A Global Stereo Matching Algorithm Based on Adaptive Support-Weight and Graph Cut

Abstract:

For the stereo matching problem in the non-texture, occluded and depth discontinuity regions, a new stereo matching algorithm that based on the adaptive support-weight of Graph Cuts is proposed. It can reduce the matching error in the depth discontinuity and non-texture regions by the single adaptive support-weight matching methods. The occlusion and smoothness penalty is considered by building the energy function. The experimental results show that the proposed algorithm can achieve more precise and reliability matching.

• Periodical: Applied Mechanics and Materials (Volume 151)
• Pages: 612-616
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.151.612
• Online since: January 2012
• Authors: Guo He Yu, Jian Ming Liu, Xu Sheng Xie, Ji Guo Zeng
• Keywords: Graph Cuts, Stereo Matching, Stereo Vision

References

[1] F Schaffalitzky, A Zisserman.Viewpoint invariant texture matching and wide baseline stero[c]// IEEE International Conference on In Computer Vision, 2001. ICCV 2001:636~643.

DOI: 10.1109/iccv.2001.937686

[2] T K anade, M Okutomi.A stereo matching algorithm with an adaptive window[J].Theory and experiment,1994, 16 (9):920~931.

[3] Yoon K J, Kwen I S. Adaptive support-weight approach for correspondence search[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2006, 28(4): 650-656.

DOI: 10.1109/tpami.2006.70

[4] Tombari F, Mattoccia S, Stefano L D. Segmentation-based adaptive support for accurate stereo correspondence[C]∥Springer Lecture Notes in Computer Science. Berlin/Heidelberg: Springer, 2007: 427-438.

DOI: 10.1007/978-3-540-77129-6_38

[5] Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts[J]. IEEE TransPattern Analysis and Machine Intelligence, 2001, 23(11): 1 222-1 239.

DOI: 10.1109/34.969114

[6] Kolmogorov V,Zabih R. Multi-camera scene reconstruction via graph cuts[C]∥the 3th European Conference on Computer Vision.2002:82-96.

DOI: 10.1007/3-540-47977-5_6

[7] Kolmogorov V,Zabih R. Computing visual correspondence with occlusions using graph cuts[C],//Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada,2001：508-515.

DOI: 10.1109/iccv.2001.937668

[8] ZHANG Lingtao, QU Daokui,XU Fang. An Improved Stereo Matching Algorithm Based on Graph Cuts [J]. Robot, 2010-01-0104-05:1002-0446

DOI: 10.3724/sp.j.1218.2010.00104

[9] L.R. Ford,Jr.and D.R. Fulkerson.Flows in Networks[R],Princeton University Press,Princeton. NJ. 1962.

[10] Yuri Boykov and Vladimir Kolmogorov.An Experimental Comparison of Min-Cut/ Max-Flow Algorithms for Energy Minimization in Vision[C] //In IEEE Transactions on PAMI, Sept, 2004, 26(9):1124-1137.

DOI: 10.1109/tpami.2004.60

[11] Birchfield S, Tomasi C. A pixel dissimilarity measure that is insensitive to image sampling [J]. IEEE Trans Pattern Analysis and Machine Intelligence,1998, 20(4): 401-406.

DOI: 10.1109/34.677269

[12] Scharstein D, Szeliski R.A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms[J]. International Journal of Computer Vision,2002,47:7-42.

DOI: 10.1109/smbv.2001.988771

[13] International research community of stereo matching algorithm.the latest performance evaluation report of all algorithm submitted[EB/OL]. [2009-03-21]. http:∥vision.middlebury.edu/stereo/eval, 200.