Earthquake Damage Assessment of Buildings Using Pre-event and Post-event Imagery

Abstract The serious natural disasters such as flood and earthquake result in great loss to human every year. The natural disasters cannot be eliminated completely, but it can be minimize the sufferings through proper awareness of the likely disasters and its impact by developing a suitable warning system, disaster preparedness and management of disasters and assessment. Rapid damage assessment after natural disasters (e.g., earthquakes) and violent conflicts (e.g., war-related destruction) is crucial for initiating effective emergency response actions. For rapid impact assessment, remote sensing data sets can provide important information since they can map the extended areas quickly and in an uncensored manner. In this project, a novel method is introduced, that detects buildings destroyed in an earthquake using pre-event and post-event detected imagery. The method operates at the level of individual buildings and assumes that they have a rectangular footprint and are isolated. Several procedures were followed and finally features are matched. The similarity between the predicted image and the actual image is analyzed. If the similarity is high, the building is likely to be still intact, whereas a low similarity indicates that the building is destroyed. 1