Advertisement

Stereo matching with implicit detection of occlusions

  • Ralph Trapp
  • Siegbert Drüe
  • Georg Hartmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)

Abstract

In this paper we introduce a new stereo matching algorithm, in which the matching of occluded areas is suppressed by a self-organizing process. In the first step the images are filtered by a set of oriented Gabor filters. A complex-valued correlation-based similarity measurement, which is applied to the responses of the Gabor filters, is used in the second step to initialize a self-organizing process. In this self-organizing network, which is described by coupled, non-linear evolution equations, the continuity and the uniqueness constraints are established. Occlusions are detected implicitly without a computationally intensive bidirectional matching strategy. Due to the special similarity measurement, dense disparity maps can be calculated with subpixel accuracy. Unlike phase-difference methods the disparity range is not limited to the modulation wavelength of the quadrature-filter. Therefore, there is no need for a hierachical coarse-to-fine control strategy in our approach.

Keywords

Gabor Filter Stereo Match Disparity Estimation Occlude Region Occlude Area 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Ayache, N.; Hansen, C.: Rectification of Images for Binocular and Trinocular Stereovision. In Proc. of the 9th Intern. Conference on Pattern Recognition, pp. 11–16, Oktober 1988.Google Scholar
  2. 2.
    Baker, H. H.; Binford, T. O.: Depth from Edge and Intensity Based Stereo. In Proceedings of the 7th International Joint Conference on Artifical Intelligence, pp. 631–636, August 1981.Google Scholar
  3. 3.
    Barnard, S. T.: Stochastic stereo matching over scale. In International Journal of Computer Vision, vol. 2, pp. 17–32, 1989.CrossRefGoogle Scholar
  4. 4.
    Barnard, S. T.; Thompson, W. B.: Disparity Analysis of Images. In Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-2, no. 4, pp. 333–340, July 1980.Google Scholar
  5. 5.
    Bertero, M.; Poggio, T. A.; Torre, V.: Ill-Posed Problems in Early Vision. In Proceedings of the IEEE, vol. 76, no. 8, pp. 869–889, August 1988.CrossRefGoogle Scholar
  6. 6.
    Burt, P.; Julesz, B.: A Disparity Gradient Limit for Binocular Fusion. In Science, vol. 208, pp. 615–617, 1980.Google Scholar
  7. 7.
    Fleet, D. J.: Disparity from Local Weighted Phase-Correlation. In IEEE International Conference on Systems, Man and Cybernetics, pp. 48–56, San Antonio, October 1994.Google Scholar
  8. 8.
    Fleet, D. J.; Jepson, A. D.; Jenkin, M. R. M.: Phase-Based Disparity Measurement. In CVGIP: Image Understanding, vol. 53, no. 2, pp. 198–210, March 1991.zbMATHCrossRefGoogle Scholar
  9. 9.
    Gabor, D.: Theory of communication. In J. IEE, vol. 93, pp. 429–457, London, 1946.Google Scholar
  10. 10.
    Geman, S.; Geman, D.: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-6, no. 6, pp. 721–741, November 1984.Google Scholar
  11. 11.
    Gennert, M. A.: Brightness-based stereo matching. In International Conference on Computer Vision, pp. 139–143, 1988.Google Scholar
  12. 12.
    Grimson, W. E. L.: A computer implementation of a theory of human stereo vision. In Philosophical Transactions of the Royal Society of London, vol. B 292, pp. 217–253, 1981.Google Scholar
  13. 13.
    Haken, H.: Synergetic Computers and Cognition. Springer-Verlag, Berlin, 1991.zbMATHGoogle Scholar
  14. 14.
    Hoff, W.; Ahuja, N.: Surfaces from Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection. In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 2, February 1989.Google Scholar
  15. 15.
    Jenkin, M. R. M.; Jepson, A. D.: Recovering Local Surface Structure through Local Phase Difference Measurements. In Computer Vision, Graphics and Image Processing: Image Understanding, vol. 59, no. 1, pp. 72–93, January, 1994.CrossRefGoogle Scholar
  16. 16.
    Jones, D. G.; Malik, J.: A computational framework for determining stereo correspondence from a set of linear spatial filters. In Proceedings of the 2nd European Conference on Computer Vision, Springer Verlag, Berlin, pp. 395–410, 1992Google Scholar
  17. 17.
    Julesz, B.: Foundations of cyclopean perception. University of Chicago Press, 1971.Google Scholar
  18. 18.
    Kim, Y. C.; Aggarwal, J. K.: Positioning Three-Dimensional Objects Using Stereo Images. In IEEE Journal of Robotics and Automation, vol. RA-3, no. 4, pp. 361–373, August 1987.Google Scholar
  19. 19.
    Konrad, J.; Dubois, E.: Multigrid Bayesian Estimation of Image Motion Fields Using Stochastic Relaxation. In Proceedings of the 2nd International Conference on Computer Vision, pp. 354–362, 1988.Google Scholar
  20. 20.
    Luo, A.; Burkhardt, H.: An Intensity-Based Cooperative Bidirectional Stereo Matching with Simultaneous Detektion of Discontinuities and Occlusions. In International Journal of Computer Vision, vol. 15, pp. 171–188, 1995.CrossRefGoogle Scholar
  21. 21.
    Marr, D.; Poggio, T.: A computational theory of human stereo vision. In Proceedings of Royal Society of London, vol. B 204, pp. 301–328, 1979.CrossRefGoogle Scholar
  22. 22.
    Medioni, G.; Nevatia, R.: Segment-Based Stereo Matching. In Computer Vision, Graphics, and Image Processing, vol. 31, pp. 2–18, 1985.Google Scholar
  23. 23.
    Moravec, H. P.: Towards automatic visual obstacle avoidance. In Proceedings of the 5th International Joint Conference on Artifical Intelligence, p. 584, 1977.Google Scholar
  24. 24.
    Otha, Y.; Kanade T.: Stereo by intra-and inter-scanline search. In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-7, no. 2, pp. 139–154, March 1985.Google Scholar
  25. 25.
    Poggio, T. A.; Torre, V; Koch, C.: Computational Vision and Regularization Theory. In Nature, vol. 317, pp. 314–319, 1985.CrossRefGoogle Scholar
  26. 26.
    Pollard, S. B.; Mayhew, J. E. W.; Frisby, J. P.: PMF: A stereo correspondence algorithm using a disparity gradient constraint. In Perception, 14, pp. 449–470, 1985.Google Scholar
  27. 27.
    Reimann, D.; Haken, H.: Stereovision by Self-Organisation. In Biological Cybernetics, vol. 71, pp. 17–26, 1994.zbMATHGoogle Scholar
  28. 28.
    Sanger, T. D.: Stereo Disparity Computation Using Gabor Filters. In Biological Cybernetics, vol. 59, pp. 405–418, 1988.CrossRefGoogle Scholar
  29. 29.
    Terzopoulos, D.: Regularization of Inverse Visual Problems Involving Discontinuities. In IEEE Trans. Pattern Anal. and Machine Intel., vol. PAMI-8, no. 4, pp. 413–424, July 1986.CrossRefGoogle Scholar
  30. 30.
    Varga, R. S.: Matrix Iterative Analyse. G. Forsythe (ed.), Prentice-Hall Series in Automatic Computation, New Jersey, 1962.Google Scholar
  31. 31.
    Weng, J.; Ahuja, N.; Huang, T. S.: Two-view matching. In Proceedings of the 2nd International Conference on Computer Vision, pp. 64–73, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Ralph Trapp
    • 1
  • Siegbert Drüe
    • 1
  • Georg Hartmann
    • 1
  1. 1.Department of Electrical EngineeringUniversity of PaderbornPaderbornGermany

Personalised recommendations