Refine Stereo Correspondence Using Bayesian Network and Dynamic Programming on a Color Based Minimal Span Tree
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.
KeywordsDynamic Programming Bayesian Network Minimal Span Tree Helmholtz Free Energy Occlusion Modeling
Unable to display preview. Download preview PDF.
- 4.Brown, M.Z., Burschka, D., Hager, G.D.: Advances in computational stereo. TPAMI 7 (2003)Google Scholar
- 7.Frey, B.J., Jojic, N.: A comparison of algorithms for inference and learning in probabilistic graphical models. TPAMI 27(9) (2005)Google Scholar
- 9.Geiger, D., Ishikawa, H.: Occlusions, discontinuities, and epipolar lines in stereo. In: ECCV (1998)Google Scholar
- 10.Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: ECCV (2002)Google Scholar
- 12.Sonka, M., Hlavac, V., Boyle, R.: Image Processing Analysis and Machine Vision, 2nd edn., USA (2002)Google Scholar
- 13.Sun, J., Zheng, N., Shum, H.: Stereo matching using belief propagation. TPAMI 7 (2003)Google Scholar
- 14.Veksler, O.: Stereo correspondence by dynamic programming on a tree. In: CVPR (2005)Google Scholar