Fast and Automatic Ship Detection for SAR Imagery Based on Multiscale Contrast Measure

Ship detection from synthetic aperture radar (SAR) imagery is an important and challenging task. An urgent problem is to improve the detection speed on the condition of the high detection rate. In this letter, a fast and automatic detection method inspired by the multiscale patch-based contrast measure (MPCM) algorithm is proposed. The method can quickly lock some potential target pixels and guide ship detection on them, which avoids the unnecessary and exhaustive search. Experiments on real SAR images demonstrate that the proposed method works well in various noise backgrounds with a high probability of detection (POD), low false alarm rate (FAR), and fast detection speed.