An Algorithm Based on SIFT Matching Combined SR Saliency Detection with Frequency Segmentation for Remote Sensing Images

A fast remote sensing scene matching method, taking airports, oil depots, harbors and so on as research objects, is proposed in this article which is based on the SR saliency detection and frequency segmentation. Saliency detection is used to determine the candidate region where the target may exist to reduce the searching range effectively. And then, frequency segmentation is used to eliminate the frequency component except the frequency of the target to reduce the redundant information, thereby saving the computation of SIFT feature extraction and matching. A variety of experiments under different interference factors are carried out in this paper. Experimental results show that the fast matching algorithm proposed in this paper can not only maintain the validity of SIFT features under the condition of rotation, scale, illumination and viewpoint changes, but also shorten the matching time largely and improve the matching efficiency, laying the foundation for further practical application.