SAR change detection techniques have proved to be a precious
tool for damaged areas rapid mapping especially after
natural disasters. In case of similar acquisition modalities,
general framework uses SAR images local statistics to extract
efficient change measures. Recent works propose a new technique
adapted to different sensors, acquisition modalities or
climatic conditions. This technique is based on projecting the
statistics of the first image to the acquisition conditions of the
second image using the copula theory modelled by a quantile
regression. However, this is done without considering the
SAR texture behaviour which follows a Rayleigh distribution.
In this paper, we present a new method adapted to heterogeneous
SAR images. A new copula has been constructed
starting fromtwo marginal Rayleigh distributions. Then usual
Kullback Leibler (KL) based comparisons are used to validate
the proposedmethod and shows its suitability to SAR images.
Different climatic conditions ENVISAT SAR images are used
to highlight the performances of this technique.