Finding the Largest Unambiguous Component of Stereo Matching

  • Radim Šára
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


Stereo matching is an ill-posed problem for at least two principal reasons: (1) because of the random nature of match similarity measure and (2) because of structural ambiguity due to repetitive patterns. Both ambiguities require the problem to be posed in the regularization framework. Continuity is a natural choice for a prior model. But this model may fail in low signal-to-noise ratio regions. The resulting artefacts may then completely spoil the subsequent visual task.

A question arises whether one could (1) find the unambiguous component of matching and, simultaneously, (2) identify the ambiguous component of the solution and then, optionally, (3) regularize the task for the ambiguous component only. Some authors have already taken this view. In this paper we define a new stability property which is a condition a set of matches must satisfy to be considered unambiguous at a given confidence level. It turns out that for a given matching problem this set is (1) unique and (2) it is already a matching. We give a fast algorithm that is able to find the largest stable matching. The algorithm is then used to show on real scenes that the unambiguous component is quite dense (10–80%) and error-free (total error rate of 0.3–1.4%), both depending on the confidence level chosen.


Inhibition Zone Match Problem Stable Match Stereo Match Maximum Cardinality 
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.


  1. 1.
    Julesz, B.: Towards the automation of binocular depth perception (AUTOMAP-1). In: IFIPS Congress, Munich (1962)Google Scholar
  2. 2.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by shape carving. IJCV 38 (2000) 199–218zbMATHCrossRefGoogle Scholar
  3. 3.
    Baker, S., Sim, T., Kanade, T.: A characterization of inherent stereo ambiguities. In: Proc ICCV. (2001) 428–435Google Scholar
  4. 4.
    Schlesinger, M.I.: Ambiguity in stereopsis. Personal communication (1998)Google Scholar
  5. 5.
    Šára, R.: Failure analysis of stable matchings. Research report (In preparation)Google Scholar
  6. 6.
    Stewart, C.V., Dyer, C.R.: The trinocular general support algorithm: A three-camera stereo algorithm for overcoming binocular matching errors. In: Proc ICCV. (1988) 134–138Google Scholar
  7. 7.
    Satoh, K., Ohta, Y.: Occlusion detectable stereo using a camera matrix. In: Proc ACCV. (1995) 331–335Google Scholar
  8. 8.
    Marr, D.: A note on the computation of binocular disparity in a symbolic, low-level visual processor. A.I. Memo 327, AI Lab, MIT (1974)Google Scholar
  9. 9.
    Pollard, S.B., Mayhew, J.E.W., Frisby, J.P.: PMF: A stereo correspondence algorithm using a disparity gradient limit. Perception 14 (1985) 449–470CrossRefGoogle Scholar
  10. 10.
    Zitnick, C.L., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Trans PAMI 22 (2000) 675–684Google Scholar
  11. 11.
    Belhumeur, P.N.: A Bayesian approach to binocular stereopsis. IJCV 19 (1996) 237–260CrossRefGoogle Scholar
  12. 12.
    Bobick, A.F., Intille, S.S.: Large occlusion stereo. IJCV 33 (1999) 181–200CrossRefGoogle Scholar
  13. 13.
    Robert, L., Deriche, R.: Dense depth map reconstruction: A minimization and regularization approach which preserves discontinuities. In: Proc ICIP. (1992) 123–127Google Scholar
  14. 14.
    Barnard, S.T.: Stochastic stereo matching over scale. IJCV 3 (1989) 17–32CrossRefGoogle Scholar
  15. 15.
    Scharstein, D., Szeliski, R.: Stereo matching with nonlinear diffusion. IJCV 28 (1998) 155–174CrossRefGoogle Scholar
  16. 16.
    Boykov, Y., Veksler, O., Zabih, R.: Disparity component matching for visual correspondence. In: Proc Conf CVPR. (1997) 470–475Google Scholar
  17. 17.
    Ishikawa, H., Geiger, D.: Occlusions, discontinuities, and epipolar lines in stereo. In: ECCV. (1998) 232–248Google Scholar
  18. 18.
    Roy, S., Cox, I.J.: A maximum-flow formulation of the n-camera stereo correspondence problem. In: Proc ICCV. (1998) 492–499Google Scholar
  19. 19.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc ICCV. (2001) 508–515Google Scholar
  20. 20.
    March, R.: Computation of stereo disparity using regularization. Pattern Recognition Letters 8 (1988) 181–187CrossRefGoogle Scholar
  21. 21.
    March, R.: A regularization model for stereo vision with controlled continuity. Pattern Recognition Letters 10 (1989) 259–263zbMATHCrossRefGoogle Scholar
  22. 22.
    Jung, D.Y., Oh, J.H., Lee, S.C., Lee, C.H., Nam, K.G.: Stereo matching by discontinuity-preserving regularization. J of Elect Eng and Inf Sci 4 (1999) 452–8Google Scholar
  23. 23.
    Manduchi, R.; Tomasi, C.: Distinctiveness maps for image matching. In: Proc ICIAP. (1999) 26–31Google Scholar
  24. 24.
    Šára, R.: Sigma-delta stable matching for computational stereopsis. Research Report CTU-CMP-2001-25, Center for Machine Perception, Czech Technical University (2001) [].
  25. 25.
    Krol, J.D., van der Grind, W.A.: Rehabilitation of a classical notion of Panum’s fusional area. Perception 11 (1982) 615–619CrossRefGoogle Scholar
  26. 26.
    Yuille, A.L., Poggio, T.: A generalized ordering constraint for stereo correspondence. A.I. Memo 777, AI Lab, MIT (1984)Google Scholar
  27. 27.
    Šára, R.: A fast algorithm for confidently stable matching. Research Report CTU-CMP-2002-03, Center for Machine Perception, Czech Technical University (2002) [].
  28. 28.
    Moravec, H.P.: Towards automatic visual obstacle avoidance. In: Proc IJCAI. (1977) 584Google Scholar
  29. 29.
    Mandelbaum, R., Kamberova, G., Mintz, M.: Stereo depth estimation: a confidence interval approach. In: Proc ICCV. (1998) 503–509Google Scholar
  30. 30.
    Cox, I.J., Hingorani, S., Maggs, B.M., Rao, S.B.: Stereo without disparity gradient smoothing: a Bayesian sensor fusion solution. In: Proc BMVC. (1992) 337–346Google Scholar
  31. 31.
    Scheibe, K., Korsitzky, H., Reulke, R., Scheele, M., Solbrig, M.: EYESCAN-a high resolution digital panoramic camera. In: Int Wkshp Robot Vision, Auckland (2001) 77–83Google Scholar
  32. 32.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Technical Report MSR-TR-2001-81, Microsoft Research, Redmont, WA (2001) To appear in IJCV.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Radim Šára
    • 1
  1. 1.Center for Machine Perception, Department of Cybernetics Faculty of Electrical EngineeringCzech Technical UniversityPragueCzech Republic

Personalised recommendations