Multi-Temporal SAR Change Detection using Wavelet Transforms

In this paper, we propose a new method for automatic change detection in multi-temporal SAR images based on statistical wavelet subband modeling. The proposed method allows to take into account the correlation structure between subbands by modeling the wavelet coefficients through multivariate probability distributions. Two types of correlation are investigated: inter-scale dependence and inter-orientation dependence. The multivariate Gaussian distribution is used to model the interdependencies between wavelet coefficients at different orientations and scales. Kullback-Leibler similarity measures are computed and used to generate the change map. We show that the information residing in the correlation between subbands improve the accuracy of the change map and lead to better performance.