Change Detection for Earthquake-damaged and Reconstructed Urban Area on Sar Images

Considering the purpose of change detection task, this paper extracts the urban area from the filtered co-registered original image with the method based on variogram first. Then, it takes advantage of generalized Gamma model to fit SAR images, in order to gain the characteristics information, such as radiation value, local texture, etc, because of the clutter statistical characteristics of SAR image. Moreover, the degree of evolution between the statistical characteristics of multi temporal SAR image is measured by the definition of Kullback–Leibler Divergence in information theory. Afterwards, KS test has been applied into the evaluation of fitting function for the difference map captured in the former step, which help select the best fitting function automatically for the model-based KI threshold segmentation. Experiment is carried on the multi-temporal SAR images for Dujiangyan area, Sichuan province, acquired by TerraSAR-X and Chinese airborne X-band SAR image. Experimental results show that the method proposed in this paper not only avoids large number of false alarms generated from the area which have no variance in texture, but differ in mean value, but also effectively detects the regions ignored by traditional methods, which have no variance in mean value, but differ in texture.