Advertisement

Refine Stereo Correspondence Using Bayesian Network and Dynamic Programming on a Color Based Minimal Span Tree

  • Naveed I Rao
  • Huijun Di
  • GuangYou Xu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4179)

Abstract

Stereo correspondence is one of the basic and most important problems in computer vision. For better correspondence, we need to determine the occlusion. Recently dynamic programming on a minimal span tree (mst) structure is used to search for correspondence. We have extended this idea. First, mst is generated directly based on the color information in the image instead of converting the color image into a gray scale. Second, have treated this mst as a Bayesian Network. Novelty is attained by considering local variances of the disparity and intensity differences in the conditional Gaussians as unobserved random parameters. These parameters are iteratively inferenced by alternate estimation along the tree given a current disparity map. It is followed by dynamic programming estimation of the map given the current variance estimates thus reducing the overall occlusion. We evaluate our algorithm on the benchmark Middlebury database. The results are promising for modeling occlusion in early vision problems.

Keywords

Dynamic Programming Bayesian Network Minimal Span Tree Helmholtz Free Energy Occlusion Modeling 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Belhumeur, P.N.: A bayesian-approach to binocular stereopsis. IJCV 19, 237–260 (1996)CrossRefGoogle Scholar
  2. 2.
    Bobick, A.F., Intille, S.S.: Large occlusion stereo. IJCV 33(3), 1–20 (1999)CrossRefGoogle Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI 11(23), 1222–1239 (2001)CrossRefGoogle Scholar
  4. 4.
    Brown, M.Z., Burschka, D., Hager, G.D.: Advances in computational stereo. TPAMI 7 (2003)Google Scholar
  5. 5.
    Cormen, T., Leiserson, C., Rivest, R.: Introduction to Algorithms. MIT Press, Cambridge (1990)MATHGoogle Scholar
  6. 6.
    Cox, I.J., Hingorani, S.L., Rao, S.B., Maggs, B.M.: A max likelihood stereo algorithm. Computer Vision and Image Understanding 63, 542–567 (1996)CrossRefGoogle Scholar
  7. 7.
    Frey, B.J., Jojic, N.: A comparison of algorithms for inference and learning in probabilistic graphical models. TPAMI 27(9) (2005)Google Scholar
  8. 8.
    Geiger, D., Ladendorf, B., Yuille, A.: Occlusions and binocular stereo. IJCV 14(3), 211–226 (1995)CrossRefGoogle Scholar
  9. 9.
    Geiger, D., Ishikawa, H.: Occlusions, discontinuities, and epipolar lines in stereo. In: ECCV (1998)Google Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: ECCV (2002)Google Scholar
  11. 11.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 1-3(47), 7–42 (2002)CrossRefGoogle Scholar
  12. 12.
    Sonka, M., Hlavac, V., Boyle, R.: Image Processing Analysis and Machine Vision, 2nd edn., USA (2002)Google Scholar
  13. 13.
    Sun, J., Zheng, N., Shum, H.: Stereo matching using belief propagation. TPAMI 7 (2003)Google Scholar
  14. 14.
    Veksler, O.: Stereo correspondence by dynamic programming on a tree. In: CVPR (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Naveed I Rao
    • 1
  • Huijun Di
    • 1
  • GuangYou Xu
    • 1
  1. 1.Pervasive Computing Lab, Institute of Human Computer Interaction Department, of Computer EngineeringTsinghua UniversityBeijingChina

Personalised recommendations