A fast line-scanning-based detection algorithm for real-time SAR ship detection

Synthetic aperture radar (SAR) provides a powerful surveillance capability allowing the observation of target, independently from weather effects and from the day and night cycle. Unfortunately, the automatic interpretation of SAR images is often complicated and time consuming. In support of real-time vessel monitoring, a fast line-scanning detector designed for detecting ships from SAR imagery is proposed in this paper. The detector does not require any prior knowledge about ships and background observation. It uses a novel local gray-level gathering degree algorithm to detect potential targets and then a complementary filtering scheme to reject false alarms. The performance analysis over real SAR images confirms that the proposed detector works well in various circumstances with high detection rate, fast detection speed and perfect shape preservation.