Automated oil slicks detection using SAR images

Synthetic Aperture Radar (SAR) is widely used to detect and monitor oil pollution on the sea surface. As it is sensitive to surface roughness, the presence of oil film on the sea surface decreases the backscattering of this target type resulting in a dark feature patches in SAR images. In this paper, an automated method for oil slicks detection is presented. It is mainly based on the combination of automatic selection of sea SAR scenes images and fuzzy classification. Oil slicks signature is extracted trough two steps procedure. First, we performed multiscale analysis of SAR images to extract textual descriptors that characterize the image roughness. Thus, we used the Kullback-Leibler Similarity Distance (KLD) and Differential Morphological Profile (PMD). Second, the multi-scales features resulting from KLD and PMD are integrated into fuzzy clustering system to extract the dark spots in radar images. In this work three fuzzy algorithms are tested namely FCM (Fuzzy C-Means), GK (Gustafsson and kessel) and WFCM (Weighted FCM). The proposed method is applied to European Remote Sensing (ERS) images acquired on Algerian coats and it yields an encouraging automatic detection