A matching method for low SNR SAR images
Qingqing Li, Di Zhang, Zhikai Yu, Panhu Li, Jiaqi Li · 2021 2nd China International SAR Symposium (CISS) · 2021
Aiming at the requirement of high accuracy of synthetic aperture radar (SAR) image matching in scene matching guidance technology, and the problem that traditional matching method is not suitable for low signal to noise ratio (SNR) SAR image, a new SAR image matching method based on Scale-invariant feature transform (SIFT) feature is proposed. Firstly, the enhanced Lee filter is used to pre-process the image, and then the ROEWA is used to assign the main direction and construct the feature vector for SIFT feature points. Finally, the matching result is obtained according to the bidirectional Euclidean distance. The reliability and robustness of the proposed method are verified by comparative simulation.