International Journal of Computer Vision

, Volume 33, Issue 3, pp 181–200 | Cite as

Large Occlusion Stereo

  • Aaron F. Bobick
  • Stephen S. Intille


A method for solving the stereo matching problem in the presence of large occlusion is presented. A data structure—the disparity space image—is defined to facilitate the description of the effects of occlusion on the stereo matching process and in particular on dynamic programming (DP) solutions that find matches and occlusions simultaneously. We significantly improve upon existing DP stereo matching methods by showing that while some cost must be assigned to unmatched pixels, sensitivity to occlusion-cost and algorithmic complexity can be significantly reduced when highly-reliable matches, or ground control points, are incorporated into the matching process. The use of ground control points eliminates both the need for biasing the process towards a smooth solution and the task of selecting critical prior probabilities describing image formation. Finally, we describe how the detection of intensity edges can be used to bias the recovered solution such that occlusion boundaries will tend to be proposed along such edges, reflecting the observation that occlusion boundaries usually cause intensity discontinuities.

stereo occlusion dynamic-programming stereo disparity-space 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Anderson, B. and Nakayama, K. 1995. Toward a general theory of stereopsis: Binocular matching, occluding contour, and fusion. Psychological Review, 101(3):414–445.Google Scholar
  2. Baker, H.H. and Binford, T.O. 1981. Depth from edge and intensity based stereo. In Proc. 7th Int. Joint Conf. Art. Intel., pp. 631–636.Google Scholar
  3. Baker, H.H., Bolles, R.C., and Woodfill, J. 1994. Realtime stereo and motion integration for navigation. In Proc. Image Understanding Workshop, pp. 1295–1304.Google Scholar
  4. Barnard, F. 1982. Computational stereo. Computing Surveys, 14:553–572.CrossRefGoogle Scholar
  5. Belhumeur, P. 1993a. Bayesian models for reconstructing the scene geometry in a pair of stereo images. In Proc. Info. Sciences Conf. Google Scholar
  6. Belhumeur, P. 1993b. A binocular stereo algorithm for reconstructing sloping, creased, and broken surfaces in the presence of halfocclusion. In Proc. Int. Conf. Comp. Vis.Google Scholar
  7. Belhumeur, P. and Mumford, D. 1992. A bayseian treatment of the stereo correspondence problem using half-occluded regions. In Proc. Comp. Vis. and Pattern Rec.Google Scholar
  8. Bellman, R.E. 1957. Dynamic Programming. Princeton University Press.Google Scholar
  9. Bolles, R., Baker, H., and Hannah, M. 1993. The JISCT stereo evaluation. In Proc. Image Understanding Workshop, pp. 263–274.Google Scholar
  10. Canny, J. 1986. A computational approach to edge detection. IEEE Trans. Patt. Analy. and Mach. Intell., 8(6):679–698.Google Scholar
  11. Chang, C., Catterjee, S., and Kube, P.R. 1991. On an analysis of static occlusion in stereo vision. In Proc. Comp. Vis. and Pattern Rec., pp. 722–723.Google Scholar
  12. Chung, R. and Nevatia, R. 1991. Use of monocular groupings and occlusion analysis in a hierarchical stereo system. In Proc. Comp. Vis. and Pattern Rec., pp. 50–55.Google Scholar
  13. Cochran, S.D. and Medioni, G. 1992. 3-d surface description from binocular stereo. IEEE Trans. Patt. Analy. and Mach. Intell., 14(10):981–994.Google Scholar
  14. Cox, I.J., Hingorani, S., Rao, S., and Maggs, B. 1996. A maximum likelihood stereo algorithm. Comp. Vis. and Img. Und., 63(3):542–568.Google Scholar
  15. Dhond, U.R. and Aggarwal, J.K. 1989. Structure from stereo—a review. IEEE Trans. Sys., Man and Cyber., 19(6):1489–1510.Google Scholar
  16. Dhond, U.R. and Aggarwal, J.K. 1995. Stero matching in the presence of narrow occluding objects using dynamic disparity search. IEEE Trans. Patt. Analy. and Mach. Intell., 17(7):719–724.Google Scholar
  17. Geiger, D., Ladendorf, B., and Yuille, A. 1992. Occlusions and binocular stereo. In Proc. European Conf. Comp. Vis., pp. 425–433.Google Scholar
  18. Geiger, D., Ladendorf, B., and Yuille, A.L. 1995. Occlusions and binocular stereo. Int. J. of Comp. Vis., 14(3):211–226.Google Scholar
  19. Hannah, M.J. 1989. A system for digital stereo image matching. Photogrammetric Eng. and Remote Sensing, 55(12):1765–1770.Google Scholar
  20. Intille, S.S. and Bobick, A.F. 1994. Disparity-space images and large occlusion stereo. In Proc. European Conf. Comp. Vis., Stockholm, pp. 179–186.Google Scholar
  21. Julesz, B. and Chang, J. 1976. Interaction between pools of binocular disparity detectors tuned to different disparities. Biological Cybernetics, 22:107–119.Google Scholar
  22. Kanade, T. and Okutomi, M. 1990. A stereo matching algorithm with an adaptive window: theory and experiment. In Proc. Image Understanding Workshop, pp. 383–389.Google Scholar
  23. Little, J.J. and Gillett, W.E. 1990. Direct evidence for occlusion in stereo and motion. Image and Vision Comp., 8(4):328–340.Google Scholar
  24. Nakayama, K. and Shimojo, S. 1990. Da Vinci stereopsis: Depth and subjective occluding contours from unpaired image points. Vision Research, 30(11):1811–1825.Google Scholar
  25. Ohta, Y. and Kanade, T. 1985. Stereo by intra-and inter-scanline search using dynamic programming. IEEE Trans. Patt. Analy. and Mach. Intell., 7:139–154.Google Scholar
  26. Quam, L.H. 1984. Hierachical warp stereo. In Proc. Image Understanding Workshop, New Orleans, pp. 149–155.Google Scholar
  27. Shimojo, S. and Nakayama, K. 1990. Real world occlusion constraints and binocular rivalry. Vision Research, 30(1):69–80.Google Scholar
  28. Yang, Y., Yuille, A., and Lu, J. 1993. Local, global, and multilevel stereo matching. In Proc. Comp. Vis. and Pattern Rec.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • Aaron F. Bobick
    • 1
  • Stephen S. Intille
    • 2
  1. 1.College of ComputingGeorgia Institute of TechnologyAtlanta
  2. 2.MIT Media LaboratoryCambridge

Personalised recommendations