一种基于双向动态规划的立体匹配算法

Stereo Matching Algorithm Based on Bidirectional Dynamic Programming

提出了一种利用双向动态规划和视差可靠性准则的立体匹配算法。首先,提出了一种新的全局能量函数,它解决了扫描线间的不连续性,同时保护了的视差不连续边缘;其次,利用加强顺序约束和遮挡约束的双向动态规划方法来处理遮挡;最后,在利用三个可靠性准则去除伪视差点之后,使用可移动窗口方法填充伪视差点的视差获得稠密视差图。实验结果表明,该算法在深度不连续区域和大的无纹理区域均能取得很好的匹配效果。

A stereo matching algorithm using bidirectional dynamic programming and disparity reliability rules was proposed. Firstly, a new global cost function was proposed which resolved inconsistency between scanlines and preserved disparity discontinuities; Secondly, a bidirectional dynamic programming method enforcing ordering and occlusion constraints was used to handle occlusions; Finally, after mismatches were removed by three reliability rules, shiftable window method was used to refill the disparities of mismatches and dense disparity maps were got. The experiment results reveal that the algorithm is effective both in depth discontinuities and large untextured regions.