基于可靠匹配点约束的遥感影像密集匹配

针对现有由稀到密的加密匹配算法中,初始匹配点可靠性低将导致迭代匹配拓展过程存在较多误匹配的问题,提出一种基于可靠匹配点约束的遥感影像密集匹配算法.首先,利用SIFT匹配点约束直线匹配获得的同名直线构建虚拟匹配点集,结合虚拟匹配点集和SIFT匹配点集建立初始匹配点集;然后,依次采用局部影像信息和局部几何约束对初始匹配点集...

A Dense Matching Algorithm for Remote Sensing Images based on Reliable Matched Points Constraint

To avoid the problem of mismatches caused by initial matched points that may contain false matches during iterative dense matching based on corresponding points, a dense matching algorithm for remote sensing images based on reliable matched point constraint is presented. Firstly, to increase the number of initial matching points and expand the covering range of initial matching points, the initial set of matched points containing the matched Scale-invariant Feature Transform (SIFT) points and virtual corresponding points is constructed, where the virtual corresponding points are generated from the intersections of corresponding lines obtained by the line matching algorithm based on the matched SIFT points constraint. Secondly, the initial set of matched points is checked to remove the false matches using local image information and local geometry constraints in turn. This process first uses the local texture feature constraint constructed based on fingerprint information and gradient information to eliminate the mismatched points with low similarity, and then uses the local geometric constraint constructed by Delaunay triangulation to remove the false matches generated by similar textures, thereby obtaining the optimized set of reliable matched points. Finally, the Delaunay triangulation is constructed using reliable matched points, and the gravity center of the triangles satisfying the areal threshold is used as the matching primitive during the dense matching process. The matching based on the epipolar constraint and affine transformation constraint is performed iteratively to obtain the dense matching results. This paper used four sets of forward and backward viewing data of ZY-3 to perform parameter analysis experiment and comparative analysis experiment to prove the effectiveness of the proposed dense matching algorithm. The results of parameter analysis experiment show that the reliable matched points can be obtained when the weighted index, texture feature similarity threshold, and local geometric similarity threshold are 0.3, 0.95, and 0.85, respectively. The average matching accuracy of the reliable matched points on the four sets of data is improved by 19% compared with the initial matched point. Meanwhile, the results of comparative analysis experiment show that the dense matching algorithm based on the reliable matched point constraint can effectively avoid the error propagation, which has higher matching accuracy compared with the comparison algorithms selected in this paper. The average matching accuracy of the four sets of data is 95%. Therefore, the algorithm can obtain better dense matching results by effectively eliminating mismatched points.