MULTISCALE SEGMENTATION OF OIL SLICK IN SAR IMAGES BASED ON MORPHOLOGICAL PYRAMID

We propose a new approach based on the Marangoni theory, particularly a dampening of the wave spectra energy. The observation is decomposed into multiscale analysis using a pseudo morphological pyramid, named here as a alternating contextual filter, to improve the detection of local variations of the wave spectrum. The morphological thick gradient contrast is first performed with a varying structuring element. The filtering is balanced by the low pass image. The residue image gives information about the surface energy spectrum in relation to the dispersion equation. Then images generated are merged with the help of fuzzy c-mean algorithm to achieve the segmentation process. The method is tested on ERS2 SAR and ENVISAT ASAR Images. The obtained results are promising and show an improvement of the oil slick detection.