Cognitive model based method for earthquake damage assessment from high-resolution satellite images: A study following the WenChuan earthquake

Because of the availability of high-resolution satellite imagery, rapid post-earthquake damage assessment might be made over large areas, and such surveys could be of great value to rescue and post-event recovery. Urgent tasks in remote sensing require automated and robust analysis methods for image data from airborne and satellite sensor platforms. In this paper, we proposed a cognitive model based method to assessing the damage mainly from the RS data, aiming to make the understanding process to be near-real-time and the knowledge of image interpreting can be reused. The method is applied to detect the earthquake-related damage in the rural town of Xiang´e in DuJiangyan, using IKONOS and QuickBird images, acquired before and after the earthquake respectively following the WenChuan earthquake. The result of the damage inspection was compared with TTA marks obtained from field survey data, and the accuracy and usefulness of the high-resolution satellite images in damage detection were demonstrated.