Stereo Matching based on Robust Likelihoods and MST Leveraged Smoothness Priors

摘要：

　　This paper proposes a global stereo correspondence using robust matching likelihoods and minimum spanning tree (MST) leveraged smooth priors in a probabilistic graphical model framework.The matching likelihoods of the stereo correspondence can be robustly constructed as data term by aggregating initial matching costs from Weber local descriptors using an unsymmetrical guided filtering in a linear model.The disparity priors are devised as smooth term to characterize the smoothness constraints leveraged by the MST structure.The presented stereo approach provides an effective and efficient way to reflect robust visual dissimilarity and resolve local and regional discontinuities.Experiments demonstrate that the proposed global stereo matching method can produce piecewise smooth,accurate and dense disparity map,while removing effectively the visual ambiguity of the stereo matching problem.

关键词： stereo vision Markov random field Weber descriptor minimun spanning tree QPBO optimization

作者: Tianliang Liu Liang Wang Xiuchang Zhu

作者单位: Jiangsu Provincial Key Lab of Image Processing and Image Communication College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, China

会议类型: 国际会议

会议名称: 2012 IEEE 11th International Conference on Signal Processing (第11届IEEE信号处理国际会议)

会议地点: 北京

会议语种:英文

页码: 1160-1164

在线出版日期: 2012-10-21（万方平台首次上网日期，不代表论文的发表时间）