Hierarchical adaptive stereo matching algorithm for obstacle detection with dynamic programming
Ming BAI
Yan ZHUANG
Wei WANG
摘要：An adaptive weighted stereo matching algorithm with multilevel and bidirectional dynamic programming based on ground control points(GCPs) is presented.To decrease time complexity without losing matching precision,using a multilevel search scheme,the coarse matching is processed in typical disparity space image,while the fine matching is processed in disparity-offset space image.In the upper level,GCPs are obtained by enhanced volumetric iterative algorithm enforcing the mutual constraint and the threshold constraint.Under the supervision of the highly reliable GCPs,bidirec-tional dynamic programming framework is employed to solve the inconsistency in the optimization path.In the lower level,to reduce running time,disparity-offset space is proposed to efficiently achieve the dense disparity image.In addition,an adaptive dual support-weight strategy is presented to aggregate matching cost,which considers photometric and geomet-ric information.Further,post-processing algorithm can ameliorate disparity results in areas with depth discontinuities and related by occlusions using dual threshold algorithm,where missing stereo information is substituted from surrounding re-gions.To demonstrate the effectiveness of the algorithm,we present the two groups of experimental results for four widely used standard stereo data sets,including discussion on performance and comparison with other methods,which show that the algorithm has not only a fast speed,but also significantly improves the efficiency of holistic optimization.
机标关键词：dynamic programmingobstacle detectioninformationground control pointsiterative algorithmmatching algorithmtime complexityimage
资助基金：the National Natural Science Foundation of China(60605023)the National Natural Science Foundation of China(60775048)Specialized Research Fund for the Doctoral Program of Higher Education(20060141006)
论文发表日期：2009-01-01
在线出版日期：2025-08-15（本平台首次上网日期，不代表文献的发表时间）
页数：7( 41-47 )
英文信息