液晶与显示2013，Vol.28Issue(3)：450-458,9.DOI:10.3788/YJYXS20132803.0450
面向低纹理图像的快速立体匹配
New Stereo Matching Method Based Edge Extraction
摘要
Abstract
Computing disparity images for stereo pairs of low texture images is a challenging task because matching costs inside low texture areas of the stereo pairs are almost similar.This problem can not be solved straightforwardly by increasing the size of aggregation windows or by using global optimization methods,e.g.dynamic programming,because those approaches will smooth depth discontinued boundaries as well.This paper proposes a new method that is able to robustly perform stereo matching for low texture stereo images.First,edge detection and Sobel filtering are performed for the images;second,edge maps is used to guide the aggregation of pixel matching costs;Finally,disparity computation and left-right validation(≥88％) are used to get the disparity maps.Experimental results demonstrate that the proposed method utilizes the edge maps computed from the stereo pairs to guide the cost aggregation process in stereo matching,and can produce a larger number of and a better accuracy of reliable disparities for low texture stereo images than the moving average method.关键词
三维重建/立体匹配/代价聚合/左右一致性检验/Winter-Take-AllKey words
3D reconstruction/stereo matching/cost aggregation/left-right validation/winter take-all分类
信息技术与安全科学引用本文复制引用
张来刚,魏仲慧,何昕,孙群..面向低纹理图像的快速立体匹配[J].液晶与显示,2013,28(3):450-458,9.基金项目
山东省自然科学基金(No.ZR2012CO026,No.ZR2011EL038) （No.ZR2012CO026,No.ZR2011EL038）
