Remote Sensing Image Registration with Multiple Features and Parameter Optimization

Abstract

Remote sensing image registration plays an essential role in agriculture and military fields, it has been widely used in agriculture and urban land use planning, military damage assessment, and environmental monitoring, etc. In this paper, we propose an image registration method based on multiple features and parameter optimization. Which has a contribution, the parameter $L$ is optimized in the local feature. And we optimize the parameter in different registration modes to promote the registration accurate. We evaluated the performances of the proposed method by a series of remote sensing images from Google Earth, and compared with five state-of-the-art methods. Where our method shows the best alignments in most scenarios.