摘要
为了快速的计算出相机与目标物之间的距离,需要找到两幅图像的对应点。采用SIFT算法提取图像特征向量后,在匹配时加入外极线的约束条件,可以有效地去除误匹配,提高测量精度。实验结果表明,距离测量的相对误差在2%以内。
In order to calculate the distance between camera and target in parallel binocular vision system,the matching points in two images should be confirmed.The image matching algorithm based on scale invariant feature transform is used,and the fake matching points are eliminated by adding epipolar restriction in this study.This new image matching algorithm can achieve high-precision measurement,and the relative error of distance measurement is less than 2%.
出处
《青岛大学学报（自然科学版）》
CAS
2009年第1期59-62,共4页
Journal of Qingdao University(Natural Science Edition)
关键词
平行双目视觉
距离计算
SIFT特征匹配
外极线约束
parallel binocular stereo vision
distance computing，SIFT feature matching
epipolar restriction
