Auto Segmentation of Oil Slick in RADARSAT SAR Image Data around Rupat Island, Malacca Strait

摘要

As one of major tankers routes in Indonesia, Malacca Strait is potentially prone to oil spill pollution. SAR image data is used to detect oil slick on sea surface, because of its capability for large scale of sea monitoring, and to solve clouds covering problem in Indonesia. Oil slick is visible on SAR images as dark patches, because it decreases the radar backscatter on sea surface, which is explained by Bragg scattering theory. This project proposes the procedure for auto segmentation of oil slick in SAR image data. To reduce speckle in SAR image, we used the Bayesian approach with maximum a posteori filter with assumption that radar reflectivity and speckle noise follow Gamma distribution. This technique is compared with another adaptive filter such as Lee and Frost filter, which shows the best result on reducing speckle on whole area with the lowest ratio of mean and standard deviation, reducing the bright fleck on oil area, and showing the continuity on oil slick and sea area, which is make easier in feature extraction of oil slick. Maximum entropy technique is used for feature extraction on oil slick segmentation with assumption that only two moments are to be determined i.e. oil slick and sea area. It shows the best performance on oil slick segmentation among the others co-occurrence techniques. The area classification between oil slick and look-alike area on low wind area is done based on these result. Usually, low wind areas are located near coastal line. Therefore, coastal line is applied as boundary condition. Coastal line is detected with Canny filter using first derivative of Gaussian as edge detector and mark the position of edge where the gradient is local maximum. Finally, if areas are captured near coastal lines, these areas are marked as the possible looks-alike area.