一种沿区域边界的动态规划立体匹配算法  

Stereo Matching Algorithm Based on Dynamic Programming along Region Boundary

作　　者：刘赫伟[1] 汪增福[1] 

机构地区：[1]中国科学技术大学自动化系视听觉信息处理与模式识别实验室,合肥230027

出　　处：《模式识别与人工智能》2010年第1期38-44,共7页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金资助项目(No.60875026)

摘　　要：提出一种基于图像区域分割的立体匹配算法.与通常的沿扫描行进行动态规划的立体匹配算法不同,该算法以图像"区域"为基元计算视差.首先使用相关法得到初始视差,然后利用一种区域边界上的多种子动态规划算法对视差进行精细计算,最终通过插值得到整个图像的稠密视差.实验结果表明,此算法速度较快、可靠性较高.A region based stereo matching algorithm is presented. The presented algorithm uses regions in images as elements for disparity computation, which is different from conventional stereo matching algorithms based on dynamic programming along scan lines. Once the initial disparities are obtained, a multiple seeds based dynamic programming process along the region boundaries of the image improves and refines the imperfect disparities. The experimental results show that the proposed algorithm is fast and effective.

关 键 词：立体匹配 动态规划 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]