论文部分内容阅读
通过将匹配支持度的相似性测度引入SIFT特征匹配算法,提出了一种能够应用于不同源遥感影像的自动匹配方法。首先,建立待匹配影像中特征点的SIFT特征描述符;然后,以待匹配点与参考点间的欧氏距离为相似性测度,挑选一定数量的距离最为接近的匹配点作为候选点;最后,分别计算候选匹配点间的匹配支持度,并通过松弛法剔除误匹配点以完成影像的自动匹配。实验结果表明,与传统的灰度匹配及经典的SIFT特征匹配相比,此算法可明显提高影像匹配的成功率和可靠性。
By introducing similarity measure of matching support into SIFT feature matching algorithm, an automatic matching method that can be applied to different source remote sensing images is proposed. Firstly, the SIFT feature descriptor of the feature points in the image to be matched is established; then the Euclidean distance between the point to be matched and the reference point is taken as the similarity measure, and a certain number of matching points with the closest distance are selected as the candidate points; finally, Respectively, to calculate the matching support points between candidate matching points, and eliminate the matching points by relaxation to complete the automatic matching of images. Experimental results show that this algorithm can significantly improve the success rate and reliability of image matching compared with traditional gray matching and classic SIFT feature matching.