, address = {M{\"u}nster, Germany}, series = {Arbeitsgestaltung, Technikbewertung, Zukunft}, booktitle = {Arbeiten und begreifen: neue Mensch-Maschine-Schnittstellen}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-8258-3850-1}, author = {Distler, HK and van Veen, HAHC and Braun, SJ and B{\"u}lthoff, HH} } @Inbook { 437, title = {Virtuelle Realit{\"a}t als Methode der modernen Hirnforschung}, year = {1997}, month = {1}, pages = {241-260}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/virtuelle_welt_als_methode_der_modernen_hirnforschung_437[0].pdf}, department = {Department B{\"u}lthoff}, editor = {Krapp, H. , T. W{\"a}genbaur}, publisher = {Fink}, address = {M{\"u}nchen}, booktitle = {K{\"u}nstliche Paradiese, Virtuelle Realit{\"a}ten: K{\"u}nstliche R{\"a}ume in Literatur-, Sozial- und Naturwissenschaften}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-7705-3253-8}, author = {B{\"u}lthoff, HH and Foese-Mallot, B and Mallot, HA} } @Inbook { 608, title = {Bayesian decision theory and psychophysics}, year = {1996}, month = {12}, pages = {123-161}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/bayesian_decision_theory_and_psychophysics_608[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dl.acm.org/citation.cfm?id=239487}, editor = {Knill, D. , W. Richards}, publisher = {Cambridge University Press}, address = {Cambridge, Great Britain}, booktitle = {Perception as Bayesian Inference}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-521-46109-X}, author = {Yuille, AL and B{\"u}lthoff, HH} } @Inbook { 600, title = {Shape from texture: ideal observers and human psychophysics}, year = {1996}, month = {1}, pages = {287-321}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/shape_from_texture_ideal_observers_and_human_psychophysics_600[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://dl.acm.org/citation.cfm?id=239490}, editor = {Knill, D. , W. Richards}, publisher = {Cambridge University Press}, address = {Cambridge, UK}, booktitle = {Perception as Bayesian Inference}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-521-46109-X}, author = {Blake, A and B{\"u}lthoff, HH and Sheinberg, DL} } @Inbook { 717, title = {Shape from X: Psychophysics and Computation}, year = {1991}, pages = {305-330}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/shape_from_x_psychophysics_and_computation_717[0].pdf}, editor = {Landy, M.S. , J.A. Movshon}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Computational Models of Visual Processing}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-262-12155-7}, author = {B{\"u}lthoff, HH} } @Inbook { 753, title = {The MIT Vision Machine}, year = {1990}, pages = {492-529}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/the_mit_vision_machine_753[0].pdf}, editor = {Winston, P.H. , S.A. Shellard}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, booktitle = {Artificial Intelligence at MIT: Expanding Frontiers 2}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {0-262-23151-4}, author = {Poggio, T and Little, J and Gamble, E and Gillet, W and Geiger, D and Weinshall, D and Villalba, M and Larson, N and Cass, T and B{\"u}lthoff, HH and Drumheller, M and Oppenheimer, P and Yang, W and Hurlbert, A} } @Inbook { 842, title = {Computation of Motion and Position in the Visual System of the Fly (Musca): Experiments with Uniform Stimulation}, year = {1984}, month = {12}, pages = {149-152}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/computation_of_motion_and_position_in_the_visual_system_of_the_fly_musca_experiments_with_uniform_simulation_ROTATE_842[0].pdf}, editor = {Varju, D. , H. U. Schnitzler}, publisher = {Springer}, address = {Heidelberg, Germany}, series = {Proceedings in life sciences}, booktitle = {Localization and Orientation in Biology and Engineering}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, language = {en}, ISBN = {3-540-12741-0}, author = {B{\"u}lthoff, HH and Wehrhahn, C} } @Inbook { 848, title = {Three-Dimensional Reconstruction and Stereoscopic Display of Neurons in the Fly Visual System}, year = {1983}, pages = {183-205}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf848.pdf}, department = {Department G{\"o}tz}, editor = {Strausfeld, N.J. , M.E. Adams}, publisher = {Springer}, address = {Berlin, Germany}, series = {Springer series in experimental entomology}, booktitle = {Functional neuroanatomy}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, ISBN = {3-540-12742-9}, author = {Hengstenberg, R and B{\"u}lthoff, HH and Hengstenberg, B} } @Techreport { LeeB2012, title = {Helilab User Manual: Human Behavior and Flight Data Acquisition and Analysis}, year = {2012}, month = {5}, number = {196}, abstract = {We, here, introduce a flight simulator dedicated to collect both human behavior and flight data with high fidelity. This paper illustrates the current settings of the flight simulator, key issues in using the simulator, and the standard procedure of data acquisition and analysis.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/MPIK-TR-196a.pdf}, department = {Department B{\"u}lthoff}, institution = {Max Planck Institute for Biological Cybernetics}, author = {Lee, J-J and B{\"u}lthoff, HH} } @Techreport { 4490, title = {A novel immersive virtual environment setup for behavioural experiments in humans, tested on spatial memory for environmental spaces}, year = {2007}, month = {3}, number = {158}, abstract = {We present a summary of the development of a new virtual reality setup for behavioural experiments in the area of spatial cognition. Most previous virtual reality setups can either not provide accurate body motion cues when participants are moving in a virtual environment, or participants are hindered by cables while walking in virtual environments with a head-mounted display (HMD). Our new setup solves these issues by providing a large, fully trackable walking space, in which a participant with a HMD can walk freely, without being tethered by cables. Two experiments on spatial memory are described, which tested this setup. The results suggest that environmental spaces traversed during wayfinding are memorised in a view-dependent way, i.e., in the local orientation they were experienced, and not with respect to a global reference direction.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/mpik-tr-158_[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max-Planck-Institute for Biological Cybernetics, T{\"u}bingen, Germany}, language = {en}, author = {Meilinger, T and Riecke, BE and Berger, D and B{\"u}lthoff, HH} } @Techreport { 4373, title = {Simulating believable forward accelerations on a Stewart motion platform}, year = {2007}, month = {2}, number = {159}, abstract = {Here we present a study where human participants rated the believability of forward accelerations simulated with a hexapod motion platform equipped with a projection screen. Visual forward accelerations were presented together with brief forward surge translations and backwards pitches of the platform, and synchronous random up-down movements of the camera in the visual scene and the platform. The magnitudes of all of the parameters were varied independently across trials. Even though we found a high variability between participants, most believable simulation occured with strong visual accelerations combined with backwards pitches of the platform which approximately matched the visually simulated acceleration. This was contrary to a previous study, which had found most believable simulation when the platform movements simulated a much smaller acceleration than what was shown visually. Furthermore, surge translations increased believability if they qualitatively matched the magnitude of visual acceleration. The acceleration-deceleration profile of the surge translation and the magnitude and frequency range of the up-down movements had little effect on the believability. When strong visual acceleration cues were given, most participants reported trials as realistic even when the platform tilt rate was above thresholds for the vestibular canals reported in literature. These results can be used to optimize motion cueing algorithms for the simulation of linear accelerations in motion simulators.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/mpik-tr-159_4373[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {MPI f{\"u}r biologische Kybernetik, T{\"u}bingen, Germany}, language = {en}, author = {Berger, D and Schulte-Pelkum, J and B{\"u}lthoff, HH} } @Techreport { 4187, title = {Spatialized auditory cues enhance the visually-induced self-motion illusion (circular vection) in Virtual Reality}, year = {2005}, month = {10}, number = {138}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Riecke_05_TR-138__Spatialized\%20auditory\%20cues\%20enhance\%20the\%20visually-induced\%20self-motion\%20illusion\%20(circular\%20vection)\%20in\%20Virtual\%20Reality_[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, language = {en}, digital = {1}, author = {Riecke, BE and Schulte-Pelkum, J and Caniard, F and B{\"u}lthoff, HH} } @Techreport { 3371, title = {Selective Attention to Biological Motion}, year = {2005}, month = {5}, number = {139}, abstract = {A number of recent findings suggest that attention may play a larger role in the processing of biological motion than has been previously assumed. In the current study we assess individual thresholds for the detection of masked pointlight walkers and obtain performance measures on a range of attention related tasks. Our results indicate a strong and consistent correlation between selective attention and the processing of biological motion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf3371.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Chandramouli, C and Thornton, IM and B{\"u}lthoff, HH} } @Techreport { 2774, title = {The MPI VideoLab: A system for high quality synchronous recording of video and audio from multiple viewpoints}, year = {2004}, month = {5}, number = {123}, abstract = {The MPI VideoLab is a custom built, flexible digital video- and audio recording studio that enables high quality, time synchronized recordings of human actions from multiple viewpoints. This technical report describes the requirements to the system in the context of our applications, its hardware- and software equipment and the special features of the recording setup. Important aspects of the hardware and software implementation are discussed in detail.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2774.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Kleiner, M and Wallraven, C and B{\"u}lthoff, HH} } @Techreport { 2574, title = {Influence of display device and screen curvature on perceiving and controlling simulated ego-rotations from optic flow}, year = {2004}, month = {2}, number = {122}, abstract = {This study investigated how display parameters influence humans’ ability to control simulated egorotations from optic flow. The literature on visual turn perception reports contradictory data, which might be partly due to the different display devices used in these studies. In this study, we aimed at disentangling the influence of display devices, screen curvature, and field of view (FOV) on the ability to control simulated ego-rotations solely from visual information. In Experiment 1, FOV and display device (projection screen vs. head-mounted display (HMD)) was manipulated. In Experiment 2, screen curvature and FOV were varied. Subjects’ task was to perform visually simulated self-rotations with target angles between 45 and 270 degree. Stimuli consisted of limited lifetime dots on a dark background, and subjects used a joystick to control the turning angle of the visual stimulus. In Experiment 1, performance was tested in a within-subject design, using a curved projection screen (FOV 84 degree \(\times\) 63 degree), a HMD (40 degree \(\times\) 30 degree), and blinders (40 degree \(\times\)30 degree) that restricted the FOV on the screen. Performance was best with the screen (gain factor 0.77) and worst with the HMD (gain 0.57). We found a significant difference between blinders (gain 0.73) and HMD, which indicates that different display devices can influence ego-motion perception differentially, even if the physical FOVs are equal. In Experiment 2, screen curvature was found to influence the perception of ego-rotations: At identical FOVs of 84 degree, participants undershot target angles on the curved screen (gain 0.84), while they overshot target angles on the flat screen (gain 1.08). Perceptual mechanisms that may underlie these results will be discussed. We conclude the following: First, differences between display devices (HMD vs. curved projection screen) are more critical than the FOV for the perception of ego-rotations, with projection screens being better than HMDs. Second, screen curvature significantly influences performance for visually simulated egorotations: Compared to the flat screen, the curved screen enhanced the perception of ego-rotations. These findings have relevant implications for the design of motion simulators.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2574.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Schulte-Pelkum, J and Riecke, BE and von der Heyde, M and B{\"u}lthoff, HH} } @Techreport { 2356, title = {Do Visual Cues Influence the Perception of Earth Vertical?}, year = {2003}, month = {8}, number = {116}, abstract = {Accurate perception of the direction of earth vertical can be achieved by sensing the direction of gravity in body coordinates. This is equivalent to knowing body orientation in world coordinates. There are a number of visual and non-visual cues we can use to estimate earth vertical relative to the body. Non-visual cues include the sensation of gravity and forces due to acceleration, and they can be measured by the somatosensory and vestibular systems. These systems cannot always tell us directly about the direction of gravity because they signal gravito-inertial (GI) force, which is the sum of all forces acting on the body at a given time. For example, if one is accelerating, the GI force is the sum of the force due to acceleration and the force due to gravity. In these situations, the direction of GI force does not indicate the direction of earth vertical, but visual cues may be used to resolve the ambiguity. We conducted an experiment in which the direction of GI force was manipulated by pitching observers (rotation about the body’s x-axis) on a motion platform. Their task was to indicate the direction of earth vertical using a pointing device. In some conditions, no visual stimulus was presented. In other conditions, observers were presented with a visual scene depicting acceleration over a flat, textured ground plane. Two cues in the visual display contained information relevant to judging the direction of earth vertical: 1) the location and orientation of the horizon and 2) the rate of acceleration over the ground plane. We present a model of how these visual and non-visual cues might be used to generate an estimate of the direction of earth vertical. Observer responses are compared with the predictions of this model. Results suggest that under the conditions of the present experiment, visual cues had very little effect, and perception of earth vertical was estimated primarily on the basis of vestibular and somatosensory cues.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2356.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, language = {en}, author = {MacNeilage, P and Berger, DR and von der Heyde, M and Banks, S and B{\"u}lthoff, HH} } @Techreport { 2068, title = {Interactions between facial form and facial motion during the processing of identity}, year = {2002}, month = {11}, number = {94}, abstract = {Previous research has shown that facial motion can carry information about age, gender, emotion and, at least to some extent, identity. With respect to identity, two important issues remain unresolved: first it is unclear to what extent purely non-rigid facial motion contributes to the processing of identity. Secondly, as most previous studies have involved techniques that severely reduced available cues to facial form (e.g., blurring or pixelation), it is not really known how, if at all, information concerning facial form and facial motion interact. By combining recent computer animation techniques with psychophysical methods, we show that during the computation of identity the human face recognition system accesses and integrates both types of information: individual non-rigid facial motion and individual facial form. This has important implications for cognitive and neural models of face perception, which currently emphasize a separation between the processing of invariant aspects (facial form) and changeable aspects (facial motion) of faces.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2068.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Knappmeyer, B and Thornton, IM and B{\"u}lthoff, HH} } @Techreport { 4782, title = {Psychophysical results from experiments on recognition \& categorisation}, year = {2002}, month = {11}, number = {IST-2000-29375}, abstract = {A firm understanding of how the human visual system recognises and categorises objects is important in order to build a successful cognitive vision system. We have reviewed the relevant literature both on visual object recognition and categorisation (chapter 1). Based on this review and the technical annex of this project we have addressed several topics in a series of psychophysical experiments, focusing on structural aspects of recognition memory, object similarity in the context of categorisation, shape transformations in categorisation, the role of context in recognition and categorisation, and the interplay between object motion and shape for categorisation decisions (chapter 2). Based on our psychophysical results we present our view on recognition and categorisation, proposing an integrative framework that serves as a theoretical basis for a computational recognition system grounded in cognitive research (chapter 3).}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/GraSchWalBul2002_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://fhweb.imvs.ch/ppt/content/pub/psychophysical-results-from-experiments-on-recognition-categorisation}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Fachhochschule Nordwestschweiz, Information Society Technologies Programme, Cognitive Vision Systems}, language = {en}, author = {Graf, M and Schwaninger, A and Wallraven, C and B{\"u}lthoff, HH} } @Techreport { 2004, title = {The Dynamics of Visual Pattern Masking in Natural Scene processing: A MEG-Study}, year = {2002}, month = {10}, number = {103}, abstract = {We investigated the mechanisms of pattern masking in a scene recognition task by recording simultaneously psychophysical performance and magnetic brain activity using magnetoencephalography (MEG). Photographs of natural scenes were displayed for various durations and then immediately followed by a pattern mask. We were able to identify the transient brain activation caused by the switching from scene to mask. The latency of this mask-transient signals the earliest cortical interaction between target and mask. The scenes alone elicited a transient occipital activation starting 70ms after stimulus onset, peaking at 110ms and reaching a minimum at 160ms. By comparing psychophysical performance with the latency of the mask transient and the dynamics of the undistorted processing of the scene at various SOAs we found that the initial occipital activation peak reflects processes vulnerable to pattern masking. The additional activation from the mask falling within this target-processing activity significantly reduces recognition performance. We found no measurable impact of mask activation later than 160ms after target onset. Our results indicate that the information necessary for the reliable recognition of a scene among a set of distracters can be extracted within about 90ms of cortical processing. Our data support the view, that the effect of the pattern backward mask occurs by overwriting a visual buffer in which the scene is stored during analysis.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf2004.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Rieger, JW and Braun, C and Gegenfurtner, KR and B{\"u}lthoff, HH} } @Techreport { 1624, title = {Grasp effects of the Ebbinghaus illusion: Obstacle-avoidance is not the explanation}, year = {2002}, month = {6}, number = {91}, abstract = {It is often assumed that the primate brain processes visual information in two different streams, one for visual awareness (or perception) and one for motor performance. Previous reports that the Ebbinghaus illusion deceives perception but not grasping, seemed to provide strong evidence for this perception versus action hypothesis. The dichotomy between an action stream and a perceptual stream appeared to be fundamental enough to be reflected in the overt behavior of non neurological, healthy humans. Contrary to this view, we show that the Ebbinghaus illusion affects grasping to the same extent as perception. We also show that the grasp effects cannot be accounted for by non perceptual obstacle avoidance mechanisms, as was recently suggested (Haffenden \&amp; Goodale, 2000; Haffenden, Schiff, \&amp; Goodale, 2001). Instead, even subtle variations of the Ebbinghaus illusion affect grasping in the same way as perception. Our results suggest that the same signals are responsible for the perceptual effects and for the motor effects of the Ebbinghaus illusion. This casts doubt on one line of evidence which has often been counted as being especially strong in favor of the perception versus action hypothesis.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/MPIK-TR-91.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Franz, V and B{\"u}lthoff, HH and Fahle, M} } @Techreport { 1609, title = {Interactions between view changes and shape changes in picture-picture matching}, year = {2002}, month = {5}, number = {95}, abstract = {Four studies presented pictures of different morphs of novel, complex, three-dimensional objects, similar to objects which we must identify in the real world. We investigated how viewpoint changes influence our ability to discriminate between morphs. View changes had a powerful effect on performance in picture-picture matching tasks when similarly shaped morphs had to be discriminated. Shape changes were detected faster and more accurately when morphs were depicted from the same rather than different views. In contrast, view change had no effect when dissimilarly shaped morphs had to be discriminated. This interaction between the effects of view change and shape change was found for both simultaneous stimulus presentation and for sequential presentation with interstimulus intervals of up to 3600ms. The interaction was found following repeated presentations of the stimuli prior to the matching task and following practice at the matching task as well as after no such pre-exposure to the stimuli or to the task. The results demonstrate the importance of view changes relative to other task manipulations in modulating the shape discrimination abilities of the human visual recognition system.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1609.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Lawson, R and B{\"u}lthoff, HH and Dumbell, S} } @Techreport { 1646, title = {A Brief Introduction to Cortical Representations of Objects}, year = {2002}, month = {2}, number = {97}, abstract = {To understand how objects are recognized and represented in the human brain is still one of the ultimate goals of cognitive science. In this article, we will collect evidence from mainly neurophysiological studies which suggest that object recognition is achieved by hierarchical processing in the brain and that the representation of objects is distributed and view-based. Furthermore, these studies propose that the temporal coherence of the visual input plays a fundamental role in the learning of object representations.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1646.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Techreport { 1550, title = {Relearning of metric relations in a familiar environment}, year = {2002}, month = {1}, number = {90}, abstract = {The ability of spatial memory to adapt to changes in an environment was investigated in an experiment, where participants navigated in a virtual reality reconstruction of a city they were familiar with. In the learning phase, participants used a special bike to pedal through a reconstruction of the inner city of T{\"u}bingen, Germany. Their task was to memorize the locations of the buildings in the city. In the experimental conditions, the city was scaled nonuniformly compared to the actual city, that is the north-south axis was streched or compressed relative to the east-west axis. In the control condition, the proportions of the virtual city were not distorted. In the test phase participants were asked to judge distances between buildings from memory by both, verbal magnitude estimation and navigation. They had to estimate all possible distances between 8 pairs of houses. Distance estimates differed between scaling conditions, but they reflected the scaling of the virtual environment only in one condition. Therefore, it could be shown, that modifications of a familiar environment on a purely metrical level affect spatial representations, but there is only weak evidence that distance estimates mirror the distortions of the virtual environments.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1550.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Rothkegel, R and Mallot, HA and B{\"u}lthoff, HH} } @Techreport { 1324, title = {Effects of Pointing Direction and Direction Predictability on Event-related Lateralisations of the EEG}, year = {2001}, month = {6}, number = {88}, abstract = {In two experiments, we investigated hemispheric EEG differences in 9(12) healthy volunteers during pointing to lateral and central targets. The questions addressed were whether horizontal pointing direction and the predictability of pointing direction modulated hemispheric differences (event-related lateralisations of the EEG = ERLs). To vary pointing direction predictability, targets were displayed either randomly at one of nine different positions on a screen (‘random‘) or at the same horizontal position in five subsequent trials (''sequenced'') while vertical positions varied randomly. ERLs varied with pointing direction. This was true across changes in target eccentricity and pointing distance. Foci of the ERLs were in premotor, motor and parietal cortex, reflecting the critical involvement of these areas in the control of visually guided reaching. Direction predictability reduced the parietal ERL before pointing onset, probably reflecting a lesser effort in visuomotor transformation. Predictability also added an additional component to the early ERLs after target onset and increased direction effects during movement.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/effects_of_pointing_direction_and_direction_predictability_on_event-related_lateralisations_of_the_eeg_1324[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Berndt, I and Franz, V and B{\"u}lthoff, HH and Wascher, E} } @Techreport { 634, title = {Temporal adaptation and the role of temporal contiguity in spatial behavior}, year = {2000}, month = {12}, number = {85}, abstract = {Rapid and accurate interaction with the world requires that proper spatial and temporal alignment between sensory modalities be maintained. The introduction of a misalignment (either spatial or temporal) impairs performance on most spatial tasks. For over a century, it has been known that a few minutes of exposure to a spatial misalignment can induce a recalibration of intersensory spatial relationships, a phenomenon called Spatial Adaptation. Here, we present evidence that the sensorimotor system can also adapt to intersensory temporal misalignments, a phenomena that we call Temporal Adaptation. Temporal Adaptation is striking parallel to Spatial Adaptation, and has strong implications for the understanding of spatial cognition and intersensory integration.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf634.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Cunningham, DW and Chatziastros, A and von der Heyde, M and B{\"u}lthoff, HH} } @Techreport { 1548, title = {Learning to Recognize Objects}, year = {2000}, month = {10}, number = {84}, abstract = {In this report we review a large body of literature describing how experience affects recognition. Both neurophysiology and psychophysics provide clear evidence for the development of recognition over time. In particular, we show how perceptual learning in recognition tasks can be directly linked to learning in feature tuned inferotemporal lobe neurons in the primate brain. The environment as we experience it, is so structured that potentially very different images appearing in close temporal succession are likely to be views of the same object. We argue that this temporal structure forms the basis of a tendency (a prior in the sense of Bayesian Statistics) of the human visual system to associate images of objects together over short periods of time.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1548.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics T{\"u}bingen}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Techreport { 1203, title = {Visual Homing is possible without Landmarks: A Path Integration Study in Virtual Reality}, year = {2000}, month = {9}, number = {82}, abstract = {The literature often suggests that proprioceptive and especially vestibular cues are required for navigation and spatial orientation tasks involving rotations of the observer. To test this notion, we conducted a set of experiments in virtual reality where only visual cues were provided. Subjects had to execute turns, reproduce distances or perform triangle completion tasks: After following two prescribed segments of a triangle, subjects had to return directly to the unmarked starting point. Subjects were seated in the center of a half-cylindrical 180 degree projection screen and controlled the visually simulated ego-motion with mouse buttons. Most experiments were performed in a simulated 3D field of blobs providing a convincing feeling of self-motion (vection) but no landmarks, thus restricting navigation strategies to path integration based on optic flow. Other experimental conditions included salient landmarks or landmarks that were only temporarily available. Optic flow information alone proved to be sufficient for untrained subjects to perform turns and reproduce distances with negligible systematic errors, irrespective of movement velocity. Path integration by optic flow was sufficient for homing by triangle completion, but homing distances were biased towards mean responses. Additional landmarks that were only temporarily available did not improve homing performance. However, navigation by stable, reliable landmarks led to almost perfect homing performance. Mental spatial ability test scores correlated positively with homing performance especially for the more complex triangle completion tasks, suggesting that mental spatial abilities might be a determining factor for navigation performance. Compared to similar experiments using virtual environments (P{\'e}ruch et al., 1997; Bud, 2000) or blind locomotion (Loomis et al., 1993), we did not find the typically observed distance undershoot and strong regression towards mean turn responses. Using a virtual reality setup with a half-cylindrical 180 degree projection screen allowed us to demonstrate that visual path integration without any vestibular or kinesthetic cues is sufficient for elementary navigation tasks like rotations, translations, and homing via triangle completion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1203.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Riecke, BE and van Veen, HAHC and B{\"u}lthoff, HH} } @Techreport { 1546, title = {A prior for global convexity in local shape from shading}, year = {2000}, month = {7}, number = {81}, abstract = {To solve the ill-posed problem of shape-from-shading, the visual system often relies on prior assumptions, for example, that the illumination is from above or that the viewpoint is from above. Here we demonstrate that a third prior assumption is used, namely that the surface is globally convex. Using unfamiliar randomly corrugated surfaces, we find that performance in a local shape discrimination task is significant higher when the surfaces are globally convex than when they are globally concave. The results are surprising because the qualitative global shape of the surfaces are perceptually unambiguous. The results thus generalize findings such as the hollow potato illusion (Hill H. \& Bruce V. 1994) which considered global shape perception only.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1546.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Langer, MS and B{\"u}lthoff, HH} } @Techreport { 1544, title = {Categorical Perception of Familiar Objects}, year = {2000}, month = {3}, number = {79}, abstract = {We investigated whether familiar, 3-D objects are categorically perceived in the same way that other visual stimuli (e.g., colour and faces) are perceived as categorical. A continuum of shape change between fifteen pairs of objects was created and the images along the continuum were used as stimuli. In Experiment 1 participants were first required to discriminate pairs of images of objects that lay along the shape continuum. Then participants were asked to classify each morph-image into one of two pre-specified shapes. We found evidence for categorical perception in some but not all of our object pairs. In Experiment 2 we lloked in more detail at specific object pairs by increasing the difficulty of the discrimination task and found that more object pairs were categorically perceived. In Experiment 3 similarity ratings for each object pair were collected. These similarity scores correlated with the degree of perceptual categorisation found for the object pairs. Our findings suggest that familiar objects are perceived categorically and that categorical perception is closely tied to inter-object perceptual similarity.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1544.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Newell, FN and B{\"u}lthoff, HH} } @Techreport { 1543, title = {Effects of Temporal Association on Recognition Memory}, year = {2000}, month = {3}, number = {78}, abstract = {The influence of temporal association on the representation and recognition of objects was investigated. Subjects were presented sequences of novel faces in which the identity of the face changed as the head rotated. The subjects showed a tendency to treat the views as if they were of the same person. The results counter the proposal that object views are recognised simply on the basis of objective, structural components. Instead, they suggest that we are continuously associating views of objects to support later recognition, and that we do so not only on the basis of their physical similarity, but also their correlated appearance in time.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1543.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Wallis, GM and B{\"u}lthoff, HH} } @Techreport { 1545, title = {Viewpoint dependence in visual and haptic object recognition}, year = {2000}, month = {3}, number = {80}, abstract = {On the whole, we recognise objects best when we see them from a familiar view and worse from views that were previously occluded from sight. Unexpectedly, we found haptic object recognition to also be viewpoint-specific, even though hand movements were unrestricted. This was due to the hands preferring the back ''view'' of the objects. Furthermore, when the sensory modalities (visual vs. haptic) differed between learning an object and recognising it, we found that recognition performance was best when the objects were also rotated back-to-front between learning and recognition. Our data indicate that the visual system recognises the front view of the objects best whereas the hand recognises the objects best from the back.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1545.pdf}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, language = {en}, author = {Newell, F and Ernst, MO and Tjan, BS and B{\"u}lthoff, HH} } @Techreport { 1542, title = {Vision and Action in Virtual Environments: Modern Psychophysics in Spatial Cognition Research}, year = {1999}, month = {12}, number = {77}, abstract = {The classical psychophysical approach to human perception has been to study isolated aspects of perception using well-controlled and strongly simplified laboratory stimuli. This so-called cue reduction technique has successfully led to the identification of numerous perceptual mechanisms, and has in many cases guided the uncoverage of neural correlates (see chapters elsewhere in this volume). Its limitations, however, lie in the almost complete ignorance of the intimate relationship between action, perception and the environment in which we live. Real world situations are so different from the stimuli used in classical psychophysics and the context in which they are presented, that applying laboratory results to daily life situations often becomes impractical if not impossible. At the Max-Planck-Institute for Biological Cybernetics in T{\"u}bingen we pursue a behavioral approach to human action and perception that proves especially well suited for studying more complex cognitive functions, such as object recognition and spatial cognition. The recent availability of high-fidelity ''Virtual Reality'' environments enables us to provide subjects a level of sensory realism and dynamic sensory feedback that approaches their experiences in the real world. At the same time, we can keep the ultimate control over all stimulus aspects that are required by the rules of psychophysics. In this chapter, we take a closer look at these developments in spatial cognition research and present results from several different experimental studies that we have conducted using this approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1542.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {B{\"u}lthoff, HH and van Veen, HAHC} } @Techreport { 1346, title = {The Effects of Visual Illusions on Grasping}, year = {1999}, month = {11}, number = {74}, abstract = {In recent years the view has been advocated that the motor system is immune to visual size illusions. This is regarded as a consequence of a fundamental division of labor in the primate brain: vision for action versus vision for perception. We tested this claim for the Mueller-Lyer illusion and the Parallel-Lines illusion. Both illusions clearly affected grasping. The effects on grasping were similar though not perfectly equal to the effects on perception. We present evidence that these small differences are due to problems in matching the perceptual and the motor tasks. We argue that grasping is an inherently unipolar measure because only one object can be grasped with the same hand at a time, while perceptual measures usually are bipolar because they require a comparison of two objects. We show that this difference is a central problem in matching the perceptual and the motor task.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/effects_of_visual_illusions_on_grasping_1346[0]_1346[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Franz, V and Fahle, M and B{\"u}lthoff, HH and Gegenfurtner, K} } @Techreport { 1540, title = {The perception of spatial layout in a virtual world}, year = {1999}, month = {11}, number = {75}, abstract = {The perception and recognition of spatial layout of objects within a three-dimensional setting was studied using a virtual reality (VR) simulation. The subject's task was to detect the movement of one of several objects across the surface of a tabletop after a retention interval during which time all objects were occluded from view. Previous experiments have contrasted performance in this task after rotations of the observer's observation point with rotations of just the objects themselves. They found that subjects who walk or move to new observation points perform better than those whose observation point remains constant. This superior performance by mobile observers has been attributed to the influence of non-visual information derived from the proprioceptive or vestibular systems. Our experimental results show that purely visual information derived from simulated movement can also improve subject's performance, although the performance differences manifested themselves primarily in improved response times rather than accuracy of the responses themselves.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1540.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Christou, C and B{\"u}lthoff, HH} } @Techreport { 1539, title = {Perception of shape from shading on a cloudy day}, year = {1999}, month = {10}, number = {73}, abstract = {The human visual system has a remarkable ability to interpret smooth patterns of light and shade on a surface in terms of 3-D surface geometry. Classical studies of shape-from-shading have assumed that surface luminance depends on the local surface orientation. This classical shading model holds, for example, on a sunny day. A common situation in which the classical model fails to hold, however, is a diffuse lighting condition such as on a cloudy day. Here we report on the first set of psychophysical experiments that explicitly address perception of shape-from-shading under diffuse lighting. Our main findings are that depth discrimination under diffuse lighting is superior to that predicted by a classical sunny day model, and by a model in which depth varies with perceived luminance i.e. dark means deep. We find that performance is correlated with the latter model, however, under both diffuse source and point source lighting. The results imply that the visual system uses multiple models when perceiving shape-from-shading.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1539.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Langer, MS and B{\"u}lthoff, HH} } @Techreport { 649, title = {The effect of field of view and surface texture on driver steering performance}, year = {1999}, month = {10}, number = {71}, abstract = {In the present study we investigated steering accuracy in terms of our ability to keep to the middle of a lane in a fixed-base driving simulator. In particular, we studied the dependence of steering accuracy on the visibility of different road sections, on the assumption that performance reflects the importance of different road sections in guiding steering. Other influences on steering accuracy - including the presence of textural cues, in the form of a textured road surface, and the horizontal field of view - were also investigated. We found that textural cues can improve accuracy in lateral lane control, presumably by providing strong optical flow, and that driving accuracy is little affected by increasing the horizontal field of view from 40 deg to a full field of 180 deg.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf649.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Chatziastros, A and Wallis, GM and B{\"u}lthoff, HH} } @Techreport { 650, title = {The use of optical flow and splay angle in steering a central path}, year = {1999}, month = {10}, number = {72}, abstract = {In the present experiment we investigated the importance of velocity information during a lane-centering task between the walls of a simulated tunnel. We varied both simulated velocity and the spatial frequency content of the walls' surfaces, in order to address the influence of each parameter on steering performance. Further, this performance was compared to the effectiveness of lateral control using lane border information. We found that drivers used both velocity and spatial frequency information to maintain a centered position on a path, and that the presence of lane borders improved accuracy. The results suggest that multiple sources of visual information, rather than mere demarcating lines, are used for lateral control on a straight path.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf650.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Chatziastros, A and Wallis, G and B{\"u}lthoff, HH} } @Techreport { 1536, title = {Viewpoint information provided by a familiar environment facilitates object identification}, year = {1999}, month = {3}, number = {68}, abstract = {We studied whether contextual information regarding an observer's location within a familiar scene could influence the identification of objects. The context was provided by a 3D virtual living room, which allowed natural familiarization of the scene and objects together with a high level of interactivity. Results of initial self-orientation judgments obtained in the room showed observers could make accurate judgments of their instantaneous orientation with respect to a reference point. We wanted to know if this information could in turn be used as an aid to identify objects from unfamiliar viewpoints. Our main experiment showed that after familiarization of objects within the virtual room, the presence of the room during identification produced significantly fewer errors than when the objects were shown in isolation. This reduction in error was attributed to the provision of a consistent reference frame by the room. This was tested by a control experiment, in which we randomly varied the orientation of the objects with respect to the room. In this case, the observer's relative orientation with respect to the objects could not be derived from the room. Results showed that recognition accuracy dropped significantly in this case. The results in general suggest that object identification can be aided by knowledge of where we are in space and in which direction we are looking.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1536.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Christou, C and Tjan, BS and B{\"u}lthoff, HH} } @Techreport { 1535, title = {Grasping visual illusions: No evidence for a dissociation between perception and action}, year = {1999}, month = {2}, number = {67}, abstract = {Neuropsychological studies motivated the theory that the primate visual system might be organized into two parallel pathways, one for conscious perception and one to guide action (Milner \& Goodale, 1995). Supporting evidence in healthy humans seemed to come from a dissociation in visual illusions: Aglioti, DeSouza, and Goodale (1995) reported that the Ebbinghaus (or Titchener) Illusion deceived perceptual judgments of size, but only marginally influenced the size estimates used in grasping. Here we show that identical effects of the illusion are found if the perceptual and grasping tasks are appropriately matched. We show that the differences found by Aglioti et al. (1995) can be accounted for by a hitherto unknown, super additive effect in the illusion. We conclude that the illusion does not provide evidence for the existence of two distinct pathways for perception and action in the visual system.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Franz, V and Gegenfurtner, K and B{\"u}lthoff, HH and Fahle, M} } @Techreport { 1530, title = {Differences between Active-Explorers and Passive-Observers in Virtual Scene Recognition}, year = {1998}, month = {6}, number = {62}, abstract = {Recognition of a newly learned environment from both familiar and novel perspectives was investigated using a 3D-computer model in which observers made simulated translational and rotational head movements. They were encouraged to move around the environment to find and acknowledge spatially localized coded markers. During each acknowledgement the observers' viewing parameters were stored and later used for stimulus generation. The observers' movements were restricted to a small region of the environment and complete rotational head-movements were not allowed. To test the importance of making volitional movements during familiarization, two groups of observers were tested: active-explorers initiated their own movement through the environment while the passive-observers watched a playback of these movements. In the recognition tests, all participants were shown both familiar and novel views of both acknowledged and unacknowledged locations. Testing took place immediately and was repeated after 7 days. Results indicate that observers always found novel perspective views more difficult to recognize than familiar views, and surprise locations more difficult than acknowledged locations. The principle difference between active and passive was an advantage in recognizing novel direction views by active-explorers. This difference became more pronounced over the course of seven days. The results provide evidence for egocentric encoding and suggest that this can be reduced, if only marginally, by facilitating observer self-locomotion during learning.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1530.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Christou, C and B{\"u}lthoff, HH} } @Techreport { 1528, title = {Modeling biological sensorimotor control with genetic algorithms}, year = {1998}, month = {5}, number = {60}, abstract = {Evolutionary optimization of sensorimotor control has lead to matched filter neurons in the visual system of flies that are specialized to certain visual motion patterns. We apply the technique of genetic algorithms in order to model parts of the sensor system and behavior of an artificial agent. The agents are rather simple systems with only four sensors. We will show how genetic algorithms can be applied to evolve simple matched filters that analyze the visual motion information for the task of obstacle avoidance. We compare the agents' sensorimotor control to that of flies. Further we test the optimization performance of the genetic algorithms. We can show that the use of binary or Gray coding has no significant influence on our optimization results and the speed of convergence. Real value coding leads on average to slightly smaller maximal fitness values. The use of a combination of mutation and crossover leads to high fitness individuals and a high fitness population.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1528.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Huber, SA and Mallot, HA and B{\"u}lthoff, HH} } @Techreport { 1525, title = {Navigating through a Virtual City: Using Virtual Reality Technology to Study Human Action and Perception}, year = {1998}, month = {3}, number = {57}, abstract = {The introduction of virtual reality technology in the field of human perception and behaviour research has spawned many new research initiatives. The paper outlines the motivations of researchers in this field to start using virtual environments for their studies by presenting two such studies conducted in our laboratory. First, we discuss how we are building a large virtual model of the city of T{\"u}bingen and how we are using it for our research on human navigation behaviour. Second, we present data on the phenomenon that observers tend to underestimate the perceived speed of their movement through a virtual environment, and we discuss what implications these results have for the design of virtual environments.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {van Veen, H-J and Distler, H and Braun, S and B{\"u}lthoff, HH} } @Techreport { 1524, title = {On Robots and Flies: Modeling the visual orientation behavior of flies}, year = {1998}, month = {2}, number = {56}, abstract = {Although artificial and biological systems face similar sensorimotor control problems, until today only a few attempts have been made to implement specific biological control structures on robots. Nevertheless, the process of designing the sensorimotor control of a robot can contribute to our understanding of these mechanisms and can provide the basis of a critical evaluation of existing biological models. Flies have developed a specialized visuomotor control for tasks such as course stabilization, fixation and approach towards stationary objects, tracking of moving objects, and landing, which are based on the analysis of visual motion information. Theoretical and experimental results suggest that in flies the visuomotor control for course stabilization as well as fixation and approach towards stationary objects may be implemented at least partially by one common sensory circuit. We present agents with a visuomotor controller that regulates the two behaviors of course stabilization and object fixation. To test this controller under real world conditions, we implemented it on a miniature robot. We have been able to show that, in addition to course stabilization and object fixation, the robot also approaches stationary objects.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Huber, S and Franz, M and B{\"u}lthoff, HH} } @Techreport { 1520, title = {Viewpoint Effects in Naming Silhouette and Shaded Images of Familiar Objects}, year = {1998}, month = {1}, number = {54}, abstract = {We studied the visual features that support efficient entry-level object recognition by measuring naming latencies for different views of artifacts and four-legged animals that were shown as shaded images or as silhouettes. Experiment 1 revealed important differences in performance for the two renderings. Although three-quarter views of animals were recognized relatively quickly when shaded, they were not recognized quickly when presented as silhouettes. The same was true of artifacts when they were seen from the back. Experiment 2 used ideal-observer analyses to confirm that these effects could not be accounted for by differences in the intrinsic complexity of the stimuli. Together, these findings indicate that, for human observers, the shape of an object's bounding contour does not serve as a direct visual coding of the object, although it might be used as a first index into visual memory. These results also indicate that shading is important for recognizing objects in certain views. It remains unclear, however, what features are provided by shading. Shading might be used to derive a more precise part-based description of the object, or it might be used to extract surface properties or distinctive features and their spatial relations that are themselves elements of a view-based description of the object.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1520.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Liter, JC and Tjan, BS and B{\"u}lthoff, HH and K{\"o}hnen, N} } @Techreport { 1516, title = {View canonicality affects naming but not name verification of common objects}, year = {1997}, month = {6}, number = {51}, abstract = {Previous studies suggest that there are ''canonical'' viewpoints from which objects are identified most readily. Object naming has been the primary objective measure used to assess view canonicality, but this task has not proven adequate in distinguishing the many explanations of this phenomenon that have been offered. We examine object naming (Experiment 1a) and name verification (Experiments 1b and 2) to better understand the origin and nature of canonical view effects in recognition. In the name verification experiments, observers read an object name and then viewed an image of an object and decided as quickly as possible whether the image matched the name. The stimuli were images of 3D computer models of seven common objects. Each object was rendered from one canonical viewpoint2 (determined in a separate experiment by Blanz, Tarr, B{\"u}lthoff, \& Vetter, 1996) and two noncanonical viewpoints. Observers named the objects faster in canonical views, but performance was not affected by viewpoint in either name verification experiment, even on the first presentation of each view. We interpret these results in terms of a view-based similarity model. Naming is slow for noncanonical views because they are similar to stored views of more than one object, leading to response competition. The name verification task reduces the space of relevant views in long-term memory that must be compared to an input view, which for the views studied here minimized the likelihood of confusions and eliminated differences in response times for different views.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1516.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Liter, JC and B{\"u}lthoff, HH} } @Techreport { 1511, title = {Homing by parameterized scene matching}, year = {1997}, month = {2}, number = {46}, abstract = {In visual homing tasks, animals as well as robots can compute their movements from the current view and a snapshot taken at a home position. Solving this problem exactly would require knowledge about the distances to visible landmarks, information, which is not directly available to passive vision systems. We propose a homing scheme that dispenses with accurate distance information by using parameterized disparity fields. These are obtained from an approximation that incorporates prior knowledge about perspective distortions of the visual environment. A mathematical analysis proves that the approximation does not prevent the scheme from approaching the goal with arbitrary accuracy. Mobile robot experiments are used to demonstrate the practical feasibility of the approach.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Franz, MO and Sch{\"o}lkopf, B and B{\"u}lthoff, HH} } @Techreport { 1512, title = {View-based representations for dynamic 3D object recognition}, year = {1997}, month = {2}, number = {47}, abstract = {Much of the experimental and computational modeling research on human recognition processes has focused exclusively on the domain of static three-dimensional (3D) objects. The issue of the nature of internal representations underlying dynamic 3D object recognition is largely unexplored. Here we examine this issue, with emphasis on view-point dependency, using variants of biological motion sequences of the kind described by Johansson (1973). Our first experiment investigated whether observers exhibit the well-known canonical view-point effect while recognizing 3D biological motion sequences. Results showing a markedly impaired recognition performance with sequences recorded from unusual view-points provide preliminary evidence for the role of view-point familiarity and the inability of the visual system to extract view-independent representations. Next, to examine whether the motion traces used for recognition preserve 3D information, or are largely 2D, we developed a special class of biological motion sequences. The distinguishing characteristic of these sequences was that while they preserve the `normal' 2D projections from one view-point, their 3D structures were randomized. View-points preserving the `normal' 2D projections yielded vivid biological motion percepts, whereas other viewpoints yielded percepts of randomly moving dots. In the final set of experiments we examined whether this result could be an outcome of a recognition-dependent top-down suppression of anomalies in 3D structures. Our results indicate that subjects' expectations about 3D structure can suppress the bottom-up depth information provided by binocular stereo. Taken together, these findings suggest that biological motion sequences are represented by the human visual system as 2D traces rather than as 3D structural descriptions, and that the perception of 3D structure may be based not only upon low-level processes but also upon recognition-dependent top-down influences.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {B{\"u}lthoff, I and B{\"u}lthoff, HH and Sinha, P} } @Techreport { 1508, title = {An Introduction to Object Recognition}, year = {1996}, month = {12}, number = {43}, abstract = {In this report we present a general introduction to object recognition. We begin with brief discussions of the terminology used in the object recognition literature and the psychophysical tasks that are used to investigate object recognition. We then discuss models of shape representation. We dispense with the idea that shape representations are like the 3-D models used in computer aided design and explore instead models of shape representation that are based on feature descriptions. As these descriptions encode only the features that are visible from a particular viewpoint, they are generally viewpoint-specific. We discuss various means of achieving viewpoint-invariant recognition using such descriptions, including reliance on diagnostic features visible from a wide range of viewpoints, storage of multiple descriptions for each object, and the use of transformation mechanisms. Finally, we discuss how differences in viewpoint dependence that are often observed for within-category and between-category recognition tasks could be due to differences in the types of features that are naturally available to distinguish among different objects in these tasks.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1508.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Liter, JC and B{\"u}lthoff, HH} } @Techreport { 1507, title = {What object attributes determine canonical views?}, year = {1996}, month = {11}, number = {42}, abstract = {We investigated preferred or canonical views for familiar and novel three-dimensional objects using computer-graphics psychophysics. We assessed the canonical views for objects by allowing participants to actively rotate realistically shaded three-dimensional models in real-time. Objects were viewed on a Silicon Graphics Workstation and manipulated in virtual space using a three degree-of-freedom input device. In the first experiment, participants adjusted each object to the viewpoint from which they would take a photograph if they planned to use the object to illustrate a brochure. In the second experiment, participants mentally imaged each object based on the name and then adjusted the object to the viewpoint from which they imagined it. In both experiments, there was a large degree of consistency across participants in terms of the preferred view for a given object. Our results provide new insights on the geometrical, experiential, and functional attributes that determine canonical views under ecological conditions.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1507.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Blanz, V and Tarr, MJ and B{\"u}lthoff, HH and Vetter, T} } @Techreport { 1504, title = {Features of the representation space for 3D objects}, year = {1996}, month = {9}, number = {40}, abstract = {To explore the nature of the representation space of 3D objects, we studied human performance in forced-choice classification of objects composed of four geon-like parts, emanating from a common center. The two class prototypes were distinguished by qualitative contrasts (bulging vs.\textbackslash waist-like limbs). Subjects were trained to discriminate between the two prototypes (shown briefly, from a number of viewpoints, in stereo) in a 1-interval forced-choice task, until they reached a 90\% correct-response performance level. In the first experiment, 11 subjects were tested on shapes obtained by varying the prototypical parameters both orthogonally (Ortho) and in parallel (Para) to the line connecting the prototypes in the parameter space. For the eight subjects who performed above chance, the error rate increased with the Ortho parameter-space displacement between the stimulus and the corresponding prototype (the effect of the Para displacement was marginal). Clearly, the parameter-space location of the stimuli mattered more than the qualitative contrasts (which were always present). To find out whether both prototypes or just the nearest neighbor of the test shape influenced the decision, in the second experiment we tested 18 new subjects on a fixed set of shapes, while the test-stage distance between the two classes assumed one of three values (Far, Intermediate, and Near). For the 13 subjects who performed above chance, the error rate (on physically identical stimuli) in the Near condition was higher than in the other two conditions. The results of the two experiments contradict the prediction of theories that postulate exclusive reliance on qualitative contrasts, and support the notion of a metric representation space, with the subjects' performance determined by distances to more than one reference point or prototype.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1504.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Edelman, S and B{\"u}lthoff, HH and B{\"u}lthoff, I} } @Techreport { 1502, title = {How is bilateral symmetry of human faces used for recognition of novel views?}, year = {1996}, month = {8}, number = {38}, abstract = {The role of bilateral symmetry in face recognition is investigated in two psychophysics experiments using a same/different paradigm. The results of Experiment 1 confirm the hypothesis that the ability to identify mirror symmetric patterns is used for viewpoint generalization by approximating the view symmetric to the learned view by its mirror reversed image. The results of Experiment 2 show that the match between this virtual view and the test image is performed directly between the images. Performance drops dramatically if the symmetry between the intensity patterns of the learning and the test view is disturbed by an asymmetric illumination, although the symmetry between the spatial arrangement of high-level features is retained. A simple image based model can explain important aspects of the data and we show how this model can be extended towards a general algorithm for image comparison. Experimental results and the model are discussed in terms of their relation to existing approaches to object recognition.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Troje, N and B{\"u}lthoff, HH} } @Techreport { 1499, title = {Evolution of the Sensorimotor Control in an Autonomous Agent}, year = {1996}, month = {7}, number = {35}, abstract = {Visually guided agents are introduced, that evolve their sensor orientations and sensorimotor coupling in a simulated evolution. The work builds on neurobiological results from various aspects of insect navigation and the architecture of the ''Vehicles'' of Braitenberg (1984). Flies have specialized visuomotor programs for tasks like compensating for deviations from the course, tracking, and landing, which involve the analysis of visual motion information. We use genetic algorithms to evolve the obstacle avoidance behavior. The sensor orientations and the transmission weights between sensor input and motor output evolve with the sensors and motors acting in a closed loop of perception and action. The influence of the crossover and mutation probabilities on the outcome of the simulations, specifically the maximum fitness and the convergence of the population are tested.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/evolution_of_the_sensorimotor_control_in_an_autonomous_agent_1499[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Huber, S and Mallot, HA and B{\"u}lthoff, HH} } @Techreport { 1497, title = {Learning View Graphs for Robot Navigation}, year = {1996}, month = {7}, number = {33}, abstract = {We present a purely vision-based scheme for learning a parsimonious representation of an open environment. Using simple exploration behaviours, our system constructs a graph of appropriately chosen views. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. Simulations and robot experiments demonstrate the feasibility of the proposed approach.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Franz, M and Sch{\"o}lkopf, B and Georg, P and Mallot, HA and B{\"u}lthoff, HH} } @Techreport { 1493, title = {Scene Recognition Workshop, T{\"u}bingen July 3-5, 1996}, year = {1996}, month = {6}, number = {30}, abstract = {In the past few years the question of how humans recognize and analyse natural, complex scenes has received renewed attention, resulting in new techniques and theories. The purpose of this workshop is to bring together researchers interested in these questions from both Europe and the United States to discuss latest results and ideas for the future.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1493.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Tarr, MJ and B{\"u}lthoff, HH} } @Techreport { 1494, title = {Stimulus-specific effects in face recognition over changes in viewpoint}, year = {1996}, month = {6}, number = {31}, abstract = {The ability of observers to recognize faces across changes in viewpoint has been found previously to decline as the angle between learn and test view grows. We replicate this result, but show that the recognizability of individual faces across changes in viewpoint cannot be characterized adequately in this way. An analysis of the recognizability of individual faces in different viewpoint transfer conditions indicated that the representations of faces we make from different views may be only modestly related. We propose and implement a two-stage computational model of face recognition following Lando and Edelman (1995) that operates by: (a) transforming a previously unknown view of a face into other views, one of which may be known; and by (b) recognizing the transformed face views via an interpolation process that operates directly on the structure of the similarity relationships among faces. By combining model and human measures at the level of individual faces, using factor analysis, we isolate relatively consistent orthogonal loading patterns for three learn view conditions (full, three-quarters, profile) with respect to the human and model measures. The axes stemming from the factor analysis are interpretable in terms of recognition transfer success based on: (a) large scale distinctive global features such as head shape, (b) smaller scale distinctive features such as large noses; and (c) distinctive skin tone.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/stimulus_specific_effects_in_face_recognition_over_changes_in_viewpoint_1494[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {O'Toole, AJ and Edelman, S and B{\"u}lthoff, HH} } @Techreport { 1490, title = {Active Kinetic Depth Effect}, year = {1996}, month = {2}, number = {27}, abstract = {We investigated the motion perception of an occluding contour by an active observer. The task of the observer was to decide whether the occluding contour of an object was a sharp edge in depth, or else belonged to a smooth surface. In a first experiment using real objects, we found a strong bias to label the contour smooth. We then replicated the experiment with virtual objects in order to carefully control for the appearance of the objects, and found an advantage for active over passive viewing. Finally, we did not find any improvement of performance when the scene was observed binocularly.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1490.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Mamassian, P and B{\"u}lthoff, HH} } @Techreport { 1487, title = {The role of shape and texture information in sex classification}, year = {1995}, month = {12}, number = {23}, abstract = {The sex of a face is perhaps its most salient feature. A principal components analysis (PCA) was applied separately to the three-dimensional structure and texture data from laser-scanned human heads. Individual components from both analyses captured information related to the sex of the face. Notably, single projection coefficients characterized complex structural differences between three-dimensional male and female heads and between male and female texture maps. In a series of simulations, we compared the quality of the information available in the head versus texture data for predicting in the sex of the face. The results indicated that the three-dimensional structural data supported more accurate sex classification than the texture data, across a range of PCA-compressed (dimensionality-reduced) representations of the heads. This kind of dual face representation can give insight into the nature of the information available to humans for categorizing and remembering faces.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1487.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {O'Toole, AJ and Vetter, T and B{\"u}lthoff, HH and Troje, NF} } @Techreport { 1485, title = {Face Recognition Across Viewpoint}, year = {1995}, month = {9}, number = {21}, abstract = {In two experiments we examined the ability of human observers to recognize faces from novel viewpoints. Previous work has indicated that there are marked declines in recognition performance when observers learn a particular view of a face and are asked to recognize the face from a novel viewpoint. We replicate these findings and extend them in several ways. First, we replicate the well-known 3/4 view advantage for recognition and extend it to show that this advantage is stronger than would be expected simply due to the 3/4 view being the center of the learned views. In the second experiment, we found little evidence for advantageous transfer to a symmetric view of the other side of the face, in all cases, observers were much better at recognizing a face from the side learned. Third, we extended past results to explore the consistency of face recognizability for individual faces across different views and view transfer conditions. We found only a modest relationship between the recognizability of individual faces in the different view conditions. These data give insight into the organization of memory for faces and its stability across changes in viewpoint.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1485.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {O'Toole, AJ and B{\"u}lthoff, HH and Walker, CL} } @Techreport { 1486, title = {To what extent do unique parts influence recognition across changes in viewpoint?}, year = {1995}, month = {9}, number = {22}, abstract = {We investigated how varying the number of unique three-dimensional parts within an object influenced recognition across changes in viewpoint. Stimuli were realistically-shaded images of objects composed of five three-dimensional volumes linked end-to-end. Of the five parts within each object, either zero, one, three, or five were qualitatively distinct from other members of the recognition set (e.g., brick versus cone). Non-distinct parts were cylindrical tubes. Independent of the number of distinct parts, the three-dimensional angles between components were different for each object as in B{\"u}lthoff and Edelman (1992). In both sequential matching and naming tasks we compared the impact of depth rotations on recognition performance. Separate between-subject conditions were defined based on the number of distinct parts for each member of the recognition set. The No-Parts condition was run on all subjects and served as a baseline for the other conditions. For both tasks, three major results stand out. First, regardless of the number of qualitatively distinct parts there was an effect of viewpoint on recognition performance. Second, the impact of viewpoint change in the One-Part condition was less than that in each of the other conditions. Third, the addition of parts beyond a single unique part produced strong viewpoint-dependent recognition performance that was comparable to that obtained for objects with no distinct parts. Taken together these findings indicate that visual recognition may be accounted for by view-based models in which image-based representations include some qualitatively-defined features.}, note = {This technical report has also been published elsewhere}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Tarr, MJ and B{\"u}lthoff, HH and Zabinski, M and Blanz, V} } @Techreport { 1480, title = {A psychophysical and computational analysis of intensity-based stereo}, year = {1995}, month = {6}, number = {18}, abstract = {We describe two psychophysical experiments testing predictions of the square difference mechanism proposed for intensity-based stereo in an earlier paper (Arndt et al. 1995). Experiment1 assesses the relative contributions of disparity and contrast to intensity-based stereo by measuring detection thresholds. The product of disparity and contrast at threshold is shown to be constant. In Experiment 2, we measure quantitatively the global depth position perceived in stereograms of curved, smoothly shaded surfaces. The results show that disparity averaging over the surface involves a contrast dependent weighting function. The results from both experiments are consistent with predictions derived from the square difference mechanism. The relation of this mechanism to feature correspondence stereopsis and shape-from-shading is discussed and a general framework for assessing the modularity of stereopsis is presented.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Mallot, HA and Arndt, PA and B{\"u}lthoff, HH} } @Techreport { 1479, title = {Face recognition under varying pose: The role of texture and shape}, year = {1995}, month = {4}, number = {17}, abstract = {Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has been known since long, that the profile as well as the full-face view result in a recognition performance that is worse than a view from within that range. However, only few data exists that investigate this phenomenon in detail. This work intends to provide such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize on the different role of the learning view and the testing view in the recognition experiment and on the role of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: 1. Only the learning view but not the testing view effects the recognition performance. 2. For the textured faces the optimal learning view is closer to the full-face view than for the shaded faces. 3. For the shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Troje, N and B{\"u}lthoff, HH} } @Techreport { 1471, title = {Eye-Hand Coordination for 3-D Oriented Objects}, year = {1995}, month = {2}, number = {12}, abstract = {When reaching for an object in space, the distance of the object, its orientation and shape should all be correctly estimated well before the hand arrives in contact with the object. We investigate here how the visual information about the object's orientation is incorporated into the motor program which guides the hand to the vicinity of the object. This motor program governs in particular the transportation of the hand, the opening of the hand, and the rotations of the forearm and wrist. These variables are analyzed in the light of the ``visuo-motor channels'' framework proposed by Jeannerod (1981), in which the information about the object's distance and shape is processed independently, from perception to action. Our results seem to favor an alternative framework, in which an interpretation of the three-dimensional world should be built before a motor command can be generated. Due to time constraints, this mechanism appears to be mainly feedforward.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1471.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Mamassian, P and B{\"u}lthoff, HH and Kersten, D} } @Techreport { 1472, title = {Real-Time Optical Flow Extended in Time}, year = {1995}, month = {2}, number = {13}, abstract = {Currently two major limitations to applying vision in real tasks are robustness in real-world, uncontrolled environments, and the computational resources required for real-time operation. In particular, many current robotic visual motion detection algorithms (optical flow) are not suited for practical applications such as segmentation and structure-from-motion because they either require highly specialized hardware or up to several minutes on a scientific workstation. In addition, many such algorithms depend on the computation of first and in some cases higher numerical derivatives, which are notoriously sensitive to noise. In fact the current trend in optical flow research is to stress accuracy under ideal conditions and not to consider computational resource requirements or resistance to noise, which are essential for real-time robotics. As a result robotic vision researchers are frustrated by an inability to obtain reliable optical flow estimates in real-world conditions, and practical applications for optical flow algorithms remain scarce. Algorithms based on the correlation of image patches have been shown to be robust in practice but are in general infeasible due to their computational complexity. This paper describes a space-time tradeoff to this algorithm which converts a quadratic-time algorithm into a linear-time one, as well as a method for dealing with the resulting problem of temporal aliasing, resulting in an algorithm that can run at over 6 frames per second on an 50 MHz Sun Sparcstation 20.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1472.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Camus, TA and B{\"u}lthoff, HH} } @Techreport { 1468, title = {Face Recognition across Large Viewpoint Changes}, year = {1995}, month = {1}, number = {9}, abstract = {We describe a computational model of face recognition that makes use of the overlapping texture and shape information visible in different views of faces. The model operates on view dependent data from three-dimensional laser scans of human heads, which provided three-dimensional surface data as well as surface image detail in the form of a texture map. View-dependent information from these surface and texture representations was registered onto separate three-dimensional head models. We used an auto-associative memory model as a pattern completion device to fill in parts of the head from a learned view when a test view with partially overlapping information was used as a memory key. We show that the overlapping visible regions of heads for both surface and texture data can support accurate recognition, even with pose differences of as much as 90 degrees (full face to profile view) between the learning and test view.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf1468.pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {O'Toole, AJ and B{\"u}lthoff, HH and Troje, NF and Vetter, T} } @Techreport { 1460, title = {How are three-dimensional objects represented in the brain?}, year = {1994}, month = {3}, number = {5}, abstract = {We discuss a variety of psychophysical experiments that explore different aspects of the problem of object recognition and representation in human vision. In all experiments, subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects' prior exposure to the stimulus objects. Contrary to the predictions of the paradigmatic theory of recognition, which holds that object representations are viewpoint invariant, performance in all experiments was consistently viewpoint dependent, was only partially aided by binocular stereo and other depth information, was specific to viewpoints that were familiar, and was systematically disrupted by rotation in depth more than by deforming the two-dimensional images of the stimuli. The emerging concept of multiple-view representation supported by these results is consistent with recently advanced computational theories of recognition based on view interpolation. Moreover, in several simulated experiments employing the same stimuli used in experiments with human subjects, models based on multiple-views representations replicated many of the psychophysical results concerning the observed pattern of human performance.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/how_are_three-dimensional_objects_represented_in_the_brain_1460[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {B{\"u}lthoff, HH and Edelman, SY and Tarr, MJ} } @Techreport { 682, title = {How are three-dimensional objects represented in the brain?}, year = {1994}, month = {3}, number = {AIM-1479}, abstract = {We discuss a variety of psychophysical experiments that explore different aspects of the problem of object recognition and representation in human vision. In all experiments, subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects' prior exposure to the stimulus objects. Contrary to the predictions of the paradigmatic theory of recognition, which holds that object representations are viewpoint invariant, performance in all experiments was consistently viewpoint dependent, was only partially aided by binocular stereo and other depth information, was specific to viewpoints that were familiar, and was systematically disrupted by rotation in depth more than by deforming the two-dimensional images of the stimuli. The emerging concept of multiple-view representation supported by these results is consistent with recently advanced computational theories of recognition based on view interpolation. Moreover, in several simulated experiments employing the same stimuli used in experiments with human subjects, models based on multiple-views representations replicated many of the psychophysical results concerning the observed pattern of human performance.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/how_are_three_dimensional_objects_represented_in_the_brain_682[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {MIT Artificial Intelligence Laboratory and Center for Biological and Computational Learning, Cambridge, MA, USA}, author = {B{\"u}lthoff, HH and Edelman, SY and Tarr, MJ} } @Techreport { 1455, title = {Bayesian decision theory and psychophysics}, year = {1993}, month = {12}, number = {2}, abstract = {We argue that Bayesian decision theory provides a good theoretical framework for visual perception. Such a theory involves a likelihood function specifying how the scene generates the image(s), a prior assumption about the scene, and a decision rule to determine the scene interpretation. This is illustrated by describing Bayesian theories for individual visual cues and showing that perceptual biases found in psychophysical experiments can be interpreted as biases towards prior assumptions made by the visual system. We then describe the implications of this framework for the integration of different cues. We argue that the dependence of cues on prior assumptions means that care must be taken to model these dependencies during integration. This suggests that a number of proposed schemes for cue integration, which only allow weak interaction between cues, are not adequate and instead stronger coupling is often required. These theories require the choice of decision rules and we argue that this choice is important since these rules help capture the task dependent nature of vision. This is illustrated by analysing the generic viewpoint assumption. Finally, we suggest that the visual system uses a set of competing prior assumptions, rather than the single generic priors, or natural constraints, commonly used in computational theories of vision.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/bayesian_decision_theory_and_psychophysics_1455[0].pdf}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Yuille, AL and B{\"u}lthoff, HH} } @Techreport { 1457, title = {Conditions for viewpoint dependence and viewpoint invariance: What mechanisms are used to recognize an object?}, year = {1993}, month = {12}, number = {3}, abstract = {Is object recognition viewpoint dependent or viewpoint invariant under ''everyday'' conditions? While Biederman and Gerhardstein (1993) argue that viewpoint-invariant mechanisms are used almost exclusively, an analysis indicates that: 1) their conditions for immediate viewpoint invariance lack the generality to characterize everyday recognition; 2) viewpoint-dependent effects are \{it not\} the byproduct of systems other than recognition; 3) empirical evidence supports a prominent role for viewpoint-dependent mechanisms in subordindate-level discriminations; 4) geon structural descriptions provide an inadequate account of how unfamiliar exemplars of familiar categories are recognized because they are at times too stable and too sensitive with regard to the entry-level. We conclude that exemplar-based multiple-views representations may support both viewpoint-dependent and viewpoint-invariant recognition, with relevant information being applied according to context and task.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Tarr, MJ and B{\"u}lthoff, HH} } @Techreport { 1454, title = {Stereovision without localized image features}, year = {1993}, month = {12}, number = {1}, abstract = {Many theories of stereo vision are based on feature matching and the related correspondence problem. In this paper, we show that localized image features such as Laplacian zerocrossings, intensity extrema, or centroids are not necessary for binocular depth perception. Smooth one-dimensional intensity-profiles lacking some or all of these localized features were constructed and combined into stereograms with mirror-symmetric halfimages. In a discrimination task, subjects were asked to distinguish between stereograms differing only by an exchange of these halfimages (ortho- vs. pseudoscopic stereograms). In a depth ordering task, subjects had to judge which of the two versions appeared in front. Subjects are able to solve both tasks even in the absence of the mentioned image features. The performance is compared to various possible stereo mechanisms. We conclude that localized image features and the correspondences between them are not necessary to perceive stereoscopic depth. One mechanism accounting for our data is correlation or mean square difference.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany}, author = {Arndt, PA and Mallot, HA and B{\"u}lthoff, HH} } @Techreport { 2544, title = {Conditions for viewpoint dependent face recognition}, year = {1993}, month = {8}, number = {AIM-1432}, abstract = {Face recognition stands out as a singular case of object recognition: although most faces are very much alike, people discriminate between many different faces with outstanding efficiency. Even though little is known about the mechanisms of face recognition, viewpoint dependence, a recurrent characteristic of many research on faces, could inform algorithms and representations. Poggio and Vetter‘s symmetry argument [10] predicts that learning only one view of a face may be sufficient for recognition, if this view allows the computation of a symmetric, virtual, view. More specifically, as faces are roughly bilaterally symmetric objects, learning a side-view - which always has a symmetric view - should give rise to better generalization performances than learning the frontal view. It is also predicted that among all new views, a virtual view should be best recognized. We ran two psychophysical experiments to test these predictions. Stimuli were views of 3D models of laser-scanned faces. Only shape was available for recognition; all other face cues - texture, color, hair, etc. - were removed from the stimuli. The first experiment tested whether a particular view of a face was canonical. The second experiment tested which single views of a face give rise to best generalization performances. The results were compatible with the symmetry argument: face recognition from a single view is always better when the learned view allows the computation of a symmetric view.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/conditions_for_viewpoint_dependent_face_recognition_2544[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Schyns, PG and B{\"u}lthoff, HH} } @Techreport { 703, title = {3D Object Recognition: Symmetry and Virtual Views}, year = {1992}, month = {12}, volume = {A.I. Memo No. 1409}, number = {AIM-1409}, abstract = {Many 3D objects in the world around us are strongly constrained. For instance, not only cultural artifacts but also many natural objects are bilaterally symmetric. Human faces are an important case for which bilateral symmetry holds, at least approximatively. Can a priori information about generic constraints of this type help the task of 3D object recognition? It can be shown that theoretically such prior information reduces the amount of information needed to recognize a 3D object, since additional virtual views can be generated from given model views by the appropriate symmetry transformations. Under special conditions, a single non-accidental ``model‘‘ view is theoretically sufficient for recognition of novel views, if the object is bilaterally symmetric, whereas the theoretical minimum (under the same conditions) for a non-symmetric object is two views. In practice, we expect that the ''virtual'' views provided by the symmetry property will facilitate human recognition of novel views. Psychophysical experiments confirm that humans are better in the recognition of symmetric objects. The hypothesis of symmetry-induced virtual views together with a network model that successfully accounts for human recognition of generic 3D objects leads to predictions that we have verified with psychophysical experiments.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/3d_object_recognition_symmetry_and_virtual_views_703[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Vetter, T and Poggio, T and B{\"u}lthoff, HH} } @Techreport { 721, title = {Task and object learning in visual recognition}, year = {1991}, month = {3}, volume = {A. I. Memo No. 1348}, number = {AIM-1348}, abstract = {Human performance in object recognition changes with practice, even in the absence of feedback to the subject. The nature of the change can reveal important properties of the process of recognition. We report an experiment designed to distinguish between non-specific task learning and object-specific practice effects. The results of the experiment support the notion that learning through modification of object representations can be separated from less interesting effects of practice, if appropriate response measures (specifically, the coefficient of variation of response time over views of an object) are used. Furthermore, the results, obtained with computer-generated amoeba-like objects, corroborate previous findings regarding the development of canonical views and related phenomena with practice.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/task_and_object_learning_in_visual_recognition_721[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Edelman, S and B{\"u}lthoff, HH and Sklar, E} } @Techreport { 708, title = {Apparent opacity affects perception of structure from motion}, year = {1991}, month = {1}, volume = {CBIP Memo No. 34}, number = {AIM-1285}, abstract = {It is well known that the human visual system can reconstruct depth from simple random-dot displays given motion information. This fact has lent support to the notion that structure from stereo and motion systems rely on low-level primitives or tokens, such as edges, derived from image intensities. In contrast, the judgment of surface attributes such as transparency or opacity is often considered to be a higher-level visual process that would make use of low-level stereo or motion information, and perhaps attention or later recognition to tease apart the transparent from the opaque parts. This is exemplified by the lack of computational studies dealing with transparency, compared with the at least limited success of a number of algorithms to solve structure from motion or stereo. In this study, we describe a new illusion and some results that question the above view by showing that depth from transparency and opacity can override the rigidity bias in perceiving depth from motion. This provides support for the idea that the brain‘s computation of the surface material attribute of transparency may have to be done either before, or in parallel with the computation of structure from motion.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/apparent_opacity_affects_perception_of_structure_from_motion_708[0].pdf}, web_url = {ftp://publications.ai.mit.edu/ai-publications/pdf/AIM-1285.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Kersten, D and B{\"u}lthoff, HH} } @Techreport { 740, title = {Bayesian Models for Seeing Shapes and Depth}, year = {1990}, month = {11}, volume = {No. 90-11}, number = {90-11}, abstract = {We review computational models of shape and depth erception and relate them to visual psychophysics. The Bayesian approach to vision provides a fruitful theoretical framework both for modeling individual modules, such as stereo, shading, texture, and occlusion and for integrating their information. In this formalism we represent depth by one, or more, surfaces with prior probabilities for surface shape, corresponding to natural constraints, in order to avoid the ill-posedness of vision. On theoretical grounds, the less information available to the module (and the less accurate it is), then the more important the priors become. This suggests that visual illusions, and biased perceptions, will arise for scenes for which the priors are not appropriate. We describe psychophysical experiments that are consistent with these ideas. For integration of different modules we advocate strong coupling, so that the modules can interact during computation and the priors can be modified. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration and different psychophysical experiments can be understood within the Bayesian approach.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/bayesian_models_for_seeing_shapes_and_depth_740[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Harvard Robotics Laboratory, Cambridge, MA, USA}, author = {B{\"u}lthoff, HH and Yuille, A} } @Techreport { 754, title = {Viewpoint-specific representations in three-dimensional object recognition}, year = {1990}, month = {8}, volume = {A.I. Memo No. 1239}, number = {AIM-1239}, abstract = {We report a series of psychophysical experiments that explore different aspects of the problem of object representation and recognition in human vision. Contrary to the paradigmatic view which holds that the representations are three-dimensional and object-centered, the results consistently support the notion of view-specific representations that include at most partial depth information. In simulated experiments that involved the same stimuli shown to the human subjects, computational models built around two-dimensional multiple-view representations replicated our main psychophysical results, including patterns of generalization errors and the time course of perceptual learning.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/viewpoint-specific_representation_in_three_dim_object_recognition_754[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Edelman, S and B{\"u}lthoff, HH} } @Techreport { 760, title = {Disparity Gradients and Depth Scaling}, year = {1989}, month = {9}, volume = {A.I. Memo No. 1175}, number = {AIM-1175}, abstract = {The binocular perception of shape and of depth relations between objects can change considerably if the viewing direction is changed only by a small angle. We explored this effect psychophysically and found a strong depth reduction effect for large disparity gradients. The effect is found to be strongest for horizontally oriented stimuli, and stronger for line stimuli than for points. This depth scaling effect is discussed in a computational framework of stereo based on a Baysian approach which allows to integrate information from different types of matching primitives weighted according to their robustness.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/disparity_gradients_and_depth_scaling_760[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {B{\"u}lthoff, HH and Fahle, M} } @Techreport { 768, title = {Stimulus familiarity determines recognition strategy for novel 3D objects}, year = {1989}, month = {7}, volume = {A.I. Memo No. 1138}, number = {AIM-1138}, abstract = {Everyday objects are more readily recognized when seen from certain representative, or canonical, viewpoints than from other, random, viewpoints. We investigated the canonical views phenomenon for novel 3D objects. In particular, we looked for the effects of object complexity and familiarity on the variation of response times and error rates over different views of the object. Our main findings indicate that the response times for different views become more uniform with practice, even though the subjects in our experiments received no feedback as to the correctness of their responses. In addition, the orderly dependency of the response time on the distance to a “good” view, characteristic of the canonical views phenomenon, disappears with practice. One possible interpretation of our results is in terms of a tradeoff between memory needed for storing specific-view representations of objects and time spent in recognizing the objects.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/stimulus_familiarity_determines_recognition_strategy_for_novel_3d_objects_768[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Edelman, S and B{\"u}lthoff, HH and Weinshall, D} } @Techreport { 767, title = {Stereo Integration, Mean Field Theory and Psychophysics}, year = {1989}, month = {1}, volume = {No. 11-89}, number = {89-11}, abstract = {We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision and relate it to psychophysical experiments. The formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the marching. We use techniques from statistical physics to show how our theory relates lo previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different marching primitives.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/stereo_integration_mean_field_theory_and_psychophysics_767[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Harvard Robotics Laboratory, Cambridge, MA, USA}, author = {Yuille, A and Geiger, D and B{\"u}lthoff, HH} } @Techreport { 825, title = {Interaction of Different Modules in Depth Perception: Stereo and Shading}, year = {1987}, month = {5}, volume = {A.I. Memo No. 965}, number = {AIM-965}, abstract = {A method has been developed to measure the perceived depth of computer generated images of simple solid objects. Computer graphic techniques allow for independent control of different depth cues (stereo, shading and texture) and enable the investigator thereby to study psychophysically the interaction of modules for depth perception. Accumulation of information from shading and stereo and vetoing of depth from shading by edge information have been found. Cooperativity and other types of interactions are discussed. If intensity edges are missing, as in smooth-shaded surfaces, the image intensities themselves could be used for stereo matching. The results are compared with computer vision algorithms for both single modules and their integration for 3D-vision.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/interaction_of_different_modules_in_depth_perception_stereo_and_shading_825[0].pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology}, language = {en}, author = {B{\"u}lthoff, HH and Mallot, HA} } @Techreport { 827, title = {Neural Architecture for Optical Flow Computation}, year = {1987}, month = {3}, volume = {A.I. Memo No. 1067}, number = {AIM-1067}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Mallot, HA and B{\"u}lthoff, HH and Little, J} } @Techreport { 828, title = {Parallel Computation of Optical Flow}, year = {1987}, number = {AIM-929}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {Massachusetts Institute of Technology, Cambridge, MA, USA}, author = {Little, J and B{\"u}lthoff, HH} } @Poster { NestiBPB2012, title = {Human sensitivity to different motion intensities}, year = {2012}, month = {11}, volume = {13}, pages = {27}, abstract = {Sensory information processes leading to human self-motion perception have been modelled in the past in terms of visual and inertial stimulations and their interactions. The models, validated through many psychophysical experiments, rely on the assumption that our sensitivity to supra-threshold self-motion is not affected by motion intensity. In other words, the relationship between motion stimulus intensity and human sensitivity to motion is assumed to be linear. However, recent studies have shown that this relationship is non-linear, in particular at higher motion intensity. Therefore, the implementation of nonlinearities in the computational models of human motion perception would increase their accuracy over a wider range of motion stimulus intensity. Here we test human sensitivity for sinusoidal yaw rotation in darkness at frequencies of 0.5 Hz and 1 Hz and velocity amplitudes ranging between 0 and 90 deg/s. In a two interval force choice experimental paradigm, subjects undergo two consecutive rotations in the same direction for each trial. One of these movements is repeated unchanged in every trial, while the other systematically varies in amplitude. Subjects are asked to report after each trial which one of the two movements was stronger. An adaptive staircase adjusts the motion for every trial to identify the smallest detectable change in stimulus intensity (differential threshold). Results show a power law relationship between differential thresholds and stimulus intensity, meaning that sensitivity decreases as motion becomes stronger. No frequency effect is observed. These findings are of particular interest for the field of vehicle motion simulation, where knowledge about self-motion perception is widely exploited to overcome the physical limitations of motion-based simulators. Furthermore, the identification of perceptual nonlinearities in multisensory stimulation will guide future work into understanding the neural mechanisms responsible for self-motion perception.}, department = {Department B{\"u}lthoff}, web_url = {http://www.neuroschool-tuebingen-nena.de/}, event_place = {Schramberg, Germany}, event_name = {13th Conference of the Junior Neuroscientists of T{\"u}bingen (NeNA 2012)}, author = {Nesti, A and Beykirch, K and Pretto, P and B{\"u}lthoff, HH} } @Poster { BiegBBC2012_2, title = {Asymmetries in saccadic latencies during interrupted ocular pursuit}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {137}, abstract = {Smooth pursuit eye movements can be interrupted and resumed at a later stage, eg, when a concurrent task requires visual sampling from elsewhere. Here we address whether and how interruptive saccades are affected by pursuit movements. Our participants pursued an object which moved horizontally in a sinusoidal pattern (frequency: 0.25 Hz, amplitude: 4 deg. visual angle). During this, discrimination targets appeared at 10 deg. eccentricity, to the left or right of the center. They were timed so that they appeared for 1 second while the pursuit object moved either toward or away from the discrimination target's position. Saccade reaction times were earlier when the discrimination targets appeared in a position that the tracking object was moving towards. Interestingly, saccade RTs back to the pursuit object were shorter when the object moved away from the discrimination target. We conclude that interruptions of pursuit movements lead to asymmetries in saccade generation. These asymmetries could have been caused by biases in attention along the predicted pursuit path.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120443}, event_place = {Alghero, Italy}, event_name = {35th European Conference on Visual Perception}, author = {Bieg, H-J and Bresciani, J-P and B{\"u}lthoff, HH and Chuang, LL} } @Poster { ChuangNB2012, title = {Eye-movement planning during flight maneuvers}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {99}, abstract = {How are eye-movements planned to access relevant visual information during flight control? From the cockpit perspective, there are two classes of visual information that are relevant for flight control. First, the changing visuals of the external world provide direct perceptual feedback on how the pilot's command of the control stick is affecting the aircraft's current position, orientation and velocity. Second, flight instruments provide abstracted and specific values—on factors such as the aircraft's compass bearing and vertical speed—that have to be continuously monitored, in order for the global objective of certain maneuvers (eg, turns) to be achieved. Trained pilots have to coordinate their eye-movements across this structured visual workspace (ie, outside view and instruments) to access timely and task-relevant information. The current work focuses on providing descriptions of these planned eye-movements. Eye-movements were recorded of pilots in a high-fidelity flight simulator (100\(^{\circ}\) field-of-view) whilst they performed specific flight maneuvers. Fixation durations and transitions between the individual instruments and aspects of the external environment are represented as network graphs. This allowed us to formally describe the sources of information that were relied on across the different tasks and to compare actual performance to expert predictions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120634}, event_place = {Alghero, Italy}, event_name = {35th European Conference on Visual Perception}, author = {Chuang, L and Nieuwenhuizen, F and B{\"u}lthoff, HH} } @Poster { KaulardSWBd2012, title = {Inverting natural facial expressions puzzles you}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {103}, abstract = {The face inversion effect has often been demonstrated in face identification tasks. Less is known about whether processes underlying face expression recognition are also sensitive to face inversion. Face expression recognition is usually investigated using pictures of six emotional expressions. In everyday life, humans are however exposed to a much larger set of facial expressions, which are dynamic. Here, we examine the effect of face inversion on expression recognition for a variety of facial expressions displayed statically and dynamically. We measured participants'recognition accuracy for 12 expressions using a 13 alternative-forced-choice task. We varied the dynamics (videos versus pictures) and the orientation (upright versus inverted) of the presentation of the expressions in a completely crossed design. Accuracy was significantly higher when expressions were presented as videos (62\%) than as pictures (47\%). Similarly, recognition accuracy was significantly higher for upright (84\%) compared to inverted (64\%) expressions. Moreover, the effect of orientation changed significantly with expression type. No other effects were significant. This is the first study to report that face inversion affects the recognition of natural facial expressions. Because face inversion effects are interpreted as a sign of configural processing, our results suggest configural processing for a majority of facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120193}, event_place = {Alghero, Italy}, event_name = {35th European Conference on Visual Perception}, author = {Kaulard, K and Schultz, J and Wallraven, C and B{\"u}lthoff, HH and de la Rosa, S} } @Poster { ChuangNB2012_2, title = {Investigating Gaze Behavior of Novice Pilots during Basic Flight Maneuvers}, year = {2012}, month = {9}, department = {Department B{\"u}lthoff}, web_url = {http://research.fit.edu/hci-aero/hci-aero2012/Poster_Sessions.html}, event_place = {Bruxelles, Belgium}, event_name = {International Conference on Human-Computer Interaction in Aerospace (HCI-Aero 2012)}, author = {Chuang, LL and Nieuwenhuizen, FM and B{\"u}lthoff, HH} } @Poster { delaRosaMBC2012, title = {View dependencies in the visual recognition of social interactions}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {240}, abstract = {Humans daily physically interact with other people (eg when shaking hands). Understanding the action of others is important for a successful social interaction. Little is known about the visual processes underlying the visual recognition of social interactions. Here we were examined the view dependency of social interaction recognition. We used motion capture to record predefined interactions (eg high five; handshake; hug) acted out by pairs of participants and created 3D models of these interactions. In the actual experiment participants were presented with these interactions one at a time and had to identify a predefined interaction (1IFC task). We manipulated the view point (front, side, top, 45 degree side view) from which participants saw the interaction and the presentation time of the social interactions. We recorded participants'accuracy (as measured by d prime) and reaction time to identify a predefined social interaction. We found that the d primes and reaction time significantly depended on the view point of the social interaction. The results suggest the existence of view dependencies in the visual recognition of social interactions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120439}, event_place = {Alghero, Italy}, event_name = {35th European Conference on Visual Perception}, author = {de la Rosa, S and Miekes, S and B{\"u}lthoff, HH and Curio, C} } @Poster { DobrickiMB2012, title = {Onset time of visually induced circular self-motion perception as an indicator for altered self-localization in immersive virtual reality}, journal = {Journal of Vision}, year = {2012}, month = {8}, volume = {12}, number = {9}, pages = {1326}, abstract = {In the framework of the experimental induction of full-body illusions the features of the experience of being a distinct entity (selfhood) are altered such that participants identify with and mis-localize themselves towards a virtual body. On the other hand, it has been found that the experience of circular self-motion, or vection, can be induced by rotating a naturalistic visual environment around human participants. Circular vection is likely influenced by a person’s self-localization, since it is the illusion of self-rotation around a specific location. Thus, estimates of vection may serve as indicators for altered self-localization. In the framework of a within-subjects design experiment, male participants viewed an avatar from behind within a naturalistic virtual city in a head-mounted display setup. First, we stroked their back for three minutes while they watched the avatar getting synchronously and congruently stroked, or no visuo-tactile stroking was applied (stimulation factor). Subsequently, we assessed their identification with the avatar with a questionnaire, and then repeated the initial treatment. Finally, we rotated the participants’ perspective around their vertical axis for one minute. During rotation the avatar was in the same location in front of the viewer, rotating around his axis, or in a standing posture (avatar-motion factor). Participants were asked to indicate when they started to experience vection. They reported significantly higher identification with the avatar and self-localization in the avatar’s position after visuo-tactile stimulation. Moreover, when they experienced visuo-tactile stimulation, regardless of the avatar-motion factor, participants showed a later onset of vection. One possible explanation for these results is that participants perceived themselves as partially localized in the avatar’s position, and in turn this decrease in their accuracy of self-localization delayed their experience of circular vection. Consequently, we suggest estimates of self-motion as a new measure for selfhood and embodiment, and specifically for self-localization.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/12/9/1326.abstract}, event_place = {Naples, FL, USA}, event_name = {12th Annual Meeting of the Vision Sciences Society (VSS 2012)}, author = {Dobricki, M and Mohler, BJ and B{\"u}lthoff, HH} } @Poster { LinkenaugerMPB2012, title = {The Role of Visual Foot Size in Perceiving Object Size from Texture Gradient}, journal = {Journal of Vision}, year = {2012}, month = {8}, volume = {12}, number = {9}, pages = {902}, abstract = {The ground plane’s texture gradient is a well-known, perspective depth cue that derives from the fact that, for a uniformly textured surface, texture elements become smaller and more densely arrayed in the visual field with increased in distance e.g. grass on a field or cobble stones on a street. This size / distance relationship also occurs for objects such that objects of equal size occlude an equal amount of texture at their base regardless of their distance from the observer. Texture gradients have been studied primarily as a relative depth cue that specifies the size of one object relative to another. However, more definite relative scaling can be achieved if the size of texture elements is scaled to some known metric. We hypothesized that perceivers use the amount of texture occluded by their own feet to scale the sizes of objects on a textured ground. Using head-mounted displays and a motion capture system, we were able to increase or decrease the apparent size of participants’ visual feet in a virtual environment. We asked participants to verbally estimate the width and height of many objects using meters and centimeters(varying in size at the base). As hypothesized, perceivers’ estimations of the sizes of cylinders were smaller when participants had larger virtual feet and larger when participants had smaller virtual feet. This demonstrates that texture gradient, in combination with the visual self-located body, can be used to estimate the size of objects.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/12/9/902.abstract}, event_place = {Naples, FL, USA}, event_name = {12th Annual Meeting of the Vision Sciences Society (VSS 2012)}, author = {Linkenauger, S and Mohler, B and Proffitt, D and B{\"u}lthoff, HH} } @Poster { NestiBBP2012, title = {Roll rate thresholds in driving simulation}, journal = {Seeing and Perceiving}, year = {2012}, month = {6}, day = {21}, volume = {25}, pages = {167}, abstract = {The restricted operational space of dynamic driving simulators requires the implementation of motion cueing algorithms that tilt the simulator cabin to reproduce sustained accelerations. In order to avoid conflicting inertial cues, the tilt rate is limited below drivers’ perceptual thresholds, which are typically derived from the results of classical vestibular research, where additional sensory cues to self-motion are removed. These limits might be too conservative for an ecological driving simulation, which provides a variety of complex visual and vestibular cues as well as demands of attention which vary with task difficulty. We measured roll rate detection threshold in active driving simulation, where visual and vestibular stimuli are provided as well as increased cognitive load from the driving task. Here thresholds during active driving are compared with tilt rate detection thresholds found in the literature (passive thresholds) to assess the effect of the driving task. In a second experiment, these thresholds (active versus passive) are related to driving preferences in a slalom driving course in order to determine which roll rate values are most appropriate for driving simulators so as to present the most realistic driving experience. The results show that detection threshold for roll in an active driving task is significantly higher than the limits currently used in motion cueing algorithms, suggesting that higher tilt limits can be successfully implemented to better optimize simulator operational space. Supra-threshold roll rates in the slalom task are also rated as more realistic. Overall, our findings indicate that increasing task complexity in driving simulation can decrease motion sensitivity allowing for further expansion of the virtual workspace environment.}, department = {Department B{\"u}lthoff}, talk_type = {Abstract Talk}, web_url = {http://booksandjournals.brillonline.com/content/10.1163/187847612x647973}, event_place = {Oxford, UK}, event_name = {13th International Multisensory Research Forum (IMRF 2012)}, DOI = {10.1163/187847612X647973}, author = {Nesti, A and Barnett-Cowan, M and B{\"u}lthoff, HH and Pretto, P} } @Poster { Bulthoff2012_3, title = {Persistent perceptual delay for head movement onset relative to auditory stimuli of different duration and rise times}, journal = {Seeing and Perceiving}, year = {2012}, month = {6}, day = {19}, volume = {25}, pages = {32}, abstract = {The perception of simultaneity between auditory and vestibular information is crucially important for maintaining a coherent representation of the acoustic environment whenever the head moves. Yet, despite similar transduction latencies, vestibular stimuli are perceived significantly later than auditory stimuli when simultaneously generated (Barnett-Cowan and Harris, 2009; 2011). However, these studies paired a vestibular stimulation of long duration (\verb=~=1 s) and of a continuously changing temporal envelope with brief (10-50 ms) sound pulses. In the present study the stimuli were matched for temporal envelope. Participants judged the temporal order of the onset of an active head movement and of brief (50 ms) or long (1400 ms) sounds with a square or raised-cosine shaped envelope. Consistent with previous reports, head movement onset had to precede the onset of a brief sound by about 73 ms in order to be perceived as simultaneous. Head movements paired with long square sounds (\verb=~=100ms) were not significantly different than brief sounds. Surprisingly, head movements paired with long raised-cosine sound (\verb=~=115 ms) had to be presented even earlier than brief stimuli. This additional lead time could not be accounted for by differences in the comparison stimulus characteristics (duration and temporal envelope). Rather, differences among sound conditions were found to be attributable to variability in the time for head movement to reach peak velocity: the head moved faster when paired with a brief sound. The persistent lead time required for vestibular stimulation provides further evidence that the perceptual latency of vestibular stimulation is larger compared to auditory stimuli.}, department = {Department B{\"u}lthoff}, talk_type = {Abstract Talk}, web_url = {http://booksandjournals.brillonline.com/content/10.1163/187847612x646541}, event_place = {Oxford, UK}, event_name = {13th International Multisensory Research Forum (IMRF 2012)}, DOI = {10.1163/187847612X646541}, author = {Raeder, S and B{\"u}lthoff, HH and Barnett-Cowan, M} } @Poster { NestiBMB2012, title = {Differential Thresholds for Vertical Motion}, year = {2012}, month = {1}, volume = {22}, number = {12}, department = {Department B{\"u}lthoff}, web_url = {http://www.vertigocenter.ch/ZuMu2012/pres.html\#Posters}, event_place = {Z{\"u}rich, Switzerland}, event_name = {22nd Okulomotoriktreffen Z{\"u}rich-M{\"u}nchen (Z{\"u}M{\"u} 2012)}, author = {Nesti, A and Barnett-Cowan, M and MacNeilage, P and B{\"u}lthoff, HH} } @Poster { SoykaRBB2012, title = {Reaction Times for Self-Motion Detection}, year = {2012}, month = {1}, volume = {22}, number = {14}, department = {Department B{\"u}lthoff}, web_url = {http://www.vertigocenter.ch/ZuMu2012/pres.html\#Posters}, event_place = {Z{\"u}rich, Switzerland}, event_name = {22nd Okulomotoriktreffen Z{\"u}rich-M{\"u}nchen (Z{\"u}M{\"u} 2012)}, author = {Soyka, F and Robuffo Giordano, P and Barnett-Cowan, M and B{\"u}lthoff, HH} } @Poster { PapeWSBM2011, title = {Grid cell remapping in humans}, year = {2011}, month = {11}, volume = {41}, number = {288.05}, abstract = {Grid cells in entorhinal cortex of freely moving rodents were proposed to provide a universal metric of space. They tile the environment into a six-fold symmetric pattern with a particular orientation relative to the environment. The six-fold rotational symmetry of grid patterns can be used to predict a macroscopic signal to functional magnetic resonance imaging (fMRI) in humans [Doeller et al, 2010, Nature]. During hippocampal remapping, grid pattern orientations in rats also change. The purpose of the present study is to examine whether orientation changes (i.e., remapping) can also be found in humans. Participants learned object locations within a virtual room (see Figure 1 left side) and retrieved locations from different start locations during two scanning sessions. They then navigated into an adjacent room and repeated the procedure. We extracted grid orientations from odd trials, and predicted the BOLD response in even trials as a function of the deviation between running direction and the estimated grid orientation for each session. This prediction was significant for the right entorhinal cortex, replicating earlier findings. In 80\% of the cases grid cell orientations significantly differed between sessions both within a room and between rooms (see Figure 1 right side). Switching off the virtual environment between sessions for about one minute was seemingly sufficient for that. For male, but not for female participants, grid cell orientation was clustered around the random view of the room experienced at session start. Data suggests that human grid cell orientations can be rather flexible which might be due to the virtuality of the experience. Grid cell orientation might at least for male participants be related to the initial view of an environment.}, department = {Department B{\"u}lthoff}, web_url = {http://www.sfn.org/am2011/}, event_place = {Washington, DC, USA}, event_name = {41st Annual Meeting of the Society for Neuroscience (Neuroscience 2011)}, author = {Pape, A-A and Wolbers, T and Schultz, J and B{\"u}lthoff, HH and Meilinger, T} } @Poster { VolkovaMLAB2011, title = {Contribution of Prosody in Audio-visual Integration to Emotional Perception of Virtual Characters}, journal = {i-Perception}, year = {2011}, month = {10}, volume = {2}, number = {8}, pages = {774}, abstract = {Recent technology provides us with realistic looking virtual characters. Motion capture and elaborate mathematical models supply data for natural looking, controllable facial and bodily animations. With the help of computational linguistics and artificial intelligence, we can automatically assign emotional categories to appropriate stretches of text for a simulation of those social scenarios where verbal communication is important. All this makes virtual characters a valuable tool for creation of versatile stimuli for research on the integration of emotion information from different modalities. We conducted an audio-visual experiment to investigate the differential contributions of emotional speech and facial expressions on emotion identification. We used recorded and synthesized speech as well as dynamic virtual faces, all enhanced for seven emotional categories. The participants were asked to recognize the prevalent emotion of paired faces and audio. Results showed that when the voice was recorded, the vocalized emotion influenced participants’ emotion identification more than the facial expression. However, when the voice was synthesized, facial expression influenced participants’ emotion identification more than vocalized emotion. Additionally, individuals did worse on a identifying either the facial expression or vocalized emotion when the voice was synthesized. Our experimental method can help to determine how to improve synthesized emotional speech.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs3/index.php/imrf/2011/paper/view/263}, web_url2 = {http://i-perception.perceptionweb.com/journal/I/volume/2/article/ic774}, event_place = {Fukuoka, Japan}, event_name = {12th International Multisensory Research Forum (IMRF 2011)}, author = {Volkova, E and Mohler, B and Linkenauger, S and Alexandrova, I and B{\"u}lthoff, HH} } @Poster { LeeBBC2011, title = {Fast Fitting on a Saccadic Eye Movement Model for Decision Making}, year = {2011}, month = {10}, volume = {12}, pages = {33}, abstract = {How does our visual system decide where to look? The Linear Approach to Threshold with Ergodic Rate (LATER: Carpenter, 1995) is a simple decision-making model for saccadic eye movements. Currently, experimental data suggest that saccadic eye-movements can be discriminated according to whether they are performed for directed fixations or for item recognition (Montagnini \& Chelazzi, 2005; Bieg et al., submitted). Unfortunately, sufficient goodness-of-fit can only be acquired with large datasets, for each individual participant. Here, we investigate whether adapting LATER with modern computational methods can allow for saccades to be classified for their functionality, with minimal data and in real-time. In doing so, we strive towards the eventual goal of using the LATER model for predicting observer intentions in real-world applications.}, department = {Department B{\"u}lthoff}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=360}, event_place = {Heiligkreuztal, Germany}, event_name = {12th Conference of Junior Neuroscientists of T{\"u}bingen (NeNA 2011)}, author = {Lee, JJ and Bieg, H-J and B{\"u}lthoff, HH and Chuang, LL} } @Poster { PapeWSBM2011_2, title = {Grid cell remapping in humans}, year = {2011}, month = {10}, volume = {12}, pages = {38}, abstract = {Grid cells in entorhinal cortex of freely moving rodents were proposed to provide a universal metric of space. They tile the environment into a six-fold symmetric pattern with a particular orientation relative to the environment. The six-fold rotational symmetry of grid patterns can be used to predict a macroscopic signal to functional magnetic resonance imaging (fMRI) in humans [Doeller et al, 2010, Nature]. During hippocampal remapping, grid pattern orientations in rats also change. The purpose of the present study is to examine whether orientation changes (i.e. remapping) can also be found in humans. Participants learned object locations within a virtual room and retrieved locations from different start locations during two scanning sessions. They then navigated into an adjacent room and repeated the procedure. We extracted grid orientations from odd trials, and predicted the BOLD response in even trials as a function of the deviation between running direction and the estimated grid orientation for each session. This prediction was significant for the right entorhinal cortex, replicating earlier findings. In 80\% of the cases grid cell orientations significantly differed between sessions both within a room and between rooms. Switching off the virtual environment between sessions for about one minute was seemingly sufficient for that. For male, but not for female participants, grid cell orientation was clustered around the random view of the room experienced at session start. Data suggests that human grid cell orientations can be rather flexible which might be due to the virtuality of the experience. Grid cell orientation might at least for male participants be related to the initial view of an environment.}, department = {Department B{\"u}lthoff}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_place = {Heiligkreuztal, Germany}, event_name = {12th Conference of Junior Neuroscientists of T{\"u}bingen (NeNA 2011)}, author = {Pape, A-A and Wolbers, T and Schultz, J and B{\"u}lthoff, HH and Meilinger, T} } @Poster { SoykaBRB2011, title = {Integration of Translational and Rotational Vestibular Cues for Direction Detection during Eccentric Rotations}, year = {2011}, month = {10}, volume = {12}, pages = {42}, abstract = {During eccentric yaw rotations around an Earth-vertical axis the semi-circular canals are stimulated (rotational acceleration) as well as the otoliths (tangential acceleration). Most likely the brain uses both sensory signals, the canal and the otolith signal, when faced with a rotation direction detection task. Keeping the rotational acceleration profile unchanged and increasing the radius of the eccentric rotation the tangential acceleration increases. Therefore, we hypothesized that thresholds would decrease with increasing radius of rotation. The threshold was defined as the peak acceleration needed to detect the correct direction of motion in 75\% of the trials. Ten participants were tested in seven conditions (150 trials each): a head-centered rotation, a translation and five eccentric rotations with varying radii (R=0.1, 0.2, 0.3, 0.5, 0.8 m). The motion had 1s duration and consisted of a single cycle sinusoidal acceleration. Participants were blindfolded, heard white noise and their head was kept in place with a neck brace. The results show a significant decrease of thresholds with increasing radius. It can be seen that the detection process for eccentric rotations is not exclusively based on either the canal or the otolith signal, but that both signals are integrated. A model able to predict the thresholds of the eccentric rotations is proposed, which is solely based on the thresholds for the head-centered rotation and the translational motion. For small radii the detection processes is mainly based on the canal signal whereas for large radii it is dominated by the otolith signal. For intermediate radii the reduction in threshold due to the sensory combination is largest compared to using only one of the two sensors. One additional participant suffered from occasional vertigo after an ear infection indicating vestibular problems. She showed unusually high thresholds for translational motions, but normal thresholds for head-centered rotations. Interestingly, her thresholds for eccentric rotations were higher than her threshold for the head-centered rotations suggesting that she did not only use the rotational signal, but instead had a problem integrating the two sensory signals. These findings indicate that signals from the otolith and the semi-circular canals are not used independently, but are integrated in order to solve a direction detection task.}, department = {Department B{\"u}lthoff}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_place = {Heiligkreuztal, Germany}, event_name = {12th Conference of Junior Neuroscientists of T{\"u}bingen (NeNA 2011)}, author = {Soyka, F and Barnett-Cowan, M and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Poster { SoykadBGB2011, title = {Integration of visual and vestibular information used to discriminate rotational self-motion}, journal = {i-Perception}, year = {2011}, month = {10}, volume = {2}, number = {8}, pages = {855}, abstract = {Do humans integrate visual and vestibular information in a statistically optimal fashion when discriminating rotational self-motion stimuli? Recent studies are inconclusive as to whether such integration occurs when discriminating heading direction. In the present study eight participants were consecutively rotated twice (2s sinusoidal acceleration) on a chair about an earth-vertical axis in vestibular-only, visual-only and visual-vestibular trials. The visual stimulus was a video of a moving stripe pattern, synchronized with the inertial motion. Peak acceleration of the reference stimulus was varied and participants reported which rotation was perceived as faster. Just-noticeable differences (JND) were estimated by fitting psychometric functions. The visual-vestibular JND measurements are too high compared to the predictions based on the unimodal JND estimates and there is no JND reduction between visual-vestibular and visual-alone estimates. These findings may be explained by visual capture. Alternatively, the visual precision may not be equal between visual-vestibular and visual-alone conditions, since it has been shown that visual motion sensitivity is reduced during inertial self-motion. Therefore, measuring visual-alone JNDs with an underlying uncorrelated inertial motion might yield higher visual-alone JNDs compared to the stationary measurement. Theoretical calculations show that higher visual-alone JNDs would result in predictions consistent with the JND measurements for the visual-vestibular condition.}, department = {Department B{\"u}lthoff}, web_url = {http://i-perception.perceptionweb.com/journal/I/volume/2/article/ic855}, web_url2 = {http://i-perception.perceptionweb.com/journal/I/volume/2/article/ic855}, event_place = {Fukuoka, Japan}, event_name = {12th International Multisensory Research Forum (IMRF 2011)}, author = {Soyka, F and de Winkel, K and Barnett-Cowan, M and Groen, E and B{\"u}lthoff, HH} } @Poster { SchultzB2011, title = {How does the brain identify living things based on their motion?}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {682}, abstract = {Identifying living moving things in the environment is a priority for animals, as these could be prey, enemies or mates. When the shape of the moving object is hard to see (fog, twilight, great distance, small animal), motion becomes an important cue to detect it. The neural correlates of the detection of an isolated living entity on the basis of its motion are largely unknown. To study this phenomenon, we developed a single-dot stimulus, thus eliminating all possible sources of information about form, spatial arrangement, shape or structure of the object. The dot moved such that it appeared self-propelled, or moved by an external force, or something intermediary according to a small set of parameters. Self-propelled stimuli were perceived as more animate (= more likely to be alive) than the externally-moved stimuli, with a gradual transition occurring in the intermediary morphs following a classic psychometric function (cumulative gaussian). In an fMRI experiment, 20 subjects had to categorize these stimuli into alive and non-alive. A region of the left medial posterior parietal cortex (mPPC) showed BOLD signal correlating with the probability of animacy judgments about the moving dot. While activation in parts of the early visual cortex showed the same response, the mPPC was the only region in which changes in percept had a stronger effect on activation than physical changes in the stimuli. In addition, only the mPPC showed BOLD signal increases when a stimulus was judged to be animate, irrespective of its physical characteristics. This study shows that parts of the early visual cortex but particularly the medial posterior parietal cortex (mPPC) are involved in judging the animacy of an isolated translating visual stimulus, without information about its form.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/682.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.682}, author = {Schultz, J and B{\"u}lthoff, HH} } @Poster { ThorntonHB2011, title = {iMOT: interactive Multiple Object Tracking}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {293}, abstract = {We introduce a novel, iPad-based experimental paradigm to study interactive multiple object tracking (MOT). In standard MOT, participants passively track a set of independently moving objects. We devised a new task in which participants interact with objects, rather than simply track them. We combined a typical MOT display with the path-guidance, touch-screen interface popularised in smart phone games such as Flight Controller and Harbor Master. We ran the experiment using a custom iPad application. A variable number of identical spheres (1.16\(^{\circ}\) visual angle) moved slowly (0.89\(^{\circ}\)/s) on independent linear trajectories within the full iPad display area (22.6\(^{\circ}\) \(\times\) 17\(^{\circ}\)). Random direction changes occurred at intervals between 4 and 7 s. The participant's goal was to avoid object collisions by manually altering the sphere trajectories. This was achieved by touching the sphere and drawing a short linear or curved path away from it. This action created a visible path, which the sphere followed before resuming default random motion. In this initial study, we constrained path length, in order to prevent participants from creating complex “holding patterns”. A trial ended when the participant successfully avoided collisions for 30 s or when a collision occurred. A sphere was added to the display after a successful trial and removed after a collision, subject to a 6-sphere minimum. Twenty-four participants (ages 18 to 33, mean 23.58, sd 3.45); twelve from Korea University, twelve from Swansea University) completed 30 trials. There were no significant effects of culture, sex or previous gaming experience. The mean number of spheres participants could control was 8.39 (s.e.m. 0.14). This is consistent with estimates of passive tracking capacity at slow speeds. We hypothesize that executive control of scant attentional resources is critical for the current task. In support of this hypothesis, interactive tracking capacity actually increased with age (p = .016).}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/293.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.293}, author = {Thornton, IM and Horowitz, TS and B{\"u}lthoff, HH} } @Poster { VolkovaLABM2011, title = {Integration of Visual and Auditory Stimuli in the Perception of Emotional Expression in Virtual Characters}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {138}, abstract = {Virtual characters are a potentially valuable tool for creating stimuli for research investigating the perception of emotion. We conducted an audio-visual experiment to investigate the effectiveness of our stimuli to convey the intended emotion. We used dynamic virtual faces in addition to pre-recorded (Burkhardt et al, 2005, Interspeech'2005, 1517–1520) and synthesized speech to create audio-visual stimuli which conveyed all possible combinations of stimuli. Each voice and face stimuli aimed to express one of seven different emotional categories. The participants made judgments of the prevalent emotion. For the pre-recorded voice, the vocalized emotion influenced participants’ emotion judgment more than the facial expression. However, for the synthesized voice, facial expression influenced participants’ emotion judgment more than vocalized emotion. While participants rather accurately labeled (>76\%) the stimuli when face and voice emotion were the same, they performed worse overall on correctly identifying the stimuli when the voice was synthesized. We further analyzed the difference between the emotional categories in each stimulus and found that valence distance in the emotion of the face and voice significantly impacted recognition of the emotion judgment for both natural and synthesized voices. This experimental design provides a method to improve virtual character emotional expression.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110451}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {Volkova, E and Linkenauger, S and Alexandrova, I and B{\"u}lthoff, HH and Mohler, B} } @Poster { ProctorCBT2011, title = {iPad sway: Using mobile devices to indirectly measure performance}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {206}, abstract = {Body sway—the subtle, low frequency movement of the human body measured during quiet-standing—has long been used as a tool to help diagnose a range of medical conditions. It can be measured in a number of ways, including force platforms, sway magnetometry and marker or marker-less motion capture. In the current work—by analogy—we examined whether “iPad sway” could be used as an indirect measure of performance in a simple interactive task. We asked participants to stand and play a simple iPad game that involved tracking and controlling multiple objects using the touch screen. In addition to measuring variations in task performance as a function of set size and object speed, we also used the iPad’s built-in accelerometer to record changes in applied force along three axes. Analysis of this force data revealed both task relevant and task irrelevant components. The former relating directly to task demands—particularly touching the screen—and the latter reflecting idiosyncratic posture and movement patterns that can be used to uniquely identify individual users.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110578}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {Proctor, KJ and Chen, M and B{\"u}lthoff, HH and Thrornton, IM} } @Poster { deWinkelSBGB2011, title = {Multisensory integration in the perception of self-motion about an Earth-vertical yaw axis}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {183}, abstract = {Numerous studies report that humans integrate multisensory information in a statistically optimal fashion. However, with respect to self-motion perception, results are inconclusive. Here we test the hypothesis that visual and inertial cues in simulator environments are optimally integrated and that this integration develops over time. Eight participants performed a 2AFC discrimination experiment in visual-only, inertial-only and visual-inertial conditions. Conditions were repeated three times. Inertial motion stimuli were one-period 0.5 Hz sinusoidal acceleration profiles. Visual stimuli were videos of a vertical stripe pattern synchronized with inertial motion. Stimuli were presented in pairs with different peak velocity amplitudes. Participants judged which rotation of a pair had the highest velocity. Precision estimates were derived from psychometric functions. Optimal integration predicts improved precision in the combined condition. However, precision did not differ between the visual and combined conditions. This suggests that participants based their responses predominantly on visual motion. Alternatively, the results could be consistent with optimal integration if the assumption that visual precision remains unchanged during inertial motion was violated. We suggest that a change in visual sensitivity should be considered when investigating optimal integration of visual and inertial cues.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110521}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {de Winkel, K and Soyka, F and Barnett-Cowan, M and Groen, E and B{\"u}lthoff, HH} } @Poster { LeyrerLBKM2011_3, title = {Perception of the size of self and the surrounding visual world in immersive virtual environments}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {209}, abstract = {Newer technology allows for more realistic virtual environments by providing visual image quality that is very similar to that in the real world, this includes adding in virtual self-animated avatars [Slater et al, 2010 PLoS ONE 5(5); Sanchez-Vives et al, 2010 PLoS ONE 5(4)]. To investigate the influence of relative size changes between the visual environment and the visual body, we immersed participants into a full cue virtual environment where they viewed a self-animated avatar from behind and at the same eye-height as the avatar. We systematically manipulated the size of the avatar and the size of the virtual room (which included familiar objects). Both before and after exposure to the virtual room and body, participants performed an action-based measurement and made verbal estimates about the size of self and the world. Additionally we measured their subjective sense of body ownership. The results indicate that the size of the self-representing avatar can change how the user perceives and interacts within the virtual environment. These results have implications for scientists interested in visual space perception and also could potentially be useful for creating positive visual illusions (ie the feeling of being in a more spacious room).}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110436}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {Leyrer, M and Linkenauger, SA and B{\"u}lthoff, HH and Kloos, U and Mohler, BJ} } @Poster { ChuangBS2011, title = {The center-surround effect in visual speed estimation during walking}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {129}, abstract = {Walking reduces visual speed estimates of optic flow (Souman et al, 2010 Journal of Vision 10(11):14]. Simultaneously, visual background motion can influence the perceived speed of moving objects (Tynan and Sekular, 1975 Vision Research 25 1231–1238; Baker and Graf, 2010 Vision Research 50 193–201). These two effects have been attributed to different subtractive processes, which may help in segregating object motion from self-motion induced optic flow. Here, we investigate how both factors jointly contribute to the perceived visual speed of objects. Participants compared the speed of two central Gabor patches on a ground plane, presented in consecutive intervals, either while standing still or while walking on a treadmill. In half the trials, one of the Gabors was surrounded by a moving random dot pattern, the speed of which matched walking speed. Our results replicated previous findings. A moving surround as well as walking can independently induce a subtractive effect on the perceived speed of the moving center, with the effect size increasing with center speed. However, walking does not affect visual speed estimates of the center when a visual surround is present. These results suggest that the visual input dominates the segregation of object motion from background optic flow.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110345}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {Chuang, L and B{\"u}lthoff, HH and Souman, J} } @Poster { LeyrerLBKM2011_2, title = {The influence of a scaled third-person animated avatar on perception and action in virtual environments}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {69}, abstract = {Newer technology is allowing for virtual environments to become more realistic by providing visual image quality that is very similar to that in the real world. Regardless, egocentric distances estimates in virtual reality have been shown to be underestimated (Thompson et al., 2004). Interestingly, this underestimation decreases after individuals view self-representing avatars in the virtual environment; especially when the avatars are self-animated (Mohler et al., 2010). These finding support perspectives on embodied perception which assert that the body and its action capabilities can act as a “perceptual ruler” that the perceiver uses to scale the world. To test this perspective, we immersed participants into a full-cue, virtual environment where they viewed a self-animated avatar from behind at a distance of 3.5 m away at the same eye-height as the avatar. We manipulated the relationship between the size of the avatar and the size of the virtual room (which included familiar objects) to see if participants would attribute these changes either to the size of the world or to the size of their body. Participants made verbal estimates about the size of self and the world and performed a walking-in-place task. We found that participants verbally attributed the apparent size difference to the virtual world and not to the self which suggests that space perception is grounded in the physical body. Further, we found an influence of condition on the post/pre walking-in-place drift suggesting that the participants felt embodied in the third person animated avatar. Further research needs to be conducted in order to fully understand the relative importance of visual cues about self, such as motion coupling, eye-height and distance of avatar from observer, on perception and action in virtual worlds.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/69.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.69}, author = {Leyrer, M and Linkenauger, SA and B{\"u}lthoff, HH and Kloos, U and Mohler, B} } @Poster { LeeBAWB2011, title = {The other-race effect is not ubiquitous}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {626}, abstract = {race (the other-race effect or ORE) has been widely cited. Nevertheless, recognizing the identity of a face is a complex task among many others; hence it might be premature to conclude that own-race faces are always easier to process. We investigated whether same-race faces still have a processing advantage over other-race faces when only ethnicity-related information is available to differentiate between faces. We morphed the ethnicity of 20 Caucasians and 20 Asians faces toward their other-race counterpart while keeping their idiosyncratic, identity-related features. Morphing was done at three levels (20\%, 50\%, and 80\% toward the other race). The task for two groups of participants (25 T{\"u}bingen and 26 Seoul participants) was to report which face looks more Caucasian (or Asian) after looking at the original face and a morphed face sharing the same idiosyncratic features. Both faces were presented side by side on a computer monitor in one task and sequentially in another task. Importantly, we found no evidence for an ORE in participants’ performance and no performance difference between T{\"u}bingen and Seoul participants. Both groups were equally good and equally fast at comparing the ethnicity of two faces regardless of the task, the ethnicity of the faces and the question asked. However, we did find evidence that Seoul and T{\"u}bingen participants used different viewing strategies. By investigating their eye-movements in the sequential task, we found that the ethnicity of participants affected fixation durations on specific areas of the face, especially the nose. Also, the type of questions asked and stimulus race altered the pattern of eye movements. These results suggest that although Caucasians and Asians were equally good at dealing with ethnicity information of both races, they might employ different viewing strategies.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/626.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.626}, author = {Lee, RK and B{\"u}lthoff, I and Ammann, R and Wallraven, C and B{\"u}lthoff, HH} } @Poster { KaulardFBS2011, title = {Uncovering the principles that allow a distinction of conversational facial expressions}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {605}, abstract = {Facial expressions convey both emotional and conversational signals. Research focuses mostly on EMOTIONAL expressions and consistenly finds that these can be reliably distinguished along at least two dimensions: valence and arousal. CONVERSATIONAL expressions, i.e. those conveying mainly communicative meaning, are thought to be less emotional laden. Interestingly, we found evidence pointing towards the same first two underlying dimensions for CONVERSATIONAL expressions when presented dynamically. The question now arises: ''Is the emergence of the valence and arousal dimensions for conversational facial expressions based on the emotional content of these expressions?'' To answer this, we used questions addressing the emotional (Fontaine et al, 2007) and the conversational content separately. If the distinction of conversational expressions is based on the small amount of emotional information they might contain, we expect emotional content questions to allow a separation of those expressions. Ten native German participants answered a set of 27 questions for 6 emotional and 6 conversational expressions, both presented statically and dynamically, using a rating scale. A dissimilarity matrix was computed for the expressions. To uncover the meaning of the first two underlying dimensions allowing expression differentiation, multidimensional scaling (MDS) was used. Our results show that static and dynamic emotional expressions can only be distinguished by means of emotional content questions. For these emotional expressions, the valence and arousal dimensions emerged in the MDS. In contrast, conversational expressions can be distinguished using conversational content questions but not using emotional content questions. Unlike emotional expressions, dynamic information improved distinction of conversational expressions substantially. We found evidence for valence and arousal to be the underlying dimensions for conversational expressions. Our results suggest that the distinction of conversational expressions along the first two dimensions is based on conversational rather than emotional content. Moreover, different types of facial expressions benefit to different degrees from dynamic information.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/605.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.605}, author = {Kaulard, K and Fernandez Cruz, AL and B{\"u}lthoff, HH and Schultz, J} } @Poster { LinkenaugerMB2011, title = {Welcome to Wonderland: The Apparent Size of the Body Influences Perceived Extents in Virtual Environments}, journal = {Journal of Vision}, year = {2011}, month = {9}, volume = {11}, number = {11}, pages = {70}, abstract = {According to the functional approach to the perception of spatial layout, angular optic variables that indicate extents are scaled to the action capabilities of the body (see Proffitt, 2006, POPS, for a review). For example, reachable extents are perceived as a proportion of the maximum extent to which one can reach, and the apparent sizes of graspable objects are perceived as a proportion of the maximum extent that one can grasp (Linkenauger et al., 2009, JEP:HPP; Linkenauger, Ramenzoni, \& Proffitt, 2010, Psychol Sci; Witt, Proffitt, \& Epstein, 2005, JEP:HPP). Therefore, apparent distances and sizes can be influenced by changing the action capabilities of the body. In order to directly manipulate the perceived action capabilities of the body, participants were immersed into a full cue virtual environment. In real time, participants' hand, arm, and head movements were mapped onto a self-avatar which the participant viewed from the first-person perspective via a head-mounted display. To manipulate perceived action capabilities, the apparent size of the participants' hand was altered by decreasing or increasing the size of the self-avatar's virtual hand (small, normal, and large). Participants estimated the sizes of various objects in the virtual environment. Participants perceived objects to be larger when their virtual hand was smaller and perceived objects to be smaller when their virtual hand was larger. Consistent with the functional approach, the differences in apparent size across the conditions increased as a function of object size, suggesting changes in the scaling metric rather than a constant bias.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/11/11/70.abstract}, event_place = {Naples, FL, USA}, event_name = {11th Annual Meeting of the Vision Sciences Society (VSS 2011)}, DOI = {10.1167/11.11.70}, author = {Linkenauger, SA and Mohler, BJ and B{\"u}lthoff, HH} } @Poster { KaularddSFBW2011, title = {What are the properties underlying similarity judgments of facial expressions?}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {115}, abstract = {Similarity ratings are used to investigate the cognitive representation of facial expressions. The perceptual and cognitive properties (eg physical aspects, motor expressions, action tendencies) driving the similarity judgments of facial expressions are largely unknown. We examined potentially important properties with 27 questions addressing the emotional and conversational content of expressions (semantic differential). The ratings of these semantic differentials were used as predictors for facial expression similarity ratings. The semantic differential and similarity-rating task were performed on the same set of facial expression videos: 6 types of emotional (eg happy) and 6 types of conversational (eg don’t understand) expressions. Different sets of participants performed the two tasks. Multiple regression was used to predict the similarity data from the semantic differential questions. The best model for emotional expressions consisted of two emotional questions explaining 75\% of the variation in similarity ratings. The same model explained significantly less variation for conversational expressions (38\%). The best model for those expressions consisted of a single conversational question explaining 44\% of the variation. This study shows which properties of facial expressions might affect their perceived similarity. Moreover, our results suggest that different perceptual and cognitive properties might underlie similarity judgments about emotional and conversational expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110290}, event_place = {Toulouse, France}, event_name = {34th European Conference on Visual Perception}, author = {Kaulard, K and de la Rosa, S and Schultz, J and Fernandez Cruz, AL and B{\"u}lthoff, HH and Wallraven, C} } @Poster { ReichenbachBBT2011, title = {Role of the PPC in vestibular information processing during goal-directed movements tested with TMS}, year = {2011}, month = {6}, number = {940}, abstract = {fMRI and TMS studies have shown that visual and proprioceptive information for motor control are integrated in the posterior parietal cortex (PPC) (e.g. Culham and Valyear, 2006; Filimon et al., 2009; Reichenbach et al., 2010). When the head is moving in space during a goal-directed movement, vestibular signals have to be integrated into the motor processing as well. The neural correlates of these integration processes during motor control have not been investigated thus far. However, fMRI studies about vestibular stimulation have shown that the PPC is also processing vestibular information (Suzuki et al., 2001; Dieterich et al., 2003; Stephan et al., 2005). Furthermore, Seemungal et al. (2008) demonstrated that the administration of TMS over the PPC disturbs the perception of the position in space when the body is rotated. For the TMS study presented here, we used the behavioral paradigm of Bresciani et al. (2002) where subjects performed a goal-directed reaching task while suddenly being rotated. In order to assess the neural correlates of vestibular information processing for movement control, we probed with TMS the necessity of several sites on the PPC for this motor task.}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/HBM-2011-Reichenbach.pdf}, department = {Department B{\"u}lthoff}, department2 = {Department Scheffler}, web_url = {http://www.humanbrainmapping.org/i4a/pages/index.cfm?pageID=3419}, event_place = {Qu{\'e}bec City, Canada}, event_name = {17th Annual Meeting of the Organization for Human Brain Mapping (HBM 2011)}, author = {Reichenbach, A and Bresciani, J-P and B{\"u}lthoff, HH and Thielscher, A} } @Poster { 7056, title = {Evidence for predictive coding in early visual cortex in context of self-induced visual motion}, year = {2010}, month = {11}, volume = {40}, number = {74.11}, abstract = {The model of “predictive coding” suggests that feedback from a higher- to a lower-order visual area carries predictions of lower-level neural activities, whereas the feedforward connections carry the residual errors between the predictions and the actual lower-level activities (Rao and Ballard, 1999). We tested this theory in context of processing of planar motion in early (foveal) visual cortex. In a 2x2 factorial design, human subjects either fixated (eyes still) or carried out smooth pursuit on a display containing a planar random dot-field that was either stationary or moving coherently in-plane. This led to four conditions: (a) fixation on static dot-field, (b) fixation on moving dot-field, (c) pursuit on static dot-field, (d) pursuit of moving dot-field (pursuit was locked to the dot-motion). Neural activity was measured using fMRI at 3T. If early visual cortex coded for retinal motion, (b) and (c) would be expected to activate early visual cortex equally, and more than (a) and (d). In contrast, predictive coding would result in different responses. In addition to the above, early visual cortex would also code the error signal for mismatches between retinal motion input and the prediction for retinal motion, based on e.g. pursuit-related efferent copies. Such mismatches between prediction and input would occur in (b) (retinal motion without prediction of it) and in (d) (absence of retinal motion despite prediction of it). Note that these mismatches are equivalent to the presence of objective motion in the display. Thus, predictive coding would lead to highest responses in (b) (error + input), medium responses in (c) (input only) and (d) (error only), and lowest response in (a). We found (across the whole brain) the only activity satisfying these criteria in the occipital poles. The occipital poles contain the foveal confluence of early visual areas V1-V3, and are thus the key candidate for the above hypothesis. Their responses matched the hypothesized pattern precisely. In contrast, activity in motion responsive areas such as V5/MT+ and parietal regions was mainly driven by eye-movements and by retinal motion. Offline eye-tracking revealed that our results cannot be explained by differential fixation accuracies across conditions. It remains to be elucidated whether predictive coding actually accounts for the results, or whether direct feedback of objective motion signals from higher-level areas sums up with retinal input to the response observed in the occipital pole. Nevertheless, our results let us conclude that activity in the foveal representation of the early visual cortex fully match the predictions of Rao and Ballard (1999) for predictive coding.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.sfn.org/am2010/index.aspx?pagename=abstracts_main}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {San Diego, CA, USA}, event_name = {40th Annual Meeting of the Society for Neuroscience (Neuroscience 2010)}, language = {en}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Poster { 6798, title = {Towards Building a 4D Morphable Face Model}, year = {2010}, month = {10}, pages = {11}, abstract = {Morphable models have proven to be very successful for analyzing and synthesizing 2D and 3D recordings of faces. They are used extensively in computer vision, computer graphics as well as in psychology research. The growing interest in extending this work from static to dynamic faces [Curio et al. 2010] has led us to build a large database of three-dimensional facial deformation data. In comparison to other databases, this database contains a large corpus of facial deformations that were carefully put into dense correspondence. From that we can obtain generative facial expression models to build a ''4D Morphable Face Model'', extending previous work for identity [Blanz and Vetter 1999].}, department = {Department B{\"u}lthoff}, web_url = {http://www.cstr.ed.ac.uk/faa/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, institution = {University of Edinburgh}, event_place = {Edinburgh, UK}, event_name = {ACM/SSPNET 2nd International Symposium on Facial Analysis and Animation (FAA 2010)}, language = {en}, DOI = {10.1145/1924035.1924038}, author = {Breidt, M and B{\"u}lthoff, HH and Curio, C} } @Poster { 6755, title = {Velocity-dependent curvature gain and avatar use for Redirected Walking}, year = {2010}, month = {10}, pages = {1-2}, abstract = {We investigated in a study whether humans’ sensitivity to curved walking is affected by their walking velocity. Amongst other techniques, redirecting users of an immersive virtual environment on a curved path is part of the so-called ’Redirected Walking’. We conducted an experiment in which 12 participants walked specific curvatures at given speeds in a VR. We found that people are significantly less sensitive to walking on a curve when walking slower. Moreover, we assume the possibility of using avatars to support redirection algorithms as it was shown by Llobera et al. ([LSRS10]) that proxemics holds true for avatars in virtual environments, too. In this work, we depict three possible applications of how avatars could be used to achieve a better redirection.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/JVRC_Manuscript_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.interaction-design.org/references/conferences/proceedings_of_the_joint_virtual_reality_conference_of_egve_-_eurovr_-_vec.html}, editor = {Kuhlen, T. , S. Coquillart, V. Interrante}, publisher = {Eurographics Association}, address = {Goslar, Germany}, booktitle = {Virtual Environments 2010}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Stuttgart, Germany}, event_name = {2010 Joint Virtual Reality Conference of EuroVR - EGVE - VEC (JVRC 2010)}, language = {en}, ISBN = {978-3-905674-30-9}, author = {Neth, CT and Souman, JL and Engel, D and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Poster { 6404, title = {''Where is the sun?'': The sun is ''up'' in the eye of the beholder}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {146}, abstract = {In environments where orientation is ambiguous, the visual system uses prior knowledge about lighting coming from above to recognize objects, reorient the body, and determine which way is up (where is the sun?). It has been shown that when observers are tilted to the side relative to gravity, the orientation of the light-from-above prior will change in a direction between the orientation of the body, gravity and the visual surround. The contribution of ocular torsion in this change of the light-from-above prior has been acknowledged but not specifically addressed. Here we test the hypothesis that when lighting direction is the only available visual orientation cue, change in orientation of the light-from-above prior is accounted for by ocular torsion. Observers made convex-concave judgments of a central shaded disk, flanked by three similarly- and three oppositely-shaded disks. Lighting was tested every 15\(^{\circ}\) in roll in the fronto-parallel plane. Observers were tested when upright, supine, and tilted every 30 \(^{\circ}\) in role relative to gravity. Our results show that change of the light-from-above prior is well predicted from a sum of two sines; one consistent with predicted ocular torsion, the other consistent with an additional component varying with twice the frequency of body tilt.}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100409}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Barnett-Cowan, M and Ernst, MO and B{\"u}lthoff, HH} } @Poster { 6997, title = {Changing our perception of communication in virtual environments}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {183}, abstract = {When people communicate face-to-face they use gestures and body language that naturally coincide with speech [McNeill, 2007, Gesture \& Thought, University of Chicago Press.]. In an immersive virtual environment (VE) we can control both participants' visual feedback of self and the other in order to investigate the effect of gestures on a communication task. In our experiment the communication task is to make the listener say a word without the speaker saying the word. We use animated real-time self-avatars in immersive VEs to answer the question: `Does the use of naturalistic gestures help communication in VEs'. Specifically, we perform a within-subject experiment which investigates the influence of first- and third-person perspectives, and of animated speaker and listener. We find that people significantly perform better in the communication task when both the speaker and listener have an animated self-avatar and when the camera for the speaker shows a third-person perspective. When participants moved more they also performed better in the task. These results suggest that when two people in a VE are animated they do use gestures to communicate. These results demonstrate that in addition to the speaker movements, the listener movements are important for efficient communication in an immersive VE.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100134}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Dodds, TJ and Mohler, BJ and B{\"u}lthoff, HH} } @Poster { 6606, title = {Does adding a visual task component affect fixation accuracy?}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {35}, abstract = {Video-based eye-trackers are typically calibrated by instructing participants to fixate a series of dots, the physical locations of which are known to the system. Unfortunately, this procedure does not verify if fixation has actually occurred at the desired locations. This limitation can be remedied by requiring participants to perform a simple visual discrimination task at each location, thus mandating accurate fixation. Still, it remains an open question whether this modification could affect fixation accuracy. In the current study, we compared the accuracy of fixations that were performed with a visual discrimination task and those without such a requirement. Participants either identified the orientation of a small Landolt C (size = 0.1\(^{\circ}\)) or fixated a similar probe without performing the task. Results indicate that participants fixated equally well in both tasks (mean diff. of abs. error = 0.01\(^{\circ}\), Bayes factor B01 = 4.0 with JZS prior, see [Rouder et al., 2009, Psychonomic Bulletin \&am p;am p;am p; R eview, 16(2), 225-237]). Given this, we propose the implementation of this visual discrimination task to eye-tracking calibration protocols as it elicits verifiable fixations without compromising fixation accuracy.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100606}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Bieg, H-J and Chuang, LL and B{\"u}lthoff, HH} } @Poster { 6624, title = {Egocentric distance judgments in a large-screen immersive display virtual environment}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {51}, abstract = {People underestimate egocentric distances in head-mounted display virtual environments (VEs) as compared to the real world. In a recent study [Riecke et al, 2009, APGV, 15-18] it was shown that when a person viewed a photorealistic world through an HMD or a large screen display (while sitting and not moving their head) they did not underestimate egocentric distances. We further investigate whether people underestimate egocentric distances in a large screen immersive display. In our experiment, participants were asked to report verbal estimates of egocentric distances in a large screen display with floor projection or in the real world. Overall, in the virtual world we found an underestimation of distances by 17\% as compared to near accurate performance in the real world. Moreover, in the virtual world there was an effect of distance, which indicated overestimation for distances that occurred before the screen (3.5 meters), while for distances past the physical screen there was underestimation. To determine th e full reason for these effects further analysis is needed. Our results demonstrate that egocentric distance judgments are also underestimated in a large screen immersive display as compared to the real world.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Alexandrova_JVRC_authors_version_6624[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100136}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Alexandrova, IV and Teneva, PT and Kloos, U and B{\"u}lthoff, HH and Mohler, BJ} } @Poster { FischerBLB2010, title = {Functional characteristics of a motion responsive region in the posterior cingulate cortex compared to V5/MT and MST}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {95}, abstract = {Motion processing regions apart from V5+/MT+ are still relatively poorly understood. The cingulate sulcus visual area (CSv) in the dorsal posterior cingulate cortex (dPCC) was previously described to respond preferentially to coherent motion and implied in ego-motion processing. We used fMRI to compare responses of CSv/dPCC and of areas V5/MT and MST to distinct types of motion and self-motion cues such as retinal motion and objective motion, determined during pursuit. Both V5/MT and MST had a strong preference for contra- versus ipsi-lateral stimulation, no preference for 2D planar motion versus 3D flow, and reduced yet significant responses to random motion. In contrast, CSv/dPCC preferred 2D planar motion over 3D flow, showed no lateralization, and did not respond to random motion. All areas responded strongly to eye-movement related signals, however CSv responded more to ‘real’ motion than to retinal motion while the reverse was the case for V5/MT and MST. CSv/dPCC thus differs from other motion-responsive regions by its unique preference to full-field, coherent and planar motion cues and its enhanced capability to respond to real motion. These results place CSv/dPCC in a good position to process visual and non-visual cues related to self-induced motion, especially those associated to eye-movements.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100307}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Poster { 6787, title = {No other-race effect found in a task using faces differering only in race-specifying information}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {90}, abstract = {Generally, faces of one’s own ethnicity are better remembered than faces of another race. The mechanisms of this other race effect (ORE) are still unresolved. The present study investigates whether expertise for own-race results in ORE in a discrimination task when only race-specifying information varies between faces, with no interference of identity change and no memory load. If expertise is an important factor for ORE, Caucasian participants, for example, should better discriminate between two Caucasian faces presented side by side than between two Asian faces. We tested participants in Seoul and T{\"u}bingen with pairs of Asian or Caucasian faces. Their task was to tell which face of the pair was either more Asian or more Caucasian. Although we found that Asian face pairs were unexpectedly but consistently better discriminated than Caucasian faces, this Asian advantage did not differ between both city groups. Our results show furthermore that Seoul and T{\"u}bingen participants’ discrimination performance was similar for Asian and Caucasian faces. These findings suggests that when there is no memory component involved in the task and when face appearance only differs in race-specifying information, own-race expertise does not result in better performance for own-race faces.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100038}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {B{\"u}lthoff, I and Lee, RK and Wallraven, C and B{\"u}lthoff, HH} } @Poster { 6508, title = {Path integration in the third dimension}, journal = {Journal of Vestibular Research}, year = {2010}, month = {8}, volume = {20}, number = {3-4}, pages = {282}, abstract = {Path integration, the ability to update the position and orientation of external locations predominantly on the basis of internal cues, is an effective strategy for spatial navigation. While extensive work has been done on evaluating path integration in the horizontal plane, little is known for movements in the vertical (third) dimension. Here we assess whether pointing to the origin of translational movement in vertical planes is similar to that found for movement in the horizontal plane alone. 15 observers sat upright in a racecar seat that was mounted to the flange of a modified KUKA c anthropomorphic robot arm (Fig. 1a). An LCD display was 50cm in front of the observers who were otherwise tested in the dark. Sensory information was manipulated by providing visual (optic flow, limited lifetime star field), vestibular-kinesthetic (passive self motion with eyes closed), or visual and vestibularkinesthetic motion cues. Movement trajectories consisted of two segment lengths (1st: 0.4 m, 2 nd: 1 m; ± 0.24 m/s2 peak acceleration). Movements in the horizontal, sagittal and frontal planes consisted of: forward-rightward (FR) or rightward-forward (RF), downward-forward (DF) or forward-downward (FD), and downward-rightward (DR) or rightward-downward (RD) movements respectively. The angle of the two segments was either 45◦ or 90◦. A 15 s pause preceded each trajectory. Observers pointed back to their origin by moving an arrow that was superimposed on an avatar presented on the screen (Fig. 1b). Movement of the arrow was constrained to the trajectory’s plane and controlled by a joystick. The avatarwas presented from frontal, sagittal and horizontal viewpoints. Observers were allowed to use any or all viewpoints to answer. The starting orientation of the arrow was randomized across trials. Each condition was repeated 3 times and presented in random order. Signed error and response time were analyzed as dependent variables. Observers were more likely to underestimate angle size (average data less than 0◦; Fig. 1c) for movement in the horizontal plane compared to the vertical planes. In the frontal plane observers were more likely on average to overestimate angle size (average data more than 0◦), while there was no such bias in the sagittal plane. Another discrepancy between horizontal and vertical planes was that responses in the vertical planes were more closely related to a response bias suggesting that the path segments were of equal length (solid grey line). Finally, observers responded slower (Fig. 1d) when answering based on vestibular-kinesthetic information alone. These results suggest that human path integration based on vestibular-kinesthetic information alone takes longer than when visual information is present. Path integration has been well established as a means used to resolve where an observer originated but is prone to underestimates of the angle one has moved through. Our results show this for translational movement but only within the horizontal plane. In the vertical planes pointing may have been directed in accordance with an assumption of equal path lengths. This result suggests that alternative strategies for determining one’s origin may be adopted when moving in the third dimension which may relate to the fact that humans experience movement mostly within the horizontal plane.}, department = {Department B{\"u}lthoff}, web_url = {http://iospress.metapress.com/content/m2507728n2243114/fulltext.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Reykjavik, Iceland}, event_name = {XXVI B{\'a}r{\'a}ny Society Meeting}, language = {en}, DOI = {10.3233/VES-2010-0374}, author = {Barnett-Cowan, M and Meilinger, T and Vidal, M and B{\"u}lthoff, HH} } @Poster { PrettoBB2010, title = {Perceptual quirk induces safe driving in fog}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {168}, abstract = {Perceived speed of moving patterns is lower when visual contrast is reduced. In recent driving simulation experiments, this has been presented as an explanation why drivers might drive too fast in fog. In this simulation, contrast was equally reduced for all objects in the scene, independently of their distance from observer (distance-independent contrast reduction). In fog, however, contrast is reduced more for more distant objects (distance-dependent contrast reduction). We compared the effects of these two types of contrast reduction on both perceived and actual driving speed. In the first experiment twelve participants were presented with pairs of driving scenes—one with clear visibility, one with reduced contrast—and instructed to estimate which scene moved faster. Speed was underestimated with distance-independent contrast reduction but overestimated with distance-dependent contrast reduction. In the second experiment, ten drivers drove at target speeds under clear and reduced visibility conditions without tachometer. Participants increased speed with distance-independent contrast reduction but decreased speed with distance-dependent contrast reduction. These results show how visibility loss can lead to opposite perceptual and behavioural effects, depending on the nature of the underlying visual contrast reduction. In fog, indeed, the visual system fools drivers the safe way, advising them to decelerate.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100256}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, author = {Pretto, P and Bresciani, J-P and B{\"u}lthoff, HH} } @Poster { 6637, title = {Predicting Change of Vestibular Direction Detection Thresholds from Acceleration Profile Differences}, journal = {Journal of Vestibular Research}, year = {2010}, month = {8}, volume = {20}, number = {3-4}, pages = {279-280}, abstract = {In the absence of vision, the perceived direction of translational self motion is largely governed by signals originating from the otoliths. Although it has been shown that direction detection thresholds depend on the frequency of the motion stimulus, the influence of the actual time course of the motion has not been thoroughly investigated. The goal of our study was to measure, model and predict vestibular direction detection thresholds for different motion profiles in the horizontal plane. Detection thresholds for three acceleration profiles, one sinusoidal and two non-sinusoidal (Fig. 1A), with three different durations were measured for six human participants. An anthropomorphic robot arm, the Max Planck CyberMotion Simulator, was used to provide the motion stimuli. The experiment was designed as a four-alternative forced-choice task, where blindfolded participants judged the direction of motion from four possibilities: forward, backward, left or right. Stimulus intensity (peak acceleration of the motion profile) was varied based on a Bayesian adaptive method, and a psychometric function fit to the measurements determined the sensory threshold. For modeling, a 2nd order linear dynamical system with two poles and one zero, originally proposed by Young and Meiry (1968), was used to describe the data. The parameters of this model have been previously identified with sinusoidal motion stimuli over a broad frequency range for similar tasks, but predictions concerning perceptual thresholds for general motion profiles are unknown. In our study, the thresholds obtained from the three sinusoidal acceleration profiles were used to identify the static gain of the model by fitting the system gain to the inverted thresholds. The other parameters were derived from the literature. Predicting the thresholds for general motion profiles was based on the assumption that the output of the model can be interpreted as the signal intensity coming from the otoliths and that if this intensity overcomes a certain value the correct direction of motion can be perceived. In order to predict the threshold, the peak acceleration of the input profile must be selected so that that the corresponding maximum model output is equal to one (Fig. 1B). Predictions for the remaining six non-sinusoidal profiles showed that they were in good agreement with the measured data, with the average error being smaller than 20\% of the average detection threshold. This is a promising result, as just the static gain of the model was identified from only three data points. Accepting the linear model as a method to predict thresholds, it is also possible to fit the model to the nonsinusoidal profile data and identify the whole parameter set. Instead of fitting the system gain to the inverted sinusoidal thresholds, we computed the predictions for all profiles given a certain set of model parameters and iteratively varied the parameters to minimize the error between measurements and predictions. Two of the three identified model parameters agreed with the values given in the literature, while the third was found to be different. This difference suggested a phase lead for lower frequencies, which corresponds to sensitivity to jerk (the time derivative of acceleration). Comparing threshold predictions between models with different jerk sensitivities reveal distinct differences between the predictions at low frequencies. The predictions for a model with higher jerk sensitivity appear more appropriate and could be tested in future experiments. To summarize, we have shown that a linear model approach is able to predict vestibular perceptual direction detection thresholds. This allows the model parameters to be identified while resorting to non-sinusoidal stimuli, and helps to better understand vestibular linear motion perception. Future studies will extend these measurements to lower frequencies and assess this modeling approach for rotational movements.}, department = {Department B{\"u}lthoff}, web_url = {http://iospress.metapress.com/content/m2507728n2243114/fulltext.html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Reykjavik, Iceland}, event_name = {XXVI B{\'a}r{\'a}ny Society Meeting}, language = {en}, DOI = {10.3233/VES-2010-0374}, author = {Soyka, F and Beykirch, K and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Poster { BrescianiTBB2011, title = {Rich 3D environments facilitate sensorimotor learning}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {50}, abstract = {Using a visuo-vestibular adaptation paradigm, we measured how the richness/realism of the visual scene affects sensorimotor learning. Participants seating on a motorized wheelchair had to maintain their stretched arm fixed in space despite whole-body rotations. After a test session in which body rotations occurred without visual information, participants were exposed to a visuo-vestibular adaptation, and then tested again in a test session identical to the first one. In the adaptation phase, biased visual information about motion amplitude was provided during body rotations via a head-mounted display, so that participants learned a biased visuo-vestibular mapping. Four different types of adaptation were used (with different participants). Specifically, we manipulated orthogonally the visual information relative to the own body (avatar arm vs sphere indicating fingertip position) and that relative to the surrounding environment (virtual room vs sphere). All four types of visual environments gave rise to a significant adaptation (p<0.05). Interestingly, the amplitude of the adaptation (both relative and absolute) was significantly larger only when the room and the arm were realistically displayed. These results suggest that for a sensorimotor learning facilitation to occur, both body-related and environment-related visual information must be realistic.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100258}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, author = {Bresciani, J-P and Tesch, J and Bischoff, H and B{\"u}lthoff, HH} } @Poster { 6550, title = {The effect of walking speed on the sensitivity to curved walking in an immersive Virtual Environment}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {96}, abstract = {People are relatively insensitive to the curvature of their walking trajectory [Kallie et al., 2007, JEP:HPP, 33(1), 183-200]. This is exploited in the ''Redirected Walking'' technique which is used in Virtual Reality to extend the borders of Virtual Environments (VE) beyond the size of the physical walking area [Steinicke et al., 2009, Journal of Virtual Reality and Broadcasting, 6(2009)]. One method is to slowly rotate the VE while the user is aiming to walk a straight path, inducing him/her to unknowingly walk on a curved trajectory. We tested whether the sensitivity to curvature depends on walking speed. Participants followed a virtual sphere in a VE, which moved on a straight path. During walking, the entire visual scene was rotated, creating a curved real-world trajectory (radius 20-200m). Walking speed was 0.75, 1.0, or 1.25 m/s. Participants indicated whether their physical walking path curved to the left or right. Discrimination thresholds were estimated by fitting a psychometric function to the propor tion of trials in which the trajectory was reported to curve to the left. Curvature thresholds were found to be higher for slow walking. This suggests that the effectiveness of the redirected walking technique depends on walking speed.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/Abstract\%20ECVP10_[0].pdf}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100135}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Neth, C and Souman, JL and B{\"u}lthoff, HH and Kloos, U and Mohler, BJ} } @Poster { 6537, title = {The impact of an animated avatar on egocentric distance perception in an immersive virtual environment}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {51}, abstract = {To date, few head-mounted display (HMD) virtual environment systems display a rendering of the user’s own body. Subjectively, this often leads to a sense of disembodiment in the VE. In a recent study, we found that the experience with a self-avatar changed the typical pattern of distance underestimation seen in many HMD studies (Mohler et al, in press Presence). Users showed an increase in distance estimations with avatar experience, especially when the avatar was animated in correspondence with their own body-movements. The effect occurred for both co-located self-avatars and self-avatars viewed from the third person perspective. The current study investigated the importance of the degree to which self-avatar animation reflected the actual movements of the user. We compared distance judgments with a third-person perspective view of a self-avatar that was either controlled by user motions or was animated based on pre-recorded motion data. The results suggest that experience with an animated avatar, even if not in correspondence with a user’s own body movements, increases distance estimates. The magnitude of this effect will be further examined with additional participants.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100133}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, language = {en}, author = {Mohler, BJ and Creen-Regehr, SH and Thompson, WB and B{\"u}lthoff, HH} } @Poster { VolkovaABM2010, title = {Virtual storytelling of fairy tales: Towards simulation of emotional perception of text}, journal = {Perception}, year = {2010}, month = {8}, volume = {39}, number = {ECVP Abstract Supplement}, pages = {31}, abstract = {Emotion analysis (EA) is a rapidly developing area in computational linguistics. For most EA systems, the number of emotion classes is very limited and the text units the classes are assigned to are discrete and predefined. The question we address is whether the set of emotion categories can be enriched and whether the units to which the categories are assigned can be more flexibly defined. Six untrained participants annotated a corpus of eight texts having no predetermined annotation units and using fifteen emotional categories. The inter-annotator agreement rates were considerably high for this difficult task: 0.55 (moderate) on average, reaching 0.82 (almost perfect) with some annotator pairs. The final application of the intended EA system is predominantly in the emotion enhancement of human–computer interaction in virtual reality. The system is meant to be a bridge between unprocessed input text and auditory and visual information: generated speech, animation of facial expressions and body language. The first steps towards integrating text-based information annotated for emotion categories and simulation of human emotional perception of texts in story telling scenarios for virtual reality are already made. We have created a virtual character, whose animation of face and body is driven by annotations in text.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v100139}, event_place = {Lausanne, Switzerland}, event_name = {33rd European Conference on Visual Perception}, author = {Volkova, EP and Alexandrova, IV and B{\"u}lthoff, HH and Mohler, BJ} } @Poster { 6847, title = {Neural Correlates of Online Control of Reaching Movements}, year = {2010}, month = {7}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, web_url = {http://fens2010.neurosciences.asso.fr/pages/sub/SatellitesEvents.php}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Nijmegen, Netherlands}, event_name = {FENS 2010 Satellite Symposium on Motor Control}, language = {en}, author = {Reichenbach, A and Thielscher, A and Peer, A and B{\"u}lthoff, HH and Bresciani, J-P} } @Poster { SoykaBRB2010, title = {Predicting Vestibular Direction Detection Thresholds for Translatory Motions}, year = {2010}, month = {7}, department = {Department B{\"u}lthoff}, web_url = {http://www.brain.riken.jp/en/summer/previous.html}, event_place = {Tokyo, Japan}, event_name = {RIKEN Brain Science Institute Summer School 2010}, author = {Soyka, F and Beykirch, K and Robuffo Giordano, P and B{\"u}lthoff, HH} } @Poster { 6570, title = {Audio-visual interactions in binocular rivalry using the Shepard illusion in the auditory and visual domain}, year = {2010}, month = {6}, volume = {11}, number = {229}, abstract = {When both eyes are presented with dissimilar images, human observers report alternating percepts - a phenomenon known as binocular rivalry. Subjects were presented dichoptically with (1) a looming/receding starfield or (2) a looming/receding Shepard Zoom (Berger, Siggraph 2003), the visual equivalent of the Shepard tone illusion. In four psychophysical experiments, we investigated the influence of (1) a real complex tone rising/falling in pitch and (2) rising/falling Shepard tones on the dominance and suppression times of the rivaling visual motion percepts (relative to non-motion sounds or no sounds). First, we observed longer dominance times of looming than receding visual percepts even in the absence of sound. Second, auditory looming signals enhanced this looming bias by lengthening the dominance periods of their congruent visual looming percept. Third, receding auditory motion signals reduced the perceptual looming bias, though this effect was less pronounced and not consistently observed. Collectively, the results show that the perceptual predominance of looming relative to receding visual motion is amplified by congruent looming/receding auditory signals during binocular rivalry. Auditory looming/receding signals may influence the dominance times of their congruent and incongruent visual percepts via genuine multisensory and higher order attentional mechanisms at multiple levels of the cortical hierarchy.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/229}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Conrad, V and Kleiner, M and Hartcher-O‘Brien, J and Bartels, A and B{\"u}lthoff, HH and Noppeney, U} } @Poster { 6421, title = {Change of the ''light-from-above'' prior when the body is tilted relative to gravity}, year = {2010}, month = {6}, volume = {11}, number = {114}, abstract = {In environments where orientation is ambiguous, the visual system uses prior knowledge about lighting coming from above to recognize objects, reorient the body, and determine which way is up (where is the sun?). It has been shown that when observers are tilted to the side relative to gravity, the orientation of the light-from-above prior will change in a direction between the orientation of the body, gravity and the visual surround. The contribution of ocular torsion in this change of the light-from-above prior has been acknowledged but not specifically addressed. Here we test the hypothesis that when lighting direction is the only available visual orientation cue, change in orientation of the light-from-above prior is accounted for by ocular torsion. Observers made convex-concave judgments of a central shaded disk, flanked by three similarly- and three oppositely-shaded disks. Lighting was tested every 15\(^{\circ}\) in roll in the fronto-parallel plane. Observers were tested when upright, supine, and tilted every 30 \(^{\circ}\) in role relative to gravity. Our results show that change of the light-from-above prior is well predicted from a sum of two sines; one consistent with predicted ocular torsion, the other consistent with an additional component varying with twice the frequency of body tilt.}, department = {Department B{\"u}lthoff}, department2 = {Research Group Ernst}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/114}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Barnett-Cowan, M and Ernst, MO and B{\"u}lthoff, HH} } @Poster { SchultzB2010, title = {How does the brain identify living things based on their motion?}, year = {2010}, month = {6}, volume = {16}, number = {194 MT-PM}, pages = {62}, department = {Department B{\"u}lthoff}, web_url = {http://www.humanbrainmapping.org/i4a/pages/index.cfm?pageid=3342}, event_place = {Barcelona, Spain}, event_name = {16th Annual Meeting of the Organisation for Human Brain Mapping (HBM 2010)}, author = {Schultz, J and B{\"u}lthoff, HH} } @Poster { 6658, title = {It's All Me: Varying Viewpoints and Motor Learning in a Virtual Reality Environment}, year = {2010}, month = {6}, volume = {11}, number = {350}, abstract = {In the present study, healthy subjects performed a visuo-vestibular motor adaptation task in virtual reality. The task consisted of keeping the extended arm and hand stable in space during a whole-body rotation induced by a robotic wheelchair. Performance was first quantified in a pretest in which no visual feedback was available during the rotation. During the subsequent learning phase optical flow resulting from body rotation was provided. This visual feedback was manipulated to create the illusion of a smaller rotational movement than actually occurred, hereby altering the visuo-vestibular mapping. The adaptation effects of the learning phase were measured during a posttest identical to the pretest. Three different groups of subjects were exposed to different perspectives on the visual scene, i.e., first-person-, top- or mirror-view. Interestingly, sensorimotor adaptation occurred for all three viewpoint conditions (p < 0.05). Furthermore, in the mirror-view participants showed significantly less variability in performance. These results suggest that the visually richer mirror-view enhanced motor learning relative to the other viewpoints. Therefore, using virtual reality to provide rich multimodal stimulation including mirror views could add to traditional neurorehabilitation techniques by facilitating motor learning.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/350}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Schomaker, J and Tesch, J and B{\"u}lthoff, HH and Bresciani, J-P} } @Poster { 6420, title = {Latent reaction time and event-related potentials to passive physical motion}, year = {2010}, month = {6}, volume = {11}, number = {111}, abstract = {Involuntary physical responses to vestibular stimulation are very fast. The vestibulo-ocular reflex, for example, occurs approximately 20ms after the onset of vestibular stimulation (Lorente de No, 1933, Arch Neurol Psychiat). Despite these fast responses, reaction time (RT) to the perceived onset of vestibular stimulation occurs as late as 438ms after galvanic vestibular stimulation, which is approximately 220ms later than RTs to visual, somatosensory and auditory stimuli (Barnett-Cowan \& Harris, 2009, Exp Brain Res). To determine whether RTs to natural vestibular stimulation are also slow, participants in the present study were passively moved forwards by .1178m (single cycle sinusoidal acceleration; 0.75m/s/s peak acceleration) using a Stewart motion platform and were asked to press a button relative to the onset of physical motion. RTs to auditory and visual stimuli were also collected. RTs to physical motion occurred significantly later (>100ms) than RTs to auditory and visual stimuli. Event related potentials (ERPs) were simultaneously recorded where the onset of the vestibular-ERP in both RT and non-RT trials occurred about 200ms or more after stimulus onset while the onset of the auditory- and visual-ERPs occurred less than 100ms after stimulus onset. All stimuli ERPs occurred approximately 135ms prior to RTs. These results provide further evidence that vestibular perception is slow compared to the other senses and that this perceptual latency may be related to latent cortical responses to physical motion.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/111}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Barnett-Cowan, M and Nolan, H and Butler, JS and Foxe, JJ and Reilly, RB and B{\"u}lthoff, HH} } @Poster { 6659, title = {Multisensory Self-Motion Oddball Paradigm Evokes a P3 Response}, year = {2010}, month = {6}, volume = {11}, number = {370}, abstract = {Introduction: The sensation of motion is a product of the integration of information from multiple sensory modalities; vestibular, visual and proprioceptive information all have strong influences on the perception of self-motion. Here we present an electroencephalogram (EEG) study which demonstrates a P3 response to a self-motion oddball paradigm. Methods: Subjects were placed in a Maxcue Stewart motion platform. Auditory and visual cues were minimised using white noise and an enclosed environment. They were translated linearly 7cm using a 1s long sinusoidal acceleration profile at a 45\(^{\circ}\) angle forwards and left or right, with a probability of 0.8 / 0.2, balanced over runs (oddball paradigm). Subjects responded to the infrequent direction by pressing a button. During the task, EEG data were recorded using a Biosemi ActiveTwo 128-channel EEG system. The recordings were processed offline to remove artifacts. Results / Conclusion: Statistical parametric mapping shows the frequent and infrequent event-related potentials (ERPs) to differ significantly from 500ms - 950ms. Topographic analysis shows a typical P3 topography. Response-epoched ERPs show a peak of width approx 300ms. Conclusion: These results indicate that a P3-like response is generated by the motion oddball paradigm.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/370}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Nolan, H and Whelan, R and Butler, J and Foxe, J and B{\"u}lthoff, HH and Reilly, RB} } @Poster { 6422, title = {Perceived stability of objects changes when the body is tilted relative to gravity}, year = {2010}, month = {6}, volume = {11}, pages = {113}, abstract = {Knowing an object's physical stability affects our expectations about its behaviour and our interactions with it. Objects topple over when the gravity-projected centre-of-mass (COM) lies outside the support area. The critical angle (CA) is the orientation for which an object is perceived to be equally likely to topple over or right itself, which is influenced by global shape information about an object's COM and its orientation relative to gravity. When observers lie on their sides, the perceived direction of gravity is tilted towards the body. Here we test the hypothesis that the CA of falling objects is affected by this internal representation of gravity. Observers sat upright or lay left- or right-side-down, and observed images of objects with different 3D mass distributions that were placed close to the right edge of a table in various orientations. Observers indicated whether the objects were more likely to fall back onto or off the table. The subjective visual vertical was also tested as a measure of perceived gravity. Our results show the CA increases when lying right-side-down and decreases when left-side-down relative to an upright posture, consistent with estimating the stability of rightward falling objects as relative to perceived and not physical gravity.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs2/index.php/imrf/2010/paper/view/113}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Liverpool, UK}, event_name = {11th International Multisensory Research Forum (IMRF 2010)}, language = {en}, author = {Barnett-Cowan, M and Fleming, RW and B{\"u}lthoff, HH} } @Poster { 6846, title = {Proprioceptive online control of goal-directed reaching: a transcranial magnetic stimulation study}, year = {2010}, month = {6}, volume = {16}, number = {1259 MT-AM}, pages = {45}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, web_url = {http://www.humanbrainmapping.org/files/2010MeetingFiles/OHBM\%202010\%20Abstract\%20Book.pdf}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Barcelona, Spain}, event_name = {16th Annual Meeting of the Organisation for Human Brain Mapping (HBM 2010)}, language = {en}, author = {Reichenbach, A and Bresciani, J-P and Peer, A and B{\"u}lthoff, HH and Thielscher, A} } @Poster { 6739, title = {Laying the foundations for an in-depth investigation of the whole space of facial expressions}, journal = {Journal of Vision}, year = {2010}, month = {5}, volume = {10}, number = {7}, pages = {606}, abstract = {Facial expressions form one of the most important and powerful communication systems of human social interaction. They express a large range of emotions but also convey more general, communicative signals. To date, research has mostly focused on the static, emotional aspect of facial expression processing, using only a limited set of “generic” or “universal” expression photographs, such as a happy or sad face. That facial expressions carry communicative aspects beyond emotion and that they transport meaning in the temporal domain, however, has so far been largely neglected. In order to enable a deeper understanding of facial expression processing with a focus on both emotional and communicative aspects of facial expressions in a dynamic context, it is essential to first construct a database that contains such material using a well-controlled setup. We here present the novel MPI facial expression database, which contains 20 native German participants performing 58 expressions based on pre-defined context scenarios, making it the most extensive database of its kind to date. Three experiments were performed to investigate the validity of the scenarios and the recognizability of the expressions. In Experiment 1, 10 participants were asked to freely name the facial expressions that would be elicited given the scenarios. The scenarios were effective: 82\% of the answers matched the intended expressions. In Experiment 2, 10 participants had to identify 55 expression videos of 10 actors. We found that 34 expressions could be identified reliably without any context. Finally, in Experiment 3, 20 participants had to group the 55 expression videos of 10 actors based on similarity. Out of the 55 expressions, 45 formed consistent groups, which highlights the impressive variety of conversational expressions categories we use. Interestingly, none of the experiments found any advantage for the universal expressions, demonstrating the robustness with which we interpret conversational facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/10/7/606}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Naples, FL, USA}, event_name = {10th Annual Meeting of the Vision Sciences Society (VSS 2010)}, language = {en}, DOI = {10.1167/10.7.606}, author = {Kaulard, K and Wallraven, C and Cunningham, DW and B{\"u}lthoff, HH} } @Poster { 6212, title = {Reaction time and event-related potentials to visual, auditory and vestibular stimuli}, journal = {Journal of Vision}, year = {2010}, month = {5}, volume = {10}, number = {7}, pages = {1400}, abstract = {Involuntary physical responses to vestibular stimulation are very fast. The vestibulo-ocular reflex, for example, occurs approximately 20ms after the onset of vestibular stimulation (Lorente de No, 1933, Arch Neurol Psychiat). Despite these fast responses, reaction time (RT) to the perceived onset of vestibular stimulation occurs as late as 438ms after galvanic vestibular stimulation, which is approximately 220ms later than RTs to visual, somatosensory and auditory stimuli (Barnett-Cowan \& Harris, 2009, Exp Brain Res). To determine whether RTs to natural vestibular stimulation are also slow, participants in the present study were passively moved forwards by .1178m (single cycle sinusoidal acceleration; 0.75m/s/s peak acceleration) using a Stewart motion platform and were asked to press a button relative to the onset of physical motion. RTs to auditory and visual stimuli were also collected. RTs to physical motion occurred significantly later (>100ms) than RTs to auditory and visual stimuli. Event related potentials (ERPs) were simultaneously recorded where the onset of the vestibular-ERP in both RT and non-RT trials occurred about 200ms or more after stimulus onset while the onset of the auditory- and visual-ERPs occurred less than 100ms after stimulus onset. All stimuli ERPs occurred approximately 135ms prior to RTs. These results provide further evidence that vestibular perception is slow compared to the other senses and that this perceptual latency may be related to latent cortical responses to physical motion.}, department = {Department B{\"u}lthoff}, web_url = {http://www.journalofvision.org/content/10/7/1400.abstract}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Naples, FL, USA}, event_name = {10th Annual Meeting of the Vision Sciences Society (VSS 2010)}, language = {en}, DOI = {10.1167/10.7.1400}, author = {Barnett-Cowan, M and Nolan, H and Butler, JS and Foxe, JJ and Reilly, RB and B{\"u}lthoff, HH} } @Poster { 6425, title = {Asymmetrien und die Konstruktion von {\"U}berblickswissen}, journal = {Experimentelle Psychologie}, year = {2010}, month = {3}, volume = {52}, pages = {16}, department = {Department B{\"u}lthoff}, web_url = {https://www.teap.de/index.php/teap2010/saarbruecken2010}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Saarbr{\"u}cken, Germany}, event_name = {52. Tagung Experimentell Arbeitender Psychologen (TeaP 2010)}, language = {de}, author = {Meilinger, T and Souman, JL and B{\"u}lthoff, HH} } @Poster { 6241, title = {The Virtual Face Mirror Project: Revealing Dynamic Self-Perception in Humans}, year = {2010}, month = {1}, volume = {4}, number = {137}, url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/CogSys-2010-0137.pdf}, department = {Department B{\"u}lthoff}, web_url = {http://cogsys2010.ethz.ch/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Z{\"u}rich, Switzerland}, event_name = {4th International Conference on Cognitive Systems (CogSys 2010)}, language = {en}, author = {Curio, C and Kleiner, M and Breidt, M and B{\"u}lthoff, HH} } @Poster { 6162, title = {Attention to motion: Differential cortical modulation to forward and planar visual flow}, year = {2009}, month = {10}, volume = {39}, number = {558.21}, abstract = {Self- and object-motion processing greatly relies on visual cues. There are at least two entirely independent kinds of self-induced visual motion that combine to optic flow in the visual field: expansion flow, such as that induced by forward motion in depth, or planar motion, such as induced by translational self-motion or by pursuit eye movements across a visual scene. In real life, both signals may occur in combination, yet, only one of the cues may be of behavioral relevance, thus requiring to be selectively attended to. In this fMRI study we attempt to address the question whether differential neural substrates get modulated by selective attention to either one of these motion cues. We created a stimulus combining an expansion flow pattern with translational motion on the same set of dots. In a feature-based detection task, subjects selectively attended either to the expansion or to the translation component of the stimulus and reported changes in the speed of the attended motion component. In control conditions that used the same stimuli subjects attended to color hue changes of the fixation cross, or passively fixated the stimulus without any attentional demand. In each of the three attention conditions, the attentional load was kept constant across conditions by a continuously updating staircase procedure. We found that attention to expansion modulated the separately localized areas MT/V5, MST, and V3A significantly more than attention to translation. This is in line with stimulus-driven studies that showed a preference to expansion/contraction stimuli in these areas (Smith et al., 2006). In contrast, V7 and the cingulate sulcus visual area (CSv) differed from all other regions, in that they did not show any selective modulation by attention to expansion flow. Most interestingly, we found motion selective modulation in the foveal confluence of V1, despite a physical match between stimulus conditions. This might be due to differential attentional enhancement within V1, or by differential feedback from higher regions such as MT/V5, MST or V3A. Our results therefore show a differential attentional modulation within the motion-processing pathway, depending on the type of motion-component that is attended to within the same flow stimulus. Smith AT, Wall MB, Williams AL, Singh KD (2006) Sensitivity to optic flow in human cortical areas MT and MST.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.abstractsonline.com/Plan/ViewAbstract.aspx?sKey=3b1b2e24-3671-4e3d-9051-5dfbb3c15f6c\&cKey=81bf6c91-1c74-4f55-870b-c12dbcb94af7}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Chicago, IL, USA}, event_name = {39th Annual Meeting of the Society for Neuroscience (Neuroscience 2009)}, language = {en}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Poster { 6291, title = {How does the brain identify living things based on their motion?}, year = {2009}, month = {10}, volume = {39}, number = {380.15}, abstract = {Animals (including humans) have to identify living moving things in the environment: these could be prey, enemies or mates and interactions with them should be actively controlled. Living things could be detected visually through their shape or their motion, or both. When shape is hard to see (fog, twilight, great distance, small animal), motion becomes an important cue. Biological motion has been studied widely using point-light displays, but these displays appear to contain some sort of shape or form information that influences recognition. To study the neural correlates of the detection of living entities from motion alone, we developed a stimulus consisting of a single moving dot, thus eliminating all possible sources of information about form, spatial arrangement, shape or structure of the object. Our single dot moved such that it appeared either self-propelled (modelled on the movements of a fly) or moved by an external force (modelled on a leaf drifting in the wind). Both types of movement were built using the same equation but differed in speed and acceleration profiles according to a small set of parameters. Low-level stimulus characteristics of the stimuli (range of positions on the screen, average speed, overall aspect of the trajectory) were kept as constant as possible. The parameters could be varied in a continuous fashion to create morphs between the self-propelled and externally-moved extremes. Consistent with expectations, behavioral experiments showed that self-propelled stimuli were perceived as more animate (= more likely to be alive) than the externally-moved stimuli, with a gradual transition occurring in the intermediary morphs. The extreme stimuli and four intermediary morphs were presented in an fMRI experiment to participants who had to categorize the stimuli into alive and non-alive. Using separate functional localizers, we located areas hMT+/V5 and the superior temporal sulcus region responding to point-light walkers, and found that neither region showed changes in BOLD response following the changes in percept. However, BOLD response in a region of the left posterior superior parietal cortex scaled with the degree of perceived animacy. This suggests that the STS is not simply a detector of all kinds of animate motion, but might only be implicated when some sort of shape information in the stimuli (as with point-light displays or with interacting dots) is contributing to the percept of animacy.}, department = {Department B{\"u}lthoff}, web_url = {http://www.abstractsonline.com/Plan/ViewAbstract.aspx?sKey=f5dec3fb-2bb6-482d-8553-db756136f1a1\&cKey=e2a39a05-441a-496b-8048-e8c4ae6e6a46}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Chicago, IL, USA}, event_name = {39th Annual Meeting of the Society for Neuroscience (Neuroscience 2009)}, language = {en}, author = {Schultz, J and B{\"u}lthoff, HH} } @Poster { 5908, title = {Distance and alignment effects in survey knowledge of a highly familiar city}, journal = {Perception}, year = {2009}, month = {8}, volume = {38}, number = {ECVP Abstract Supplement}, pages = {63}, abstract = {In this experiment we examined alignment and distance effects in human memory for a highly familiar environmental space. Twenty-seven participants who lived on average seven years in T{\"u}bingen saw a photorealistic virtual model of the city centre of T{\"u}bingen (Virtual T{\"u}bingen) through a head-mounted display. They were teleported to five different places in Virtual T{\"u}bingen and asked to point towards well-known target locations. This procedure was repeated 36 times for each of the target locations in 12 different body orientations. Participants pointed much more accurately when oriented northwards regardless of target. There were no significant correlations between straight line distance to the pointing target and pointing speed or accuracy. These results are consistent with the assumption that all locations were represented within one oriented coordinate system. Even though this is predicted by reference direction theory, it is unclear why, first, almost all participants have the same reference direction, and second, why this direction is north. We discuss our results with respect to well-known theories of spatial memory and speculate that the bias for a north orientation is because participants rely on the memory of a map of T{\"u}bingen for their response.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v090953}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Regensburg, Germany}, event_name = {32nd European Conference on Visual Perception}, language = {en}, author = {Frankenstein, J and Mohler, B and B{\"u}lthoff, HH and Meilinger, T} } @Poster { 5954, title = {Going beyond universal expressions: investigating the visual perception of dynamic facial expressions}, journal = {Perception}, year = {2009}, month = {8}, volume = {38}, number = {ECVP Abstract Supplement}, pages = {83}, abstract = {Investigations of facial expressions have focused almost exclusively on the six so-called universal expressions. During everyday interaction, however, a much larger set of facial expressions is used for communication. To examine this mostly unexplored space, we developed a large video database for emotional and conversational expressions: native German participants performed 58 expressions based on pre-defined context scenarios. Three experiments were performed to investigate the validity of the scenarios and the recognizability of the expressions. In Experiment 1, ten participants were asked to freely name the facial expressions that would be elicited given the scenarios. The scenarios were effective: 82\% of the answers matched the intended expressions. In Experiment 2, ten participants had to identify 55 expression videos of ten actors, presented successively. We found that 20 expressions could be identified reliably without any context. Finally, in Experiment 3, twenty participants had to group the 55 expression videos based on similarity while allowing for repeated comparisons. Out of the 55 expressions, 45 formed a consistent group, respectively, showing that visual comparison facilitates the recognition of conversational expressions. Interestingly, none of the experiments found any advantage for the universal expressions, demonstrating the robustness with which we interpret conversational facial expressions.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v090219}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Regensburg, Germany}, event_name = {32nd European Conference on Visual Perception}, language = {en}, author = {Kaulard, K and Wallraven, C and Cunningham, DW and B{\"u}lthoff, HH} } @Poster { 5867, title = {Head mobility influences gaze behavior across natural viewing tasks}, journal = {Perception}, year = {2009}, month = {8}, volume = {38}, number = {ECVP Abstract Supplement}, pages = {166}, abstract = {Natural gaze behavior is often studied under conditions that restrain head movements. Here, we report how the availability of head movement can influence gaze behavior on wall-sized images of natural outdoor scenes (field-of- view: \verb=~=90\(^{\circ}\)). Participants performed half of the experiment with complete head mobility and the remaining trials with their heads restrained in a chin-rest. They were required to either rate the images for attractiveness (i.e., free-viewing) or to count the visible animals (i.e., visual search). On average, more fixations were found on the trials that allowed for head movements (unrestrained: 4.21 fixations/sec; restrained: 3.75 fixations/sec), which were also shorter in their mean duration (unrestrained: 221 ms; restrained: 252 ms). In addition, unrestrained gaze contained a larger proportion of small amplitude saccades (i.e., less than 5\(^{\circ}\)), than head-restrained gaze. Finally, our participants demonstrated a general preference in fixating regions that were close to the central eye-in-h ead orientation. Altogether, these findings suggest that the availability of head movements allowed our participants to re-orient to regions of interest and sample these regions more frequently. This sampling benefit applied to both visual search and free viewing tasks. The current findings emphasize the importance of allowing head mobility when studying natural gaze behavior.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v090902}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Regensburg, Germany}, event_name = {32nd European Conference on Visual Perception}, language = {en}, author = {Chuang, LL and Herholz, S and B{\"u}lthoff, HH and Fleming, R} } @Poster { 5710, title = {Place naming: examining the influence of language on wayfinding}, year = {2009}, month = {8}, volume = {31}, pages = {1997}, abstract = {We asked the question how language influences a presumably embodied system such as human wayfinding. To test this, participants walked along a route in a virtual environment. They were asked to remember half of the intersections by what they saw. At the other 50\% of intersections they heard an arbitrary name which they also had to remember. In the test phase they were teleported to different intersections and had to indicate the direction the route went on. At intersections without a name they performed faster and more accurately. In a second experiment meaningful names were used instead. Participants now performed better at named intersection. The results indicate an interaction between language and the presumably embodied wayfinding system. This interaction cannot be explained by a limited common resource, depth of processing, overshadowing, or linguistic scaffolding. However, it is consistent with dual coding.}, department = {Department B{\"u}lthoff}, web_url = {http://cognitivesciencesociety.org/conference2009/index.html}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Amsterdam, Netherlands}, event_name = {31st Annual Conference of the Cognitive Science Society (CogSci 2009)}, language = {en}, author = {Meilinger, T and Schulte-Pelkum, J and Frankenstein, J and Laharnar, N and Hardie{\ss}, G and Mallot, HA and B{\"u}lthoff, HH} } @Poster { 5918, title = {Re-learning face recognition: evidence for efficient strategies without holistic processing}, journal = {Perception}, year = {2009}, month = {8}, volume = {38}, number = {ECVP Abstract Supplement}, pages = {100}, abstract = {In previous experiments, we showed an advantage for visual over haptic face recognition. Promoting serial encoding in vision using a novel gaze-restricted display, we found that these differences are due to modality-specific encoding strategies (holistic in vision vs serial in haptics), and that serial encoding leads to featural (vs holistic) processing. Here, we test how the observed encoding and processing differences might be affected by expertise. Participants were trained on five consecutive days on a set of 19 faces using an old/new recognition task for which three faces were learned with feedback, followed by four test-blocks. On days 1 (pre-test), 4 (post-test), and 5, the task consisted of two upright and two inverted test-blocks. On day 5, we tested participants on a different set of faces. Performance for upright faces was low on day 1, but improved significantly through training ( d1'=1.11, d4'=3.75). Importantly, this learning effect generalized to a new face-set on day 5 ( d5'=3.07). Although performance significantly improved through training, we found no inversion effect on any day ( d1'=1.70, d4'=3.54) indicating no change in processing strategies. Our results show that participants can develop efficient, generalizing strategies to compensate for encoding differences, and that these strategies do not require holistic encoding.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v090145}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Regensburg, Germany}, event_name = {32nd European Conference on Visual Perception}, language = {en}, author = {Dopjans, L and Wallraven, C and B{\"u}lthoff, HH} } @Poster { BergerPBB2009, title = {Top-down influence of size cues on the perceived visual speed of self-motion}, journal = {Perception}, year = {2009}, month = {8}, volume = {38}, number = {ECVP Abstract Supplement}, pages = {134}, abstract = {Size cues are known to affect the perceived distance between objects. If the physical distance between two objects remains constant, the larger the retinal image of the objects is, the closer to one another they are perceived to be. We tested whether size cues affect the perceived visual speed of self-motion. Ten subjects sitting in front of a panoramic screen (230 \(\times\) 125\(^{\circ}\) of field of view) were presented with constant-speed translations of the visual scene, which simulated a forward translation of the body. The physical size of the objects present in the scene was systematically varied, and the subjects had to estimate the speed of the translations. We used a 2IFC task, ie, two stimuli were presented successively and the subject had to indicate which one was faster. The experiment had four conditions, with two main factors: object size (big/small) and object familiarity (absolute size known/unknown). Eye and horizon heights were constant throughout all conditions. We observed a main effect of object size, with speed being underestimated for larger objects. Interestingly, this effect was significantly stronger for objects whose absolute size is known. These results suggest a top - down influence of size cues on the perceived visual speed of self-motion.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v091059}, event_place = {Regensburg, Germany}, event_name = {32nd European Conference on Visual Perception}, author = {Berger, D and Pretto, P and B{\"u}lthoff, HH and Bresciani, J-P} } @Poster { 5946, title = {Bayesian integration of visual and vestibular signals for heading}, year = {2009}, month = {7}, volume = {10}, number = {549}, pages = {295}, abstract = {Building upon recent results which have shown that visual and vestibular signals combine in a statistically optimal fashion for heading, we investigate the relative weights of visual and vestibular cues during self-motion. To do investigate this, participants performed a 2-interval forced choice task (2IFC) in all conditions in which they were asked to judge {\^a}{\euro}œin which of the two intervals did you move more to the right{\^a}{\euro}?. To observe the weights assigned to each modality we introduced a discrepancy between the visual and vestibular cues in the standard visual-vestibular heading. The experiment comprised of nine conditions: vestibular alone, four visual alone at different standard headings and four visual-vestibular with small and large conflict levels ({\^I}”={\^A}±6{\^A}\(^{\circ}\) or {\^A}±10{\^A}\(^{\circ}\)) between the visual and vestibular input. We found that even when there is a large conflict between the visual and vestibular cues; participants exhibit statistically optimal reduction of variance of visual and vestibular information. On the other hand, we found that the unimodal cues did not predicted the weights in the combined cue. We conclude that visual and vestibular cue combination is not predicted solely by the reliability of each cue but that there is a prior which lends more weight to the body centric cue.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs/index.php/meetings/2009/paper/view/549}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {New York, NY, USA}, event_name = {10th International Multisensory Research Forum (IMRF 2009)}, language = {en}, author = {Butler, JS and Campos, JL and B{\"u}lthoff, HH and Smith, ST} } @Poster { 5993, title = {Neural basis of online control during visually guided reaching}, year = {2009}, month = {7}, volume = {7}, number = {A3-24}, pages = {150}, abstract = {Involvement of the left posterior parietal cortex (lPPC) in online motor control has been demonstrated using mainly functional magnetic resonance imaging (fMRI, for review see Culham et al, 2006). However, the human homologue to the macaque parietal reach region, or even more detailed functional anatomy of processes involved in motor control, is still controversial (Iacoboni, 2006). One challenge is the spatial co-localization of functions that are also involved in motor execution, e.g. saccades, and motor planning (Astafiev et al, 2003). Because of its high temporal resolution, transcranial magnetic stimulation (TMS) offers the possibility to disentangle these functions. Additionally, it allows to discriminate necessary from co-activated brain areas. Desmurget et al (1999) showed that the ability to react online to a change in visual target position when reaching for it can be disturbed by applying TMS over the lPPC. The goal of the present study was to identify sub-regions in the PPC contributing to the integration of visual information during online control of reaching. A reach-to-target paradigm with two perturbations induced correction upon target and body-related visual information, respectively: Displacement of the visual target and displacement of the visual feedback of hand position. We combined an fMRI localizer task with subsequent TMS experiments. The fMRI localizer gave an overview over the involved areas and enabled the selection of TMS stimulation sites. Inter-individual differences in (functional) neuroanatomy, being apparent in the human PPC (Grefkes and Fink, 2005), were thereby taken into account. The subsequent TMS experiments showed that regions from the anterior part of the intraparietal sulcus into the supramarginal gyrus are crucial for processing of target and bodyrelated visual information during online control of reaching. The TMS effects were spatially selective and correlated with the fMRI activation, thus demonstrating a good spatial resolution of the offline combination of TMS with fMRI.}, url = {http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/PMC-2009-Reichenbach.pdf}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Marseille, France}, event_name = {7th Edition of Progress in Motor Control (PMC 2009)}, language = {en}, author = {Reichenbach, A and Bresciani, J-P and Peer, A and B{\"u}lthoff, HH and Thielscher, A} } @Poster { 5947, title = {The acquisition of Human EEG Data during Self-Motion on a Stewart Platform}, year = {2009}, month = {7}, volume = {10}, number = {656}, pages = {363-364}, abstract = {Purpose of the study: The human sense of movement and balance integrates vestibular information with visual and somatosensory information. Research into the neural correlates of vestibular processing has been hampered because the subject must remain in a fixed position, and consequently neither magnetic resonance imaging nor positron emitted tomography are suitable methods. Therefore, research on the neural correlates of linear self-motion in humans has typically used visual vection, which is self-motion induced by large-field visual motion stimulation during which the stationary subject perceives the moving visual surroundings as being stable and themselves as moving. This study investigated the feasibility of acquiring electroencephalography (EEG) data during self-motion in human subjects. Electroencephalography would appear to be a suitable candidate for recording neural activity during motion because modern EEG acquisition equipment is lightweight and portable. Furthermore, a Stewart motion platform provides an appropriate method of producing linear self-motion in a laboratory environment. There are, however, a number of potential drawbacks to using a Stewart motion platform in conjunction with EEG recording equipment. For example, noise could be introduced into the EEG signal from the motion of the actuators, the electrical noise of the platform power source, or from muscular activity of the subject as they compensate for the acceleration at the start and finish of the motion. If achievable, this would allow a new method for investigation of vestibular processing and multisensory interaction. Understanding the contribution of different sensory modalities to the human senses of balance and movement is a key task for aiding the elderly, as the processing of vestibular signals deteriorates over time, which can lead to postural instability and falls. Method: Six subjects performed a visual oddball task {\^a}{\euro}“ designed to evoke a P3 event-related potential (ERP) {\^a}{\euro}“ under four different motion conditions on a Stewart platform. The motion conditions {\^a}{\euro}“ stationary, idle, slow and fast {\^a}{\euro}“ were designed to ascertain if the Stewart platform produced electromagnetic noise which would mask EEG data. The P3 task was chosen as it is relatively simple to evoke and can be tested using various experimental paradigms and sensory modalities, making it a robust measure. The P3 task required the subject to respond when observing an infrequent visual stimulus. The visual stimuli were projected onto a large screen in the Stewart platform. EEG data were recorded using both a shielded system, the BrainAmp MRPlus, and separately using an unshielded Biosemi ActiveTwo system. Results: Reliable P3 ERPs were found to be present under all motion conditions. The correlation among conditions during the interval -100ms to 600ms of the ERPs was at least 0.93. There were no artifacts caused by interference from the Stewart platform from both the shielded and unshielded systems. The number of rejected epochs was similar across all conditions. Conclusion: The results of this study indicate that reliable EEG data can be obtained during self-motion on a Stewart platform, and that the task-independent vestibular input did not interfere with the visually-evoked P3 ERP. The Stewart platform did not introduce noise to the data. This finding is noteworthy for the ecological validity of further research into human motion.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs/index.php/meetings/2009/paper/view/656}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {New York, NY, USA}, event_name = {10th International Multisensory Research Forum (IMRF 2009)}, language = {en}, author = {Whelan, R and Nolan, H and Butler, JS and Reilly, RB and B{\"u}lthoff, HH} } @Poster { 5917, title = {Visual experience supports haptic face recognition: Evidence from the early- and late-blind}, year = {2009}, month = {7}, volume = {10}, number = {547}, pages = {81}, abstract = {In previous experiments, we provided further evidence that the haptic and visual systems both have the capacity to process faces, and that face information can be shared across sensory modalities [1]. Interestingly, we found this information transfer across modalities to be asymmetric and limited by haptic face processing. Visual face perception relies on specific processes that evolve with perceptual expertise, while we have little to no training in haptic face recognition throughout life. We, therefore, suggest that the observed asymmetry in visual and haptic face processing might be attributed to different levels of expertise. To test the importance of visual experience with faces also for haptic recognition we studied haptic face recognition in the early-blind (N=10), late-blind (N=9) and sighted (N=18). Participants performed an old/new recognition task for which sets of three faces were learned haptically, followed by three subsequent haptic test-blocks. We found that early-blind participants could recognize faces haptically, although recognition accuracy was low (d{\^a}{\euro}™= 0.83). More interestingly, however, recognition accuracy was significantly better in late-blind (d{\^a}{\euro}™=1.56) as well as sighted (d{\^a}{\euro}™=1.42) participants. Our results, therefore, suggest that behavioral benefits in haptic face recognition require visual experience with faces. A lack thereof cannot be compensated for by purely perceptual haptic expertise as the results for the early-blind show. These findings suggest that haptic face recognition can recruit specific visual processing mechanisms that are shaped by visual experience [2].}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs/index.php/meetings/2009/paper/view/547}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {New York, NY, USA}, event_name = {10th International Multisensory Research Forum (IMRF 2009)}, language = {en}, author = {Dopjans, L and Wallraven, C and B{\"u}lthoff, HH} } @Poster { 5994, title = {Visual perturbation paradigms in goal-directed reaching investigated with functional MRI and subsequent transcranial magnetic stimulation}, journal = {NeuroImage}, year = {2009}, month = {7}, volume = {47}, number = {Supplement 1}, pages = {S170}, abstract = {Introduction Involvement of the left posterior parietal cortex (lPPC) in online motor control has been demonstrated in recent years using fMRI (Culham et al, 2006). However, the human homologue to the macaque parietal reach region, or even more detailed functional anatomy of processes involved in motor control, is still controversial (Iacoboni, 2006). The main challenge is the spatial co-localization of functions that are also involved in motor execution, e.g. saccades, and motor planning (Astafiev et al, 2003). TMS offers the possibility to disentangle these functions due to its high temporal resolution, and can discriminate necessary from co-activated brain areas. Desmurget et al (1999) showed that online correction for reaching to an altered target can be disturbed using TMS over the lPPC. Here, we test sub-regions of the lPPC for necessity in online correction to different visual perturbations. Methods Nine healthy, right-handed participants performed closed-loop (i.e., with visual feedback of the hand) reach-to-target tasks with different perturbation paradigms: Displacement of the visual target or displacement of the visual hand feedback, which allowed us to investigate the processes involved in body's effectors representation and the processes involved in representation of the environment, respectively. First, the participants were tested with an fMRI localizer task to assess putative lPPC sub-regions that are involved in online motor control. The fMRI localizer consisted of blocks for fixation, saccades, and reaching with an MR-compatible joystick. Within the reaching blocks, the visual perturbations (including none) were randomized in a fast event-related design. The different perturbation conditions were contrasted against the unperturbed reaching to assess activation related to online-correction, masked with general reaching activation. Maxima from the group analyses, individual's own maxima, and control sites were used as stimulation sites for subsequent event-related TMS studies. The TMS experiments were conducted in a VR environment with a robot arm to enable naturalistic but highly controllable conditions. Results On the group level, we found different peak fMRI activations in the lPPC for different visual perturbations (Figure 1). Additionally, most subjects had strong individual peak fMRI activations on sites without group activation (Figure 2). The perturbing effect of TMS for corrections to a visual target perturbation is correlated with the strength of the fMRI activations (Figure 3), with effects on sites of group fMRI activation, additional effects on sites of individual's fMRI activation, but none on control sites (Figure 4). The perturbing effect of TMS for corrections to a visual hand perturbation is concentrated at the single group fMRI maximum. Conclusions Widespread areas in the lPPC are crucial for processing of visual target information needed for online control of movements. These areas include SMG in addition to anterior IPS and SPL. The area necessary for visual hand information processing is a part of the areas needed for visual target processing. Planning TMS stimulation sites based on individual fMRI activations is a more successful approach than planning them based on group fMRI activation, which is still better than planning without (f)MRI. The TMS effect is spatially selective, thus demonstrating a good spatial resolution of the method.}, department = {Department B{\"u}lthoff}, department2 = {Department MRZ}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {San Francisco, CA, USA}, event_name = {15th Annual Meeting of the Organisation for Human Brain Mapping (HBM 2009)}, language = {en}, DOI = {10.1016/S1053-8119(09)71835-X}, author = {Reichenbach, A and Thielscher, A and Peer, A and B{\"u}lthoff, HH and Bresciani, J-P} } @Poster { 5945, title = {Visual-Vestibular Cue Combination during Temporal Asynchrony}, year = {2009}, month = {7}, volume = {10}, number = {815}, pages = {198}, abstract = {Currently little is known about the principles underlying human visual-vestibular integration during self-motion. Previous work from our lab has shown that 3D visual information combines with vestibular cues in a statistically optimal fashion, even when spatial offsets between the two cues are introduced. In this experiment we extended this research question by evaluating the effects of creating temporal offsets between visual and vestibular cues during a heading judgment task. This experiment was conducted using a Stewart motion platform equipped with a 90 degree, wide field-of-view projection screen. Participants were presented with a linear, diagonal movement and asked whether they were heading in a rightward or leftward direction relative to their starting position. Self-motion information was either presented via visual cues alone, vestibular cues alone, or both cues combined. In the combined condition the two cues were either congruent (1/7 trials) or incongruent in their temporal order. The temporal offsets ranged from -0.5 s (visual motion started before vestibular motion) to +0.5s (vestibular motion started before visual motion). The temporal offsets were presented in a random order and participants completed 6 daily sessions of 1.5 hours each. Results demonstrate that, for the first half of the trials, the highest variance was observed in the extreme temporal offset trials (+/- 0.5s). However, for the last half of the trials, the highest variance was actually observed in the congruent cue trials, with the lowest variance observed for the extreme temporal offsets. These findings indicate that, the way in which visual and vestibular information is combined changes dynamically as a function of increased exposure to discrepant cue information.}, department = {Department B{\"u}lthoff}, web_url = {http://imrf.mcmaster.ca/IMRF/ocs/index.php/meetings/2009/paper/view/815}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {New York, NY, USA}, event_name = {10th International Multisensory Research Forum (IMRF 2009)}, language = {en}, author = {Campos, JL and Butler, JS and B{\"u}lthoff, HH} } @Poster { 5293, title = {Neural correlates of visual self-motion cues and visual pursuit investigated using fMRI}, year = {2008}, month = {11}, volume = {38}, number = {461.19}, abstract = {For the successful estimation of self-motion based on visual cues it is necessary to take self-induced motion signals into account, such as those induced by eye-movements. In this fMRI study we used stimulus conditions that allowed us to differentiate neural responses to (a) retinal motion, (b) eye-movements (visual pursuit) and (c) objective motion. Responses to these three motion cues were measured in context of two types of visual stimuli, namely moving 2D dot-sheets and 3D-expanding flow fields. An additional localizer experiment segregated responses to contra- and ipsi-lateral stimulation as well as to full field coherent expansion as opposed to trajectory matched scrambled random motion. We found that MT/V5 and MST responded primarily to retinal motion and to eye-movements. More parietal regions such as V7 and IPS (intra-parietal sulcus) and a region recently implicated in self-motion processing, the cingulate sulcus visual area (CSv), seem to be driven by all three motion cues. The localizer experiment revealed that all of these regions responded almost exclusively to coherent motion types, while MT+/V5+ also responded, but less strongly, to the matched random motion display. CSv differed from all other regions in that it favored 2D translational coherent motion over 3D expanding flow fields, and in that its responses to ipsi- and contralateral flow were indistinguishable. It thus appears to be a strong candidate for integrating translational motion signals of retinal and non-retinal origin. Area V3A/B differed from most other motion processing regions in that it was primarily affected by objective motion, and also, but less, by visual pursuit. Furthermore, in the localizer it responded equally to coherent 3D flow and to the random motion stimulus. This suggests that V3A/B processes differential rather than coherent or self-induced motion. Our results lead us to suggest that there is a clear functional segregation among higher level motion processing regions in context of self-motion processing cues. It remains to be resolved to which extent the distinct regions inter-operate in a hierarchical or rather in a parallel fashion.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.sfn.org/am2008/}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Washington, DC, USA}, event_name = {38th Annual Meeting of the Society for Neuroscience (Neuroscience 2008)}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Poster { GaissertWB2008, title = {Analyzing haptic and visual object categorization of parametrically-de fined shapes}, year = {2008}, month = {10}, volume = {9}, number = {6}, abstract = {To investigate multi-sensory, perceptual representations of three-dimensional object spaces, we generated complex, shell-shaped objects by altering three parameters defining shell shape. For haptic experiments, 3D-printed plastic models were freely explored by blindfolded participants with both hands. For visual experiments, we used 2D images of these objects. Previously, we reported results of a similarity rating task in which we split the three-dimensional object space into three orthogonal planes. Multidimensional scaling (MDS) of the pair-wise similarity ratings showed that participants reproduced the three planes almost exactly both visually and haptically. Here, we report results of a categorization task in which all objects were presented simultaneously either visually or haptically to ten participants who then categorized the objects in as many groups as they liked to. MDS analyses revealed a three-dimensional perceptual space underlying both visual and haptic data. Interestingly, the three dimensions corresponded to the parameters of shell shape with a different weighting of the dimensions in the visual and the haptic condition. Our results show that humans are able to reproduce the underlying parameters of a complex, three-dimensional object space in a similarity and categorization task using either visual or haptic modalities surprisingly well.}, department = {Department B{\"u}lthoff}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_place = {Ellwangen, Germany}, event_name = {9th Conference of the Junior Neuroscientists of T{\"u}bingen (NeNa 2008)}, author = {Gaissert, N and Wallraven, C and B{\"u}lthoff, HH} } @Poster { FischerBLB2008, title = {Neural correlates of visual self-motion cues and visual pursuit investigated using fMRI}, year = {2008}, month = {10}, volume = {9}, number = {5}, abstract = {For the successful estimation of self-motion based on visual cues it is necessary to take self-induced motion signals into account, such as those induced by eye-movements. In this fMRI study we used stimulus conditions that allowed us to differentiate neural responses to (a) retinal motion, (b) eye-movements (visual pursuit) and (c) objective motion. Responses to these three motion cues were measured in context of two types of visual stimuli, namely moving 2D dot-sheets and 3D-expanding ow fields. An additional localizer experiment segregated responses to contra- and ipsi-lateral stimulation as well as to full field coherent expansion as opposed to trajectory matched scrambled random motion. We found that MT/V5 and MST responded primarily to retinal motion and to eye-movements. More parietal regions such as V7 and IPS (intra-parietal sulcus) and a region recently implicated in self-motion processing, the cingulate sulcus visual area (CSv), seem to be driven by all three motion cues. The localizer experiment revealed that all of these regions responded almost exclusively to coherent motion types, while MT+/V5+ also responded, but less strongly, to the matched random motion display. CSv differed from all other regions in that it favored 2D translational coherent motion over 3D expanding ow fields. Also, its responses to ipsi and contralateral ow were indistinguishable. It thus appears to be a strong candidate for integrating translational motion signals of retinal and non-retinal origin. Area V3A/B differed from most other motion processing regions in that it was primarily affected by objective motion, and also, but less, by visual pursuit. Furthermore, in the localizer it responded equally to coherent 3D now and to the random motion stimulus. This suggests that V3A/B processes differential rather than coherent or self-induced motion. Our results lead us to suggest that there is a clear functional segregation among higher level motion processing regions in context of self-motion processing cues. It remains to be resolved to which extent the distinct regions inter-operate in a hierarchical or rather in a parallel fashion.}, department = {Department B{\"u}lthoff}, department2 = {Department Logothetis}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_place = {Ellwangen, Germany}, event_name = {9th Conference of the Junior Neuroscientists of T{\"u}bingen (NeNa 2008)}, author = {Fischer, E and B{\"u}lthoff, HH and Logothetis, NK and Bartels, A} } @Poster { 5246, title = {Orientation biases in memory for vista and environmental spaces}, year = {2008}, month = {10}, volume = {9}, pages = {32}, abstract = {This experiment tested whether vista spaces such as rooms or plazas are encoded differently in memory compared to environmental spaces such as buildings or cities. Participants learned an immersive virtual environment by walking through it in one direction. The environment consisted of seven corridors forming a labyrinth within which target objects were located. The participants either learned this environmental space alone, or distant mountains provided additional compass information. In a third condition, this labyrinth was located within a big hall (i.e., a vista space) which allowed self-localisation with respect to the vista space of the hall. In the testing phase, participants were teleported to different locations in the environment and were asked to identify their location and heading first, and then to point towards previously learned targets. In general, participants self localized faster when oriented in the direction in which they originally learned each corridor. However, a subset of participants showed a different orientation specificity in their pointing performance originating more from the orientation of the mountains or the hall. These participants were identified in catch trials after the experiment. The results are first hints for a difference in memory for vista and environmental spaces.}, department = {Department B{\"u}lthoff}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Dresden, Germany}, event_name = {9. Fachtagung der Gesellschaft f{\"u}r Kognitionswissenschaft (KogWis '08)}, language = {en}, author = {Meilinger, T and Schulte-Pelkum, J and Laharnar, N and Teramoto, W and Frankenstein, J and B{\"u}lthoff, HH} } @Poster { 5215, title = {A visual but no haptic face inversion effect indicates modality-specific processing differences}, journal = {Perception}, year = {2008}, month = {8}, volume = {37}, number = {ECVP Abstract Supplement}, pages = {5}, abstract = {In previous experiments, we provided further evidence that 3-D face stimuli can be learnt and recognized across haptic and visual modalities. Our results suggested information transfer across modalities to be asymmetric due to differences in visual versus haptic face processing (ie, configural vs featural). To test this hypothesis, we designed two experiments investigating a visual, haptic and cross-modal face-inversion effect: Experiment 1 used an old/new recognition task in which three upright faces were learnt visually followed by three visual test-blocks (one with upright and two with inverted faces) and one haptic test-block with inverted faces. We found a strong inversion effect for visually learnt faces (visual-upright: d'=2.07, visual-inverted: d'=0.6, haptic-inverted: d'=0.52). When we exchanged learning and testing modalities in Experiment 2 (haptic learning of upright faces followed by one haptic-upright, two haptic-inverted and one visual-inverted test-blocks), we failed to find an inversion effect for haptically learnt faces (haptic-upright: d'=1.45, haptic-inverted: d'=1.75, visual-inverted: d'=1.16). Whereas visual face processing thus operates configurally, haptic processing seems to rely on featural information.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v080017}, institute = {Biologische Kybernetik}, organization = {Max-Planck-Gesellschaft}, event_place = {Utrecht, Netherlands}, event_name = {31st European Conference on Visual Perception}, language = {en}, author = {Dopjans, L and Wallraven, C and B{\"u}lthoff, HH} } @Poster { TcheangBB2008, title = {Dissociating visual and interoceptive rotation during path integration}, journal = {Perception}, year = {2008}, month = {8}, volume = {37}, number = {ECVP Abstract Supplement}, pages = {123}, abstract = {Path integration in darkness is classically thought to be accomplished using interoceptive information. Here we examine the contribution of visual input to the accumulation of rotational information during path integration of a return to origin task, in a fully immersive virtual environment. Nine paths that varied in turn angle and number of turns were used. Path length was approximately constant across trials. During walking the outward legs of a path, a mismatch was introduced between actual rotation and the perceived rotation of a rich virtual environment, which could be increased or decreased. The return leg of the path was performed without vision. The mismatch trials were interleaved with two control conditions; one where vision matched interoceptive information exactly on the outward paths, and one without any visual input. Sixteen subjects (balanced across gender) were tested and a mixed ANOVA analysis showed a significant effect of the visual manipulation. Return directions were consistent with the direction of the visual manipulation suggesting a strong visual component to this 'path integration' task.}, department = {Department B{\"u}lthoff}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v080081}, event_place = {Utrecht, Netherlands}, event_name = {31st European Conference on Visual Perception}, author = {Tcheang, L and B{\"u}lthoff, HH and Burgess, N} } @Poster { 5309, title = {Influence of the field of view on speed estimation during visual translations}, journal = {Perception}, year = {2008}, month = {8}, volume = {37}, number = {ECVP Abstract Supplement}, pages = {156},