A dense stereo matching using two-pass dynamic programming with generalized ground control points
A dense stereo matching using two-pass dynamic programming with generalized ground control points
复制标题
DOI：
10.1109/cvpr.2005.22
复制
发表时间：
2005-06
期刊：
影响因子：
--
通讯作者：
Jae-Chul Kim;Kyoung Mu Lee;Byoung-Tae Choi;Sang Uk Lee
中科院分区：
文献类型：
--
作者：
Jae-Chul Kim;Kyoung Mu Lee;Byoung-Tae Choi;Sang Uk Lee
本文提出了一种解决密集立体匹配问题的方法。首先，引入了一种新的广义地面控制点（GGCP）方案，其中使用定向空间滤波器通过局部匹配来分配每个像素的真实视差的一个或多个视差候选。通过允许“所有”像素具有多个候选像素来实现其真实视差，GGCP 不仅保证提供指导后续匹配过程所需的足够数量的起始像素，而且还显着降低了错误匹配的风险，改进了先前基于 GCP 的方法，其中所选控制点的数量往往与可靠性成反比。其次，通过采用沿扫描线和跨扫描线执行优化的双遍动态编程技术，我们解决了典型的扫描线间不一致问题。此外，与GGCP结合，优化的稳定性和效率得到显着提高。标准数据集的实验结果表明，所提出的算法以更少的计算成本实现了与现有技术相当的结果。
A method for solving dense stereo matching problem is presented in this paper. First, a new generalized ground control points (GGCPs) scheme is introduced, where one or more disparity candidates for the true disparity of each pixel are assigned by local matching using the oriented spatial filters. By allowing "all" pixels to have multiple candidates for their true disparities, GGCPs not only guarantee to provide a sufficient number of starting pixels needed for guiding the subsequent matching process, but also remarkably reduce the risk of false match, improving the previous GCP-based approaches where the number of the selected control points tends to be inversely proportional to the reliability. Second, by employing a two-pass dynamic programming technique that performs optimization both along and across the scanlines, we solve the typical inter-scanline inconsistency problem. Moreover, combined with the GGCPs, the stability and efficiency of the optimization are improved significantly. Experimental results for the standard data sets show that the proposed algorithm achieves comparable results to the state-of-the-arts with much less computational cost.