Stereo Vision for Obstacle Detection: A Region-Based Approach

P. Foggia, A. Limongiello, M. Vento

2007

Abstract

We propose a new approach to stereo matching for obstacle detection in the autonomous navigation framework. An accurate but slow reconstruction of the 3D scene is not needed; rather, it is more important to have a fast localization of the obstacles to avoid them. All the methods in the literature, based on a pixel stereo matching, are ineffective in realistic contexts because they are either computationally too expensive, or unable to deal with the presence of uniform patterns, or of perturbations between the left and right images. Our idea is to face the stereo matching problem as a matching between homologous regions. Our method is strongly robust in a realistic environment, requires little parameter tuning, and is adequately fast, as experimentally demonstrated in a comparison with the best algorithms in the literature.

References

  1. DeSouza, G. N. , Kak, A. C.: Vision for Mobile Robot Navigation: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 2, pp. 237-267 (2002).
  2. Kastrinaki, V., Zervakis, M., Kalaitzakis, K.: A survey of video processing techniques for traffic applications. Image and Vision Computing, vol. 21, pp. 359-381 (2003).
  3. Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision, vol. 47, no. 1, pp. 7-42 (2002).
  4. Zhang, C.: A Survey on Stereo Vision for Mobile Robots. Technical report, Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, USA (2002).
  5. Kanade, T., Okutomi, M.: A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 920-932 (1994).
  6. Fusiello, A., Roberto, V.: Efficient stereo with multiple windowing. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 858-863, Puerto Rico (1997).
  7. Veksler, O.: Stereo matching by compact windows via minimum ratio cycle. Proceedings of the International Conference on Computer Vision, vol. I, pp. 540-547, Vancouver, Canada (2001).
  8. Marr, D., Poggio, T.A.: Cooperative computation of stereo disparity. Science, vol. 194, no. 4262, pp. 283-287 (1976).
  9. Zitnick, C.L., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 22, no. 7, pp. 675-684 (2000).
  10. Geiger, D., Ladendorf, B., Yuille, A.: Occlusions and binocular stereo. International Journal of Computer Vision, vol. 14, pp. 211-226 (1995).
  11. Roy, S.: Stereo without epipolar lines: A maximum-flow formulation. International Journal of Computer Vision, vol. 34, no. 2/3, pp. 1-15 (1999).
  12. Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222- 1239 (2001).
  13. Marr, D., Poggio, T.A.: A computational theory of human stereo vision. RoyalP, vol. B, no. 204, pp. 301-328 (1979).
  14. Grimson, W.E.L.: A computer implementation of a theory of human stereo vision. Royal, vol. B, no. 292, pp. 217-253 (1981).
  15. Candocia, F., Adjouadi, M.: A similarity measure for stereo feature matching. IEEE Transaction on Image Processing, vol. 6, pp. 1460-1464 (1997).
  16. Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 195-202, Madison, WI (2003).
  17. Jolion, J.M.: Computer Vision Methodologies. CVGIP: Image Understanding, vol. 59, no. 1, pp. 53-71 (1994).
  18. http://cat.middlebury.edu/stereo/
  19. http://www.videredesign.com/
  20. Konolige, K.: Web site. http://www.ai.sri. com/software/SVS (2006).
  21. Konolige, K.: Small vision systems: hardware and implementation. Intl. Symp. On Robotics Research, pages 111-116 (1997).
Download


Paper Citation


in Harvard Style

Foggia P., Limongiello A. and Vento M. (2007). Stereo Vision for Obstacle Detection: A Region-Based Approach . In Robot Vision - Volume 1: Robot Vision, (VISAPP 2007) ISBN 978-972-8865-76-4, pages 36-45. DOI: 10.5220/0002067900360045


in Bibtex Style

@conference{robot vision07,
author={P. Foggia and A. Limongiello and M. Vento},
title={Stereo Vision for Obstacle Detection: A Region-Based Approach},
booktitle={Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)},
year={2007},
pages={36-45},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002067900360045},
isbn={978-972-8865-76-4},
}


in EndNote Style

TY - CONF
JO - Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)
TI - Stereo Vision for Obstacle Detection: A Region-Based Approach
SN - 978-972-8865-76-4
AU - Foggia P.
AU - Limongiello A.
AU - Vento M.
PY - 2007
SP - 36
EP - 45
DO - 10.5220/0002067900360045