Building Change Detection with Time-series SAR Images

Abstract:
In this paper, we present a method to detect the spatial and temporal change of buildings from time-series synthetic aperture radar (SAR) images. The method can be used for the surveillance of building changes in short periods and supervising the construction activities by urban planning department. Changed areas are obtained using backscattering properties, coherence, and change indicator designed by coefficient of variation of multi-temporal SAR data. Furthermore, the temporal information of change can be extracted by a time index for each changed pixel. Experimental results obtained from 10 TerraSAR-X Stripmap SAR images, show the effective performance of the proposed approach.