Advertisement

Concurrent Stereo Matching: An Image Noise-Driven Model

  • John Morris
  • Georgy Gimel’farb
  • Jiang Liu
  • Patrice Delmas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3757)

Abstract

Most published techniques for reconstructing scenes from stereo pairs follow a conventional strategy of searching for a single surface yielding the best correspondence between the images. The search involves specific constraints on surface continuity, smoothness, and visibility (occlusions) embedded in a matching score – typically an ad hoc linear combination of distinctly different criteria of signal similarity. The coefficients or weighing factors are selected empirically because they dramatically effect accuracy of stereo matching. The single surface assumption is also too restrictive – few real scenes have only one surface.

We introduce a paradigm of concurrent stereo that circumvents in part these problems by separating image matching from a choice of the 3D surfaces. Concurrent stereo matching first detects all likely matching 3D volumes instead of single best matches. Then, starting in the foreground, the volumes are explored, selecting mutually consistent optical surfaces that exhibit high point-wise signal similarity. Local, rather than global, surface continuity and visibility constraints are applied.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Burschka, D., Brown, M.Z., Hager, G.D.: Advances in computational stereo. IEEE Trans. PAMI 25, 993–1008 (2003)Google Scholar
  2. 2.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Poggio, T., Torre, V., Koch, C.: Computational vision and regularization theory. Nature 317, 314–319 (1985)CrossRefGoogle Scholar
  4. 4.
    Hsieh, Y.C., Mckeown Jr., D.M., Perlant, F.P.: Performance evaluation of scene registration and stereo matching for cartographic feature extraction. IEEE Trans. PAMI 14, 214–238 (1992)Google Scholar
  5. 5.
    Zitnick, C.L., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Trans. PAMI 22, 675–684 (2000)Google Scholar
  6. 6.
    Gimel’farb, G.L.: Symmetric approach to solution of the problem of automating stereo measurements in photogrammetry. Cybernetics 15, 235–247 (1979)zbMATHGoogle Scholar
  7. 7.
    Baker, H.H.: Surfaces from mono and stereo images. Photogrammetria 39, 217–237 (1984)CrossRefGoogle Scholar
  8. 8.
    Ohta, Y., Kanade, T.: Stereo by intra- and inter-scanline search using dynamic programming. IEEE Trans. PAMI 7, 139–154 (1985)Google Scholar
  9. 9.
    Gimel’farb, G.L.: Intensity-based computer binocular stereo vision: signal models and algorithms. Int. J. Imaging Systems and Technology 3, 189–200 (1991)CrossRefGoogle Scholar
  10. 10.
    Roy, S.: Stereo without epiploar lines: A maximum-flow formulation. Int. J. Computer Vision 34, 147–161 (1999)CrossRefGoogle Scholar
  11. 11.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cut. IEEE Trans. PAMI 23, 1222–1239 (2001)Google Scholar
  12. 12.
    Kim, J., Kolmogorov, V., Zabih, R.: Visual correspondence using energy minimization and mutual information. In: Proc. 9th IEEE Int. Conf. Computer Vision (ICCV 2003), Nice, France, October 13-16, vol. 2, pp. 1003–1010. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  13. 13.
    Tappen, M.F., Freeman, W.T.: Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In: Proc. 9th IEEE Int. Conf. Computer Vision (ICCV 2003), Nice, France, October 13-16, vol. 2, pp. 900–906. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  14. 14.
    Sun, J., Zheng, N.N., Shum, H.Y.: Stereo matching using belief propagation. IEEE Trans. PAMI 25(7), 787–800 (2003)Google Scholar
  15. 15.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. In: Proc. 2004 IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, 2004, vol. 1, pp. 261–268. IEEE Computer Society Press, Los Alamitos (2004)CrossRefGoogle Scholar
  16. 16.
    Sun, J., Li, Y., Kang, S.B., Shum, H.Y.: Symmetric stereo matching for occlusion handling. In: Proc. 2005 IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, San Diego, CA, June 20-26, vol. 2, pp. 399–406. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  17. 17.
    Gimel’farb, G.: Probabilistic regularisation and symmetry in binocular dynamic programming stereo. Pattern Recognition Letters 23(4), 431–442 (2002)zbMATHCrossRefGoogle Scholar
  18. 18.
    Liu, J., Gimel’farb, G.: Accuracy of stereo reconstruction by minimum cut, symmetric dynamic programming, and correlation. In: Proc. Image & Vision Computing New Zealand (IVCNZ 2004) Conf., Akaroa, New Zealand, November 21-23, pp. 65–70. Landcare Research, Lincoln (2004)Google Scholar
  19. 19.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. Int. J. Computer Vision 38, 199–218 (2000)zbMATHCrossRefGoogle Scholar
  20. 20.
    Torralba, A.: Modeling global scene factors in attention. J. Optical Society of America 20A, 1407–1418 (2003)CrossRefGoogle Scholar
  21. 21.
    Birchfield, S., Tomasi, C.: A pixel dissimilarity measure that is insensitive to image sampling. IEEE Trans. PAMI 20, 401–406 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • John Morris
    • 1
  • Georgy Gimel’farb
    • 1
  • Jiang Liu
    • 1
  • Patrice Delmas
    • 1
  1. 1.Department of Computer ScienceThe University of AucklandAucklandNew Zealand

Personalised recommendations