A correlation change detection method integrating PCA and multi-texture features of SAR image for building damage detection

Abstract

Synthetic Aperture Radar (SAR) data are used to map affected urban areas after an earthquake generally exploiting change detection techniques. In this paper, a novel change detection approach is proposed for multitemporal (SAR) images. The approach is based on two different parts, which are constructed through principal components (PCs) of multiple textural features and correlation analysis image, respectively. In the extraction of the PCs of texture, the principal component analysis technique is used to separate irrelevant and noisy elements. Then, correlation change detection (CCD) is carried out to detect the changes associated with the building collapse. Considering the earthquake that hit L’Aquila city (Italy) on 6 April 2009, the effectiveness of the proposed method is proved by the experiment results obtained on real SAR images data sets collected before and after the seismic event.