Construction and Application of a Post-Quake House Damage Model Based on Multiscale Self-Adaptive Fusion of Spectral Textures Images

In the disaster research field, extraction of post-disaster damaged house building information plays a critical role in post-disaster emergency rescue and disaster-induced damage assessment. In this study, we propose a method of automatically extracting house damage information from post-quake high-resolution optical remote-sensing imagery through multiscale fusion of spectral texture features. This is achieved in three steps. First, the texture features and spectral features of images are enhanced at the pixel level; then, the resulted feature images are fused at the feature level and the fused feature images are superpixel-segmented; finally, a post-quake house damage index model is constructed. The results show an overall accuracy of 76.75%, 75.35%, and 83.25% for the three different types of imagery studied. This suggests that our algorithm is applicable to extracting damage information from multisource remote sensing data and can provide useful guidance for post-disaster rescue and assessment based on regional house damage conditions.