Multi-Temporal SAR Image Change Detection using NSCT and K-Means Clusting

In this paper, we introduce a change detection technique for synthetic aperture radar (SAR) images based on image fusion and K-means clustering algorithm. The image fusion technique is introduced to generate a difference image using complementary information from a mean-ratio image and a log-ratio image. NSCT (Non-subsampled contourlet transform) based fusion involves an averaging operator and maximum gradient coefficient selection to fuse low-frequency and high-frequency bands to restrain the background information and enhance the information of changed regions in the fused difference image. K-means clustering algorithm is the proposed algorithm for classifying changed and unchanged regions from the fused image with performance analysis.