Use of shadows for detection of earthquake-induced collapsed buildings in high-resolution satellite imagery

In this paper, we present a hybrid shadow-analysis approach that integrates the model- and property-based methods for detecting collapsed buildings after an earthquake using high-resolution satellite imagery. The framework of the proposed approach has four main steps. (1) The three-dimensional (3D) building model is established according to its footprint and height data stored in a geographical information system. (2) The theoretical shadow area of the building at the time that the post-seismic image was acquired is calculated. And the polygon of the ground shadow area of the building, which is called the theoretical ground shadow polygon, is extracted. (3) The theoretical ground shadow polygon is overlaid with the casting shadow area of the building, which is called the actual shadow area in the post-seismic satellite image, and the mean value of the digital number values of the post-seismic image pixels within the polygon of the theoretical shadow area is calculated. (4) The calculated mean value is compared with predefined thresholds, which are determined by the training pixels collected from the different types of shadows. On this basis, the shadows of totally collapsed, partially collapsed and uncollapsed buildings can be distinguished. A comprehensive experiment for Dujiangyan city, one of the urban areas most severely damaged in the May 2008 Wenchuan Earthquake, was conducted, and the experimental results showed the superiority of the proposed approach to the other existing ones.