Data fusion approach for change detection in multi-temporal ERS-SAR images

This paper presents a new method to detect changes in multi-temporal satellite SAR images. The proposed approach consists in an extraction step-specific change measures reveal the presence of changing features-followed by a fusion step where these measures and a priori information such as geographical map are merged to detect changes. The method is applied to the detection of deforested areas in tropical rain forest of French Guiana. Results obtained with SAR images from satellites ERS 1/2 are presented at two different scales: on a macroscopic scale for the detection of zones presenting a strong deforestation probability and on a microscopic scale for a segmentation of the main deforested parcels.