Automated detection of damaged buildings using aerial HDTV images

In order to seek the possibility of automated detection of damaged buildings from aerial television, the characteristics of high-definition television (HDTV) images taken after the 1995 Kobe earthquake were investigated. The relationships between the degree of building damage and the color indices and edge intensity from the aerial images were examined by image processing techniques. The characteristics of building damage were defined on the basis of hue, saturation, brightness and edge intensity. Using the threshold values of these parameters, the typical areas were classified into damaged and undamaged pixels. A texture analysis was further conducted to these pixels and damaged buildings were identified. The extracted damage distribution by the proposed method agreed well with ground truth data and visual inspection of the HDTV images