双目动态视觉测量的匹配

Matching algorithm of binocular dynamic vision measurement

针对在双目动态视觉测量系统中对特征点的准确匹配问题,采用强后方交会优化了外参数,提高外参数的精度,从而提高求取极线的精度;提出一种针对2幅图像特征点匹配的多约束匹配算法。多约束匹配算法在极线约束的基础上,增加了唯一性约束和双向匹配约束,结合视差约束的二次匹配,得到2幅图像特征点正确的匹配关系。实验结果表明:用于双目动态视觉测量系统的匹配中,可得到100%的匹配准确率。可以满足双目动态视觉测量系统对两幅图匹配的要求。

In order to realize the matching of feature points in the binocular dynamic vision measurement system, a method of strong space resection is used to optimize the elements of exterior orientation and raise their precision, so as to improve the calculating precision of epipolar line. An algorithm of multiple restriction matching for two homologous images matching of feature points is introduced. Based on epipolar line constrain, this algorithm increases the uniqueness constraint and double constraint. Combined with the second match with disparity gradient constrain, the correct matching relationship of feature points in two homologous images is gained. The experimental results show that：this method can get the matching accuracy rate of 100% and satisfy the need of binocular dynamic vision measurement system.