Unsupervised discovery of object classes in 3D outdoor scenarios

Designing object models for a robot's detection-system can be very time-consuming since many object classes exist. This paper presents an approach that automatically infers object classes from recorded 3D data and collects training examples. A special focus is put on difficult unstructured outdoor scenarios with object classes ranging from cars over trees to buildings. In contrast to many existing works, it is not assumed that perfect segmentation of the scene is possible. Instead, a novel hierarchical segmentation method is proposed that works together with a novel inference strategy to infer object classes.

[1]  Joachim M. Buhmann,et al.  Model Order Selection and Cue Combination for Image Segmentation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Roland Siegwart,et al.  Unsupervised discovery of repetitive objects , 2010, 2010 IEEE International Conference on Robotics and Automation.

[3]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Wolfram Burgard,et al.  Unsupervised learning of 3D object models from partial views , 2009, 2009 IEEE International Conference on Robotics and Automation.

[5]  Roland Siegwart,et al.  Object classification based on a geometric grammar with a range camera , 2009, 2009 IEEE International Conference on Robotics and Automation.

[6]  Ryosuke Shibasaki,et al.  Sensor alignment towards an omni-directional measurement using an intelligent vehicle , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[7]  Christoph Stiller,et al.  Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[8]  Wolfram Burgard,et al.  Unsupervised discovery of object classes from range data using latent Dirichlet allocation , 2009, Robotics: Science and Systems.

[9]  Christoph H. Lampert,et al.  Unsupervised Object Discovery: A Comparison , 2010, International Journal of Computer Vision.

[10]  Kostas Daniilidis,et al.  Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors , 2008, ECCV.

[11]  Narendra Ahuja,et al.  Unsupervised Category Modeling, Recognition, and Segmentation in Images , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Daniel Cohen-Or,et al.  Contextual Part Analogies in 3D Objects , 2010, International Journal of Computer Vision.

[13]  Martin Buss,et al.  Comparison of surface normal estimation methods for range sensing applications , 2009, 2009 IEEE International Conference on Robotics and Automation.

[14]  Narendra Ahuja,et al.  Connected Segmentation Tree — A joint representation of region layout and hierarchy , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Roland Siegwart,et al.  Segmentation and Unsupervised Part-based Discovery of Repetitive Objects , 2010, Robotics: Science and Systems.