Abstract: Concerning the high computation complexity and low efficiency in traditional stereo matching method based on belief propagation, a fast-converging algorithm was proposed. When calculating the confidence level of each pixel, the algorithm only utilized the information translated from the neighboring pixels in an adaptive support window, while ignoring the impact of the pixels beyond the window. The experimental results show that the proposed algorithm can reduce 40% to 50% of computation time while maintaining the matching accuracy. Therefore, it can meet the real-time requirement for stereo matching.

Key words: stereo matching, belief propagation, fast convergence, cost aggregation, adaptive window, message passing

摘要： 针对传统基于置信度传播的立体匹配算法运算次数较多、效率低下的问题，提出一种快速收敛的置信度传播算法。该算法在计算每一个像素点的置信度时，只考虑当前像素点自适应大小邻域内像素点对它的信息传递，而忽略距离较远的像素点的影响。实验结果表明提出的算法在保持相近匹配精度的前提下，运算时间减少40%~50%，满足立体匹配的实时性要求。

关键词: 立体匹配, 置信度传播, 快速收敛, 匹配代价, 自适应窗口, 信息传递