Object oriented change detection of buildings after the Indian ocean tsunami disaster

Following a disaster, change detection is a prerequisite for quick assessment of damage. To assess the severity of devastation, most damage assessments focus on the destruction of man-made objects, particularly buildings. Despite the rich literature on building extraction, most existing approaches misdetect small-size buildings. In this work, we present a robust rectangular building detection that can discover both small-size buildings in residential areas and large-size buildings in industrial areas with 75 percent accuracy. We also propose an object-based change detection that is flexible for disaster cases in which the pre-disaster and post-disaster images may not be captured with the same resolution. According to our results, we conclude that, in conjunction with accurate inputs from the building detection, our change detection can discover real changes.