An automatic registration based on Genetic Algorithm for multi-source remote sensing
Zhijun Gou, Hongbing Ma · 2016
The registration of multi-source remote sensing images is a challenging and crucial problem in remote sensing field. An automatic registration based on genetic algorithm is presented in this paper. Firstly, Scale-Invariant Feature Transform Modification (SIFT-M) and global matching are used to initialize the candidate points. Next, Genetic Algorithm (GA) is utilized to exclude the mismatch pairs and find the best set of corresponding points. The objective function is calculated by the similarity of Delaunay graphs generated by the selected points from candidates. Compared with several other algorithms, the proposed algorithm is demonstrated to achieve high accuracy and robustness for various real remote sensing images even with significant gray-scale differences.