摘要
立体匹配是双目视觉系统中必不可少的环节,对特征点进行匹配求解过程复杂,而且误匹配率较高。外极线约束为立体匹配提供了便利条件,但由于实际系统中的外极线是弯曲的,使得沿外极线进行同名点搜索不仅非常耗时,而且计算过程受噪声影响大。给出一种基于图像校正与灰度相关性的立体匹配算法。首先采用图像校正方法将弯曲的外极线变为相互平行的水平外极线,简化了外极线的求取过程;再利用灰度相关性算法对同名点进行匹配。实验结果验证了本文方法的准确性和稳定性。
Stereo matching is requisite for a binocular vision system.The process of the feature points matching is complex and with some mistake.Epipolar line restriction is convenient for stereo matching.However,the epipolar line in a practical system is curved,which makes that the searching corresponding points along epipolar line not only is time-consuming,but also is seriously effected by noise.Presents a matching algorithm based on image rectification and gray correlation.The curved epipolar line was converted into parallel straight lines,which simplified the solving process of epipolar line,and then the algorithm based on gray correlation was used to match corresponding points.Programming calculation results verified its accuracy and stability.
出处
《机械》
2010年第8期15-17,33,共4页
Machinery
关键词
双目视觉
立体匹配
图像校正
灰度相关性
binocular vision
stereo matching
image rectification
gray correlation
