EDGE FEATURE MATCHING OF REMOTE SENSING IMAGES VIA PARAMETER DECOMPOSITION OF AFFINE TRANSFORMATION MODEL

Abstract. An approach of the edge feature matching of remote sensing images based on parameter decomposition of the affine transformation model is presented. First, the adaptability of affine transformation model used in image matching is analyzed, and parameters of the affine transformation model are decomposed. Second, the sum of squared gradient (SSG) similarity is constructed based on the edge feature in the images, and the parameters of the affine transformation model between the images are solved with the Genetic Algorithms (GA) which is used to obtain the global optimum solution of the similarity. Finally, the performance of the approach is analyzed in theory and validated with remote sensing image matching experiments.