EngelC2012 7 D Engel C Curio Alcalá de Henares, Spain2012-06-00 178 183 IEEE Intelligent Vehicles Symposium (IV 2012) A driver assistance system realizes that the driver is distracted and that a potentially hazardous situation is emerging. Where should it guide the attention of the driver? Optimally to the spot that allows the driver to make the best decision. Pedestrian detectability has been proposed recently as a measure of the probability that a driver perceives pedestrians in an image [9]. Leveraging this information allows a driver assistance system to direct the attention of the driver to the spot that maximizes the probability that all pedestrians are seen. In this paper we extend this concept to dynamic scenes. We use an annotated video dataset recorded from a moving car in an urban environment and acquire the detectabilities of pedestrians via a psychophysical experiment. Based on these measured detectabilites we train a machine learning algorithm to predict detectabilities from a set of image features. We then exploit this mapping to predict the optimal focus of attention in a second experiment, thus demonstrating the usefulness of our method in a dynamic driver assistance context. no notspecified http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2012/IV2012-Engel.pdf published 5 15017 15422 HerdtweckC2012 7 C Herdtweck C Curio Alcalá de Henares, Spain2012-06-00 661 667 IEEE Intelligent Vehicles Symposium (IV 2012) Visual odometry has been promoted as a fundamental component for intelligent vehicles. Relying solely on monocular image cues would be desirable. Nevertheless, this is a challenge especially in dynamically varying urban areas due to scale ambiguities, independent motions, and measurement noise. We propose to use probabilistic learning with auxiliar depth cues. Specifically, we developed an expert model that specializes monocular egomotion estimation units on typical scene structures, i.e. statistical variations of scene depth layouts. The framework adaptively selects the best fitting expert. For on-line estimation of egomotion, we adopted a probabilistic subspace flow estimation method. Learning in our framework consists of two components: 1) Partitioning of datasets of video and ground truth odometry data based on unsupervised clustering of dense stereo depth profiles and 2) training a cascade of subspace flow expert models. A probabilistic quality measure from the estimates of the experts provides a selection rule overall leading to improvements of egomotion estimation for long test sequences. no notspecified http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2012/IV-2012-Herdtweck-Curio.pdf published 6 15017 15422 LayherTSBCN2011 7 G Layher H Neumann S Scherer S Tschechne T Brosch C Curio Berlin, Germany2011-10-00 239 Workshop on "Companion-Systeme und Mensch-Companion-Interaktion" Companion technologies aim at developing sustained long-term relationships by employing emotional, nonverbal communication skills and empathy. One of the main challenges is to equip such companions with human-like abilities to reliably detect and analyze social signals. In this proposal, we focus our investigation on the modeling of visual processing mechanisms, since evidence in literature suggests that nonverbal interaction plays a key role in steering, controlling and maintaining social interaction between humans. We seek to transfer fragments of this competence to the domain of human computer interaction. Some core computational mechanisms of extracting and analyzing nonverbal signals are presented, enabling virtual agents to create socially competent response behaviors. no notspecified http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2011/Informatik-2011-Layher.pdf published -239 15017 15422 EngelBHC2011 7 D Engel C Herdtweck B Browatzki C Curio Lisboa, Portugal2011-09-00 412 425 13th IFIP TC13 Conference on Human-Computer Interaction With increasingly large image databases, searching in them becomes an ever more difficult endeavor. Consequently, there is a need for advanced tools for image retrieval in a webscale context. Searching by tags becomes intractable in such scenarios as large numbers of images will correspond to queries such as “car and house and street”. We present a novel approach that allows a user to search for images based on semantic sketches that describe the desired composition of the image. Our system operates on images with labels for a few high-level object categories, allowing us to search very fast with a minimal memory footprint. We employ a structure similar to random decision forests which avails a data-driven partitioning of the image space providing a search in logarithmic time with respect to the number of images. This makes our system applicable for large scale image search problems. We performed a user study that demonstrates the validity and usability of our approach. no notspecified http://www.kyb.tuebingen.mpg.de/ published 13 15017 15422 EngelC2011_2 7 D Engel C Curio Baden-Baden, Germany2011-06-00 429 435 IEEE Intelligent Vehicles Symposium (IV 2011) How likely is it that a driver notices a person standing on the side of the road? In this paper we introduce the concept of pedestrian detectability. It is a measure of how probable it is that a human observer perceives pedestrians in an image. We acquire a dataset of pedestrians with their associated detectabilities in a rapid detection experiment using images of street scenes. On this dataset we learn a regression function that allows us to predict human detectabilities from an optimized set of image and contextual features. We exploit this function to infer the optimal focus of attention for pedestrian detection. With this combination of human perception and machine vision we propose a method we deem useful for the optimization of Human-Machine-Interfaces in driver assistance systems. no notspecified http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2011/IV-2011-Engel.pdf published 6 15017 15422 5323 7 D Engel C Curio L Tcheang B Mohler HH Bülthoff Bordeaux, France2008-10-00 157 164 15th ACM Symposium on Virtual Reality Software and Technology (VRST 2008) 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. no notspecified http://www.kyb.tuebingen.mpg.de//fileadmin/user_upload/files/publications/VRST2008-Engel_5323[0].pdf published 7 15017 15422