Based on Dynamic Programming along Region Boundary
LIU He-Wei,WANG Zeng-Fu
Laboratory of Visual-Audio Information Processing and Pattern Recognition,Department of Automation,University of Science and Technology of China,Hefei 230027
A region based stereo matching algorithm is presented. The presented algorithm uses regions in images as elements for disparity computation, which is different from conventional stereo matching algorithms based on dynamic programming along scan lines. Once the initial disparities are obtained, a multiple seeds based dynamic programming process along the region boundaries of the image improves and refines the imperfect disparities. The experimental results show that the proposed algorithm is fast and effective.
刘赫伟,汪增福. 一种沿区域边界的动态规划立体匹配算法[J]. 模式识别与人工智能, 2010, 23(1): 39-44.
LIU He-Wei,WANG Zeng-Fu. Based on Dynamic Programming along Region Boundary. , 2010, 23(1): 39-44.
[1] Scharstein D, Szeliski R. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision, 2002, 47(1): 7-42 [2] Brown M Z, Burschka D, Hager G D. Advances in Computational Stereo. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(8): 993-1008 [3] Bobick A F, Intille S S. Large Occlusion Stereo. International Journal of Computer Vision, 1999, 33(3): 181-200 [4] Wei Yichen, Quan Long. Region-Based Progressive Stereo Matching // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA, 2004, Ⅱ: 106-113 [5] Tao H, Sawhney H, Kumar R. A Global Matching Framework for Stereo Computation // Proc of the 8th IEEE International Conference on Computer Vision. Vancouver, Canada, 2001, Ⅰ: 532-539 [6] Lin M H, Tomasi C. Surfaces with Occlusions from Layered Stereo. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(8): 1073-1078 [7] Comaniciu D, Meer P. Mean Shift: A Robust Approach toward Feature Space Analysis. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619 [8] Birchfield S, Tomasi C. A Pixel Dissimilarity Measure That Is Insensitive to Image Sampling. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(4): 401-406 [9] Ji Fengxin, Ou Zongying, Qin Xujia, et al. An Algorithm of Reconstructing 3D Surface from Discrete Data of Layered Images Based on Delaunay Triangulation. Journal of Engineering Graphics, 2001, 22(2): 53-58 (in Chinese) (纪凤欣,欧宗瑛,秦绪佳,等.基于Delaunay三角剖分的层析图像离散数据表面重建算法.工程图学学报, 2001, 22(2): 53-58) [10] Middlebury College Stereo Vision Research Page [EB/OL]. [2008- 09- 20]. http://vision.middlebury.edu/stereo [11] Veksler O. Stereo Correspondence by Dynamic Programming on a Tree // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅱ: 384-390 [12] Boykov Y, Veksler O, Zabih R. Fast Approximate Energy Minimization via Graph Cuts. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239 [13] Larsen E S, Mordohai P, Pollefeys M, et al. Temporally Consistent Reconstruction from Multiple Video Streams Using Enhanced Belief Propagation // Proc of the 11th IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 1-8 [14] Kolmogorov V, Zabih R. Computing Visual Correspondence with Occlusions Using Graph Cuts // Proc of the 8th IEEE International Conference on Computer Vision. Vancouver, Canada, 2001, Ⅱ: 508-515