Building Damage Detection from Post-earthquake

The collapsed buildings due to earthquake were detected from post-event aerial images using watershed segmentation algorithm. The objective was to detect the collapsed buildings based on the analysis of the cast shadows. The building boundaries were available and stored in a GIS as vector polygons. The building polygons were utilized to perform assessments in a building specific manner. The approach was implemented in a selected urban area of Golcuk. The shadows cast by the buildings were detected using the watershed segmentation algorithm. The shadow casting edges of the buildings were identified and a buffer zone was generated for each building polygon along these edges. Then, the initial points falling within the buffer zone were selected from both inside and outside the building polygons to start the watershed segmentation. The shadow regions were detected using a watershed segmentation algorithm. This was followed by measuring the agreement between the shadow producing edges of the buildings and the corresponding shadows based on the percentage of the shadow pixels. Of the 284 buildings analyzed, 229 were correctly labeled as collapsed or un-collapsed providing an overall accuracy of 80%. The results prove that the collapsed buildings caused by the earthquake can be successfully detected from post-event aerial images.