Robust Registration of Multispectral Satellite Images Based on Structural and Geometrical Similarity

Accurate registration of multispectral satellite images is a challenging task due to the significant and nonlinear radiometric differences between these data. To address this problem, letter explores strategy geometrical similarity triplets feature points, it combined with structural in feature-based image framework. The underlying principle that similarities generally preserve across being registered. In framework, set control points (CPs) are first detected. Then, geometric CPs defined, followed by ranking operation CPs. highly ranked used estimate spatial transformation images. Finally, initial matches obtained benchmark technique refined estimated transformation. experimental results demonstrate great effectiveness proposed for registering