A COMPOUND POLARIMETRIC-TEXTURAL APPROACH FOR UNSUPERVISED CHANGE DETECTION IN MULTI-TEMPORAL FULL-POL SAR IMAGERY

Change Detection represents a relevant topic for the analysis of multi-temporal analysis of Polarimetric SAR (PolSAR) data. However, most of the CD approaches for PolSAR imagery do not take into account textural information, which can be useful for have larger performance robustness. In this work, we propose a novel approach for unsupervised change detection considering polarimetric and textural information from multi-temporal PolSAR imagery. The approach is based on the joint use of features from coherency matrix and gradient tensor and the definition of a multi-temporal distance. A binary unsupervised thresholding is used for discriminating change and no-change classes. Experimental results obtained on a multi-temporal PolSAR dataset over Los Angeles area illustrate the effectiveness of the proposed approach.