快速视差范围估计算法及其应用.pdfVIP

第27 卷 第 1 期 计算机辅助设计与图形学学报 Vol. 27 No.1 2015 年 1 月 Journal of Computer-Aided Design Computer Graphics Jan. 2015 快速视差范围估计算法及其应用 毛 苗, 吴艳楠, 秦开怀* (清华大学计算机科学与技术系 北京 100084) (qkh-dcs@) 摘 要: 视差范围估计在立体匹配中非常重要, 准确的视差范围能提高立体匹配的精度和速度. 为此提出一种基于 匹配代价搜索和图像细分的快速视差范围估计算法. 该算法将输入图像均匀分成多个图像块, 采用匹配代价搜索计 算每一图像块的视差, 找到视差最大(最小) 的图像块, 并利用迭代细分规则将该图像块继续分成更小的子块, 直至得 到稳定的最大(最小)视差; 利用匹配代价图对图像块进行可靠性检测, 以解决弱纹理块容易误匹配的问题. 实验结果 表明, 文中算法在保持97.3% 的平均命中率的同时将立体匹配的平均搜索空间降低了27.7%, 比采用传统算法可以得 到更准确的视差范围; 将该算法应用于立体匹配算法中降低了其平均误匹配率, 并将计算时间缩短了20% ～45%. 关键词：视差范围; 立体匹配; 迭代细分; 图像块视差可靠性 中图法分类号：TP391.41 Fast Disparity Range Estimation and Its Applications * Mao Miao, Wu Yannan, and Qin Kaihuai (Department of Computer Science and Technology, Tsinghua University, Beijing 100084) Abstract: Disparity range estimation is very important in stereo matching. An appropriate disparity range can increase the precision and speed of stereo matching. This paper proposes a fast disparity range estima- tion method based on matching-cost search and image subdivision. It evenly divides input images into sev- eral sub-blocks, and searches using matching cost to find out which sub-block is having the maxi- mum/minimum disparity. After that, the maximum/minimum sub-block is recursively divided into smaller sub-blocks, until all current sub-blocks have the same disparity. To deal with image blocks with week tex- tures, detecting their disparity reliabilities is applied via matching-cost diagram. Experimental results show that our method can achieve 2