A Split-Based Approach to Unsupervised Change Detection in Large-Size Multitemporal Images: Application to Tsunami-Damage Assessment

This paper presents a split-based approach (SBA) to automatic and unsupervised change detection in large-size multitemporal remote-sensing images. Unlike standard methods that are presented in the literature, the proposed approach can detect in a consistent and reliable way changes in images of large size also when the extension of the changed area is small (and, therefore, the prior probability of the class of changed pixels is very small). The method is based on the following: 1) a split of the large-size image into subimages; 2) an adaptive analysis of each subimage; and 3) an automatic split-based threshold-selection procedure. This general approach is used for defining a system for damage assessment in multitemporal synthetic aperture radar (SAR) images. The proposed system has been developed to properly identify different levels of damages that are induced by tsunamis along coastal areas. Experimental results that are obtained on multitemporal RADARSAT-1 SAR images of the Sumatra Island, Indonesia, confirm the effectiveness of both the proposed SBA and the presented system for tsunami-damage assessment