This file was created by the Typo3 extension sevenpack version 0.7.14 --- Timezone: CEST Creation date: 2013-05-25 Creation time: 19-13-57 --- Number of references 4 inproceedings BrowatzkiTMBW2012 2012 5 2021-2028 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. http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2012/ICRA-2012-Browatzki.pdf http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de Department Bülthoff http://www.icra2012.org/ IEEE

Piscataway, NJ, USA

St. Paul, MN, USA IEEE International Conference on Robotics and Automation (ICRA 2012) 10.1109/ICRA.2012.6225218 browatbnBBrowatzki VTikhanoff GMetta hhbHHBülthoff walliCWallraven inproceedings BrowatzkiFGBW2011 2011 11 1189-1195 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. http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2011/CD4CV-2011-Browatzki.pdf http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de Department Bülthoff http://www.vision.ee.ethz.ch/CDC4CV/index.html IEEE

Piscataway, NJ, USA

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) Barcelona, Spain 1st ICCV Workshop on Consumer Depth Cameras in Computer Vision (CD4CV2011) 978-1-467-30062-9 10.1109/ICCVW.2011.6130385 browatbnBBrowatzki JFischer BGraf hhbHHBülthoff walliCWallraven inproceedings EngelBHC2011 2011 9 412-425 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. http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de Department Bülthoff http://interact2011.org/ Campos, P. , N. Graham, J. Jorge, N. Nunes, P. Palanque, M. Winckler Springer

Berlin, Germany

Human-Computer Interaction: INTERACT 2011 Lisboa, Portugal 13th IFIP TC13 Conference on Human-Computer Interaction 978-3-642-23774-4 10.1007/978-3-642-23774-4_35 engelDEngel grueschaanCHerdtweck browatbnBBrowatzki curioCCurio poster 7086 2010 10 11 9 29 One major difficulty in computational object recognition lies in the fact that a 3D object can be seen from an infinite number of viewpoints. Thus, the issue arises that objects with different 3D shapes often share similar 2D views. Humans are able to resolve this kind of ambiguity by producing additional views through object manipulation or self movement. In both cases the action made provides proprioceptive information linking the visual information retrieved from the obtained views. Following this process, we combine visual and proprioceptive information to increase recognition performance of a computer vision system. In our approach we place a 3D model of an unknown object in the hand of a simulated anthropomorphic robot arm. The robot now executes a predefined exploratory movement to acquire a variety of different object views. To assure computational tractability, a subset of representative views is selected using the Keyframe concept by Wallraven et al. (2007). Each remaining frame is then annotated with the respective proprioceptive configuration of the robot arm and the transitions between these configurations are treated as links between object views. For recognizing objects this representation can be used to control the robot arm based on learned data. If both proprioceptive and visual data agree on a candidate, the object was recognized successfully. We investigated recognition performance using this method. The results show that the number of misclassified results decreases significantly as both sources â visual and proprioceptive â are available, thus demonstrating the importance of a combined space of visual and proprioceptive information. http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de Department Bülthoff http://www.neuroschool-tuebingen-nena.de/fileadmin/user_upload/Dokumente/neuroscience/AbstractbookNeNa2010u.pdf Biologische Kybernetik Max-Planck-Gesellschaft Heiligkreuztal, Germany 11th Conference of Junior Neuroscientists of Tübingen (NeNa 2010) en browatbnBBrowatzki