Unsupervised SAR Image Change Detection Based on SIFT Keypoints and Region Information

 Unsupervised SAR Image Change Detection Based on SIFT Keypoints and Region Information

 A new unsupervised distributionfree change detection method for synthetic aperture radar (SAR) images based on scale-invariant feature transform (SIFT) keypoints and region information. Since the SIFT can detect bloblike structures in an image and be insensitive to noise, we first extract noise-robust SIFT keypoints in the log-ratio image to reduce the detection range. Then, in order to obtain accurate changed regions, rather than directly obtaining the change-detection map from the difference image as in some traditional change detection methods