Automatic Detection of Damaged Buildings after Earthquake Hazard by Using Remote Sensing and Information Technologies

The effects of earthquake can be devastating, it may cause significant life losses and property damage especially in urban regions. Observation of damaged buildings is vital for emergency management professionals, helping them for directing the rescue teams in short time to right location. Remote Sensing (RS) and Geographic Information Technologies (GIS) are an efficient tool for rapid monitoring of damaged buildings in urban regions following an earthquake. An approach was developed to determine automatic detection of damaged buildings through analysis of change with the aid of integrated RS and Information Technologies in the case of Van Erciş earthquake, which occurred on 23 October 2011. In this study pre and post event, Normalized Digital Surface Models (nDSM) were generated by subtracting the pre and post event Digital Elevation Model (DEM) and Digital Surface Model (DSM) for the years 2010 and 2011. The image differences between pre and post event DEM and DSM provide the pre and post event database for building patches. A change analysis was then applied to nDSM in order to detect damaged buildings. The performance of the analysis was evaluated by an accuracy assessment method using reference ground truth raster data. The results indicate that the proposed approach is encouraging for automatic detection of damaged buildings and it is a time saving method for monitoring buildings after earthquake.