Algorithms for oil spill detection in radarsat and ENVISAT SAR images

We present algorithms for detection of oil spills in Radarsat and ENVISAT SAR images. The algorithms are trained on 60-100 images from each sensor from European water (mainly the North Sea and the Baltic Sea). Results show that they perform very well when applied to benchmark data sets, but in some cases additional information is needed to discriminate between oil slicks and algae, particularly in the Baltic Sea