基于标签化匹配区域校正的双目立体匹配算法  

Binocular Stereo Matching Algorithm Based on Labeled Matching Region Correction

作　　者：周佳立[1,2] 陈育 吴超 武敏 ZHOU Jiali;CHEN Yu;WU Chao;WU Min(College of Science,Zhejiang University of Technology,Hangzhou 310023;Key Laboratory of Advanced Manufacturing Technology of Zhe-jiang Province,Zhejiang University,Hangzhou 310027;School of Sciences,Zhejiang University of Science and Technology,Hangzhou 310023)

机构地区：[1]浙江工业大学理学院,杭州310023 [2]浙江大学浙江省先进制造技术重点实验室,杭州310027 [3]浙江科技学院理学院,杭州310023

出　　处：《模式识别与人工智能》2020年第8期681-691,共11页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金青年科学基金项目(No.11301482);浙江省重点研发计划项目(No.2020C01005,2020C01006);浙江工业大学研究生教学改革项目(No.2018127)资助

摘　　要：双目立体视觉是一种精准有效的测量方法,由此文中提出基于标签化匹配区域校正的双目立体匹配算法.以常规图割算法为基础,通过匹配块的空间几何信息校正匹配区域,获得更高亚像素级精度的匹配视差.首先,根据标签及空间几何信息确定校正变换,充分利用左右两图匹配区域的像素信息.然后,不断更新获选标签,找到使全局能量最小的标签.最后,依据左右一致性准则及均值滤波细化视差图.实验表明,文中算法有利于寻找良好、平滑的分段线性视差图,在处理边缘区域和遮挡区域时精确度较高.Binocular stereo vision is an accurate and effective measurement method.A binocular stereo matching method for label matching region correction is proposed.Based on the conventional graph cuts algorithm,the matching region is corrected by the spatial geometrical information of the block and a higher subpixel accuracy matching disparity map is obtained.Firstly,the correction transformation is determined by label and spatial geometrical information,and consequently the pixel information of the matching area of the left and right images are fully exploited.Then,the candidate 3D label is updated repeatedly to find the label minimizing the global energy.Finally,the left-right checking and the mean filtering are utilized to refine the disparity map.Experiments show that the proposed method is effective in finding a good,smooth piecewise linear disparity map with higher accuracy for edge region and occlusion region.

关 键 词：立体匹配 图割 区域校正 3D标签 校正变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]