Automated ship detection on Synthetic Aperture Radar (SAR) images from ocean wakes

Abstract

In this study, we employ image processing techniques to detect ships from ocean wakes as seen on Synthetic Aperture Radar (SAR) images of the West Philippine Sea. Confronted with the inherent noise in SAR images, we employ contrast enhancement to highlight line features and apply the Radon transform to pinpoint ocean wakes trailing behind ships. Our method achieves a precision of 76% and a recall of 81%, despite the challenges posed by noise. These results demonstrate the potential of our approach in effectively identifying maritime vessels, paving the way for more accurate and reliable maritime surveillance in this strategically significant region.