STEREO VISION-BASED DETECTION OF MOVING OBJECTS UNDER STRONG CAMERA MOTION

Hernán Badino, Uwe Franke, Clemens Rabe, Stefan Gehrig

Abstract

The visual perception of independent 3D motion from a moving observer is one of the most challenging tasks in computer vision. This paper presents a powerful fusion of depth and motion information for image sequences. For a large number of points, 3D position and 3D motion is simultaneously estimated by means of Kalman Filters. The necessary ego-motion is computed based on the points that are identified as static points. The result is a real-time system that is able to detect independently moving objects even if the own motion is far from planar. The input provided by this system is suited to be used by high-level perception systems in order to carry out cognitive processes such as autonomous navigation or collision avoidance.

References

  1. Agrawal, M., Konolige, K., and Iocchi, L. (2005). Realtime detection of independent motion using stereo. In IEEE Workshop on Motion and Video Computing (WACV/MOTION 2005), pages 672-677, Breckenridge, CO, USA.
  2. Argyros, A. A. and Orphanoudakis, S. C. (1997). Independent 3d motion detection based on depth elimination in normal flow fields. In Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR 7897), pages 672-677.
  3. Badino, H. (2004). A robust approach for ego-motion estimation using a mobile stereo platform. In 1st International Workshop on Complex Motion (IWCM'04), Günzgburg, Germany. Springer.
  4. Dang, T., Hoffmann, C., and Stiller, C. (2002). Fusing optical flow and stereo disparity for object tracking. In Proceedings of the IEEE V. International Conference on Intelligent Transportation Systems, pages 112-117, Singapore.
  5. Demirdjian, D. and Darrel, T. (2001). Motion estimation from disparity images. In Technical Report AI Memo 2001-009, MIT Artificial Intelligence Laboratory.
  6. Demirdjian, D. and Horaud, R. (2000). Motion-egomotion discrimination and motion segmentation from image pair streams. In Computer Vision and Image Understanding, volume 78(1), pages 53-68.
  7. Franke, U. (2000). Real-time stereo vision for urban traffic scene understanding. In IEEE Conference on Intelligent Vehicles, Dearborn.
  8. Franke, U., Rabe, C., Badino, H., and Gehrig, S. (2005). 6d-vision: Fusion of stereo and motion for robust environment perception. In DAGM 7805, Vienna.
  9. Heinrich, S. (2002). Fast obstacle detection using flow/detph constraint. In IEEE Intelligent Vehicle Symposium (IV'2002), Versailles, France.
  10. Horn, B. K. P. (1987). Closed-form solution of absolute orientation using unit quaternions. In Journal of the Optical Society of America A, volume 4(4), pages 629- 642.
  11. Kang, J., Cohen, I., Medioni, G., and Yuan, C. (2005). Detection and tracking of moving objects from a moving platform in presence of strong parallax. In IEEE International Conference on Computer Vision ICCV'05.
  12. Kellman, P. J. and Kaiser, M. (1995). Extracting object motion during observer motion: Combining constraints from optic flow and binocular disparity. JOSA-A, 12(3):623-625.
  13. Lorusso, A., Eggert, D., and Fisher, R. B. (1995). A comparison of four algorithms for estimating 3-d rigid transformations. In Proc. British Machine Vision Conference, Birmingham.
  14. Mallet, A., Lacroix, S., and Gallo, L. (2000). Position estimation in outdoor environments using pixel tracking and stereovision. In Proceedings of the 2000 IEEE International Conference on Robotics and Automation, pages 3519-3524, San Francisco.
  15. Martin, M. and Moravec, H. (1996). Robot evidence grids. The Robotics Institute Carnegie Mellon University (CMU-RI-TR-96-06).
  16. Matthies, L. and Shafer, S. A. (1987). Error modeling in stereo navigation. In IEEE Journal of Robotics and Automation, volume RA-3(3), pages 239-248.
  17. Mills, S. (1997). Stereo-motion analysis of image sequences. In Proceedings of the first joint Australia and New Zealand conference on Digital Image and Vision Computing: Techniques and Applications, DICTA'97 / IVCNZ'97, Albany, Auckland, NZ.
  18. Morency, L. P. and Darrell, T. (2002). Stereo tracking using icp and normal flow constraint. In Proceedings of International Conference on Pattern Recognition, Quebec.
  19. Olson, C. F., Matthies, L. H., Schoppers, M., and Maimone, M. W. (2003). Rover navigation using stereo egomotion. In Robotics and Autonomous Systems, volume 43(4), pages 215-229.
  20. Sekuler, R., Watamaniuk, S. N. J., and Blake, R. (2004). Stevens' Handbook of Experimental Psychology, volume 1, Sensation and Perception, chapter 4, Perception of Visual Motion. Wiley, 3rd edition.
  21. Shi, J. and Tomasi, C. (1994). Good features to track. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'94).
  22. Talukder, A. and Matthies, L. (2004). Real-time detection of moving objects from moving vehicles using dense stereo and optical flow. In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pages 315-320, Sendai, Japan.
  23. van der M., W., Fontijne, D., Dorst, L., and Groen, F. C. A. (2002). Vehicle ego-motion estimation with geometric algebra. In Proceedings IEEE Intelligent Vehicle Symposium, Versialles, France, May 18-20 2002.
  24. Vidal, R. (2005). Multi-subspace methods for motion segmentation from affine, perspective and central panoramic cameras. IEEE International Conference on Robotis and Automation.
  25. Waxman, A. M. and Duncan, J. H. (1986). Binocular image flows: Steps toward stereo-motion fusion. PAMI, 8(6):715-729.
  26. Woelk, F. (2004). Robust monocular detection of independent motion by a moving observer. In 1st International Workshop on Complex Motion (IWCM'04), Günzgburg, Germany. Springer.
  27. Zhang, Z. and Faugeras, O. D. (1991). Three-dimensional motion computation and object segmentation in a long sequence of stereo images. Technical Report RR1438, Inria.
Download


Paper Citation


in Harvard Style

Badino H., Franke U., Rabe C. and Gehrig S. (2006). STEREO VISION-BASED DETECTION OF MOVING OBJECTS UNDER STRONG CAMERA MOTION . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 253-260. DOI: 10.5220/0001375702530260


in Bibtex Style

@conference{visapp06,
author={Hernán Badino and Uwe Franke and Clemens Rabe and Stefan Gehrig},
title={STEREO VISION-BASED DETECTION OF MOVING OBJECTS UNDER STRONG CAMERA MOTION},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={253-260},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001375702530260},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - STEREO VISION-BASED DETECTION OF MOVING OBJECTS UNDER STRONG CAMERA MOTION
SN - 972-8865-40-6
AU - Badino H.
AU - Franke U.
AU - Rabe C.
AU - Gehrig S.
PY - 2006
SP - 253
EP - 260
DO - 10.5220/0001375702530260