Building-damage detection using pre- and post-seismic high-resolution satellite stereo imagery: A case study of the May 2008 Wenchuan earthquake

To address the disadvantage of traditional methods providing only two-dimensional (2D) damage change of the collapsed buildings, this paper presents an approach for the detection of the buildings that have collapsed in an earthquake based on 3D geometric changes, particularly height change of the buildings, using preand post-seismic IKONOS stereo image pairs. One of the critical issues – the accuracy of the 3D ground point determination from high-resolution satellite imagery (HRSI) – is first addressed employing a bias-compensation model based on the rational function polynomial coefficient bundle adjustment. With the refined 3D ground coordinates, two ways of detecting the collapsed buildings are proposed: (1) detection of an individual collapsed building by comparing the height differences at the corner points of the building calculated from the preand post-seismic IKONOS stereo pairs and (2) determination of the region of collapsed buildings by calculating the difference between the preand post-seismic digital elevation models (DEMs) generated again from the preand post-seismic stereo images. At the same time, a pre-seismic DEM based on a topographical map is generated for detection comparison in the study. The experiment results for Dujiangyan using two IKONOS stereo pairs before and after the Wenchuan earthquake demonstrated the following. (1) Accuracy of better than 1.1 m in planimetry and 1.5 m in height can be achieved from the preand post-seismic IKONOS stereo image pairs using the affine bias compensation model. This accuracy guarantees the feasibility of detecting the 3D geometric changes of the earthquake-induced building collapses from preand post-seismic HRSI stereo images. (2) Using the refined 3D coordinates of the ground points computed from the preand post-seismic IKONOS stereo pairs, the status (i.e., totally collapsed, partially collapsed or not collapsed) and the number of collapsed storeys can be estimated for an individual building being assessed. (3) The region of collapsed buildings can be determined by differencing the preand post-seismic DEMs created from the preand postseismic IKONOS stereo pairs. An overall accuracy of better than 90% is achieved for the detection of the collapsed buildings based on the difference DEM using the pixeland object-based assessment methods. 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) Published by Elsevier B.V. All rights reserved.