Stixels estimation without depth map computation

Mobile robots require object detection and classification for safe and smooth navigation. Stereo vision improves such detection by doubling the views of the scene and by giving indirect access to depth information. This depth information can also be used to reduce the set of candidate detection windows. Up to now, most algorithms compute a depth map to discard unpromising detection windows. We propose a novel approach where a stixel world model is computed directly from the stereo images, without computing an intermediate depth map. We experimentally demonstrate that such approach can considerably reduce the set of candidate detection windows at a fraction of the computation cost of previous approaches.

[1]  Uwe Franke,et al.  Fast stereo based object detection for stop&go traffic , 1996, Proceedings of Conference on Intelligent Vehicles.

[2]  Masatoshi Okutomi,et al.  Extraction of road region using stereo images , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[3]  Uwe Franke,et al.  Real-time stereo vision for urban traffic scene understanding , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[4]  Jean-Philippe Tarel,et al.  Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[5]  R. Danescu,et al.  High accuracy stereo vision system for far distance obstacle detection , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[6]  H. Hirschmuller.  Accurate and efficient stereo processing by semi-global matching and mutual information , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Keiichi Uchimura,et al.  A complete U-V-disparity study for stereovision based 3D driving environment analysis , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Luc Van Gool,et al.  3D City Modeling Using Cognitive Loops , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[10]  M. Okutomi,et al.  Robust Obstacle Detection in General Road Environment Based on Road Extraction and Pose Estimation , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[11]  S. Kubota,et al.  A Global Optimization Algorithm for Real-Time On-Board Stereo Obstacle Detection Systems , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[12]  Rudolf Mester,et al.  Free Space Computation Using Stochastic Occupancy Grids and Dynamic Programming , 2008 .

[13]  Luc Van Gool,et al.  A mobile vision system for robust multi-person tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Hiroshi Hattori,et al.  Stereo-based Pedestrian Detection using Multiple Patterns , 2009, BMVC.

[15]  Uwe Franke,et al.  The Stixel World - A Compact Medium Level Representation of the 3D-World , 2009, DAGM-Symposium.

[16]  Shane Brennan,et al.  A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle , 2009, Int. J. Robotics Res..

[17]  Dariu Gavrila,et al.  Dense Stereo-Based ROI Generation for Pedestrian Detection , 2009, DAGM-Symposium.

[18]  Uwe Franke,et al.  Efficient representation of traffic scenes by means of dynamic stixels , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[19]  Alexander Barth,et al.  Ground truth evaluation of the Stixel representation using laser scanners , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[20]  Narendra Ahuja,et al.  A constant-space belief propagation algorithm for stereo matching , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.