摘要
立体匹配作为双目测量的关键技术之一,特征点的准确匹配将会影响双目视觉测量的准确性。所以,本文在提取图像区域特征和利用Zhang的标定算法实现摄像机标定的基础上,提出基于极线约束的对称距离的特征点匹配算法,然后采用最小二乘法计算特征点的三维坐标及两特征点的欧氏距离。实验结果分析表明,算法的匹配率高,测量的相对误差在1%以内,所以本文的匹配方法有效可行。
Stereo matching is one of the key technologies of binocular measurement. The precise matching of feature points will influence the accuracy of the binocular vision measurement. On the basis of extracting region characteristics of images and adopting Zhang calibration algorithm to achieve the camera calibration,the paper proposes a feature matching method based on symmetry distance of polar constraint,then using the least squares to computing the three- dimensional coordinates of feature points and two feature points in the Euclidean distance. The experimental results show that the proposed method has a good matching rate,the relative error of measurement within the 1%. So the matching method is effective and feasible.
作者
周艳青
薛河儒
姜新华
王春兰
徐杰
ZHOU Yanqing XUE Heru JIANG Xinhua WANG Chunlan XU Jie(College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China Inner Mongolia Institute of Standardization ,Hohhot 010070 , China)
出处
《内蒙古农业大学学报（自然科学版）》
CAS
2016年第3期107-111,共5页
Journal of Inner Mongolia Agricultural University(Natural Science Edition)
基金
国家自然科学基金项目(61461041)
关键词
双目视觉测量
特征点匹配
极线约束
三维坐标
Binocular vision measure
feature points matching
polar constraint
three-dimensional coordinate
