Recognition of Obstacles on Structured 3D Background
A stereo vision system for recognition of 3D-objects is presented. The method uses a stereo camera pair and is able to detect objects located on a structured background constituting a repetitive 3D pattern, e.g. a staircase. Recognition is based on differencing stereo pair images, where a perspective warping transform is used to overlay the left onto the right image, or vice versa. The 3D camera positions are obtained during a learning phase where a 3D background model is employed. Correspondence between images and stereo disparity are derived based on the estimated pose of the background model. Disparity provides the necessary information for a perspective warping transform used in the recognition phase. The demonstrated application is staircase surveillance. Recognition itself is based on a pyramidal representation and segmentation of image intensity differences.
KeywordsFalse Alarm Rate Correct Recognition Automatic Vehicle Guidance Cross Ratio Image Pyramid
Unable to display preview. Download preview PDF.
- 1.Peter Burt, Lambert Wixson, and Garbis Salgian. Electronically Directed ‘Focal’ Stereo. In Proceedings of International Conference on Computer Vision, pages 94–101, Cambridge, MA, USA, June 1995.Google Scholar
- 3.M. Fair and D.P. Miller. Automated Staircase Detection, Alignment & Traversal. In Proceedings of International Conference on Robotics and Manufacturing, pages 218–222, Cancun, Mexico, May 2001.Google Scholar
- 5.Paul S. Heckbert. Fundamentals of Texture Mapping and Image Warping. Technical Report CSD-89-516, Department of Electrical Engineering and Computer Science, University of Berkeley, CA, USA, June 1989.Google Scholar
- 6.Reinhold Huber. 3D Object Detection in Stereo Geometry. Technical Report ACV_TR_61, Advanced Computer Vision GmbH — ACV, Kplus Competence Center, Vienna, Austria, 2002.Google Scholar
- 7.Reinhold Huber. Matching and Pose Estimation for Regular Rigid 3D Objects. Technical Report ACV_TR_60, Advanced Computer Vision GmbH — ACV, Kplus Competence Center, Vienna, Austria, 2002.Google Scholar
- 8.Reinhold Huber, Christoph Nowak, Bernhard Spatzek, and David Schreiber. Adaptive Aperture Control for Video Acquisition. In Proceedings of IEEE Workshop on Applications of Computer Vision, pages 320–324, Orlando, FL, USA, December 2002.Google Scholar
- 9.Reinhold Huber, Christoph Nowak, Bernhard Spatzek, and David Schreiber. Reliable Detection of Obstacles on Staircases. In Proceedings of IAPR Workshop on Machine Vision Applications, pages 467–479, Nara, Japan, December 2002.Google Scholar
- 10.M. Jenkin and A. Jepson. Detecting Floor Anomalies. In E. Hancock, editor, Proceedings of British Machine Vision Conference, pages 731–740, York, UK, 1994.Google Scholar
- 12.Q.-T. Luong, J. Weber, D. Koller, and J. Malik. An Integrated Stereo-based Approach to Automatic Vehicle Guidance. In Proceedings of the International Conference on Computer Vision, pages 52–57, Cambridge, MA, USA, June 1995.Google Scholar
- 14.J. Mundy and A. Zisserman. Appendix: Projective Geometry for Machine Vision. In J. L. Mundy and A. Zisserman, editors, Geometric Invariance in Computer Vision, pages 463–519. MIT Press, 1992.Google Scholar
- 16.Todd Williamson and Charles Thorpe. Detection of Small Obstacles at Long Range using Multibaseline Stereo. In Proceedings of International Conference on Intelligent Vehicles, 1998.Google Scholar