Abstract
Multi-temporal satellite imagery is now available at sub-metre accuracy and has been found to be very useful for performing rapid damage assessment on human settlement areas affected by large-scale disasters. In this article, a method of formulating structural damage detection measures based on pre- and post-disaster satellite images is proposed. To validate the proposed damage measures, building-based structural damage assessment is conducted. First, their effectiveness in representing multilevel structural damage is demonstrated using synthetic patterns of building damage. Second, the damage classification accuracy is evaluated by means of a pattern classification approach applied to a pair of bi-temporal satellite images, wherein earthquake damage to hundreds of buildings is assessed. The article concludes that the proposed damage detection measures, which are conceptually simple and computationally efficient, outperform traditional measures, such as linear correlation coefficients.
Acknowledgements
The Holmes Fellowship Foundation, a graduate fellowship from the California Institute of Information and Telecommunication Technology, the Interdisciplinary Collaboratories fund and NSF grant (CMMI-0729357) each provided partial support for this work. Digital satellite images were obtained from DigitalGlobe. This support is gratefully acknowledged. Special thanks are due to Miss Robyn Sue Jan Chung for her help in visually performing the damage classification. Opinions in this article are those of the authors and in no way reflect those of the sponsoring agencies.