Unsupervised spatial self-similarity difference-based change detection method for multi-source heterogeneous images

Multi-source heterogeneous change detection has been widely used in dynamic disaster monitoring, land cover updating, etc. Various methods have been proposed to make heterogeneous data comparable. However, heterogeneous images are difficult to compare directly and may be affected by noise. Most existing methods obtain change information through mapping and regression, lacking the utilisation of image spatial information and a comprehensive portrayal of the changes, which may affect change detection results. To address these challenges, we propose an unsupervised spatial self-similarity difference-based change detection (USSD) method for multi-source heterogeneous images to evaluate the similarity of spatial relationships in heterogeneous images. First, the images are divided into image blocks to construct spatial self-difference images between individual image blocks aiming to make the data comparable. Second, the change information is portrayed in terms of both the magnitude differences and similarity differences to obtain a more comprehensive spatial self-difference change magnitude map. Then, the spatial neighbourhood information of the spatial self-difference change magnitude map is considered to avoid noise. Experimental results on six open datasets indicate that the overall accuracy of the USSD method was approximately 85%–95%. This method improves the change magnitude map discrimination, better detects the change region, and avoids noise in synthetic aperture radar images.