A novel approach to building collapse detection from post-seismic polarimetric SAR imagery by using optimization of polarimetric contrast enhancement

A novel approach is proposed in this paper for earthquake-induced building collapse extraction based on the optimization of polarimetric contrast enhancement (OPCE). This method can realize a quick building damage assessment since the data it requires is one post-event fully polarimetric Synthetic Aperture Radar (PolSAR) image. In this method, collapsed building is recognized as clutter and the optimal polarization states are determined based on building samples with different orientation angles. For comparison, another contrast enhancement methodology, polarization synthesis technology is also utilized. We tested these two methods by using one Radasat-2 PolSAR image from Yushu earthquake in Qinghai province of China occurred in 2010. Results were validated by manual interpretation results of very high resolution (VHR) optical image. Experiments shows that collapsed building detection accuracy of OPCE method can be 66.53% in average, which is higher than that of polarization synthesis technology (42.7%) for the reason that building orientation is considered in the data processing of OPCE method.