Ambiguous Region Matching and Boundary Pixel Optimization for Stereo Computation

摘要：

　　In this paper,we present a stereo matching algorithm based on planar surface hypothesis.It improves the results of low texture regions and mixed pixels on object boundaries.First,regions are segmented by applying the mean-shift segmentation method.Then we propose a coarse-to-fine algorithm to increase the reliable correspondences in low texture regions.Third,the Belief Propagation algorithm is used to optimize disparity plane labeling.Finally,for a mixed pixel,we utilize the results of the depth plane and the local region of it to regulate its disparity.Experimental results using the Middlebury stereo test show that the performance of our method is high.

关键词： Belief propagation dense disparity map mean-shift mixed pixel stereo matching

作者: Xingnian Cui Fan Yang Qingmin Liao

作者单位: Department of Electronic Engineering, Tsinghua University, Beijing, China

会议类型: 国际会议

会议名称: 2012 International Conference on Electrical Insulating Materials and Electrical Engineering(EIMEE2012)(2012年电绝缘材料和电气工程国际会议)

会议地点: 沈阳

会议语种:英文

页码: 735-740

在线出版日期: 2012-05-25（万方平台首次上网日期，不代表论文的发表时间）