基于网络最大流的立体匹配算法  

Stereo Matching Algorithm Based on the Maximum Flow of Network

作　　者：黄海赟[1] 戚飞虎[1] 岑峰[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200030

出　　处：《上海交通大学学报》2001年第2期168-172,共5页Journal of Shanghai Jiaotong University

摘　　要：为得到立体图像对的全局最优匹配 ,将视差搜索范围离散化 ,与图像坐标一起构成三维空间网络 .恰当定义网络各边的容量 ,使之兼顾立体匹配的相容性和光滑性约束 ,将立体匹配转化为网络优化问题 .通过求解网络的最大流和最小切割 ,获得全局最优的视差分布数据 .实验表明 ,算法生成的视差数据不仅连续稠密而且保留了细节信息 .In order to get the global optimal matching of stereo image pairs, the algorithm discretized the searching range of disparity, then combined it with image coordinates to construct a 3D network. The capacity of net edge was properly defined to satisfy both smooth and compatible constraint. Thus, stereo matching was transformed into the problem of network optimizing. The global optimal disparity was derived from solving the maximum flow and minimum cut of the network. Experiments prove that the algorithm not only produces smooth and dense disparity but also keeps detailed information. It establishes a good foundation for 3D reconstruction.

关 键 词：立体匹配 视差 最大流 立体图像 算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP391.4[自动化与计算机技术—计算机科学与技术]