Analysis of Factor Affecting SAR Ship Target Detection

Synthetic Aperture Radar (SAR) has been widely used in military and civil fields due to its advantages of all-weather operation and all-weather imaging. With the increase of SAR image datasets, SAR ship target detection has become a research hotspot. This paper analyzes the factors that affect SAR ship target detection through several open SAR image ship datasets, and explores the impact of resolution, scene and noise on target detection using two typical target detection algorithms. The results show that the mixed resolution dataset has good generalization performance, the complex scene dataset is suitable for the detection of multiple scene types, and the strong noise data has a higher role in improving the ship detection performance in complex scenes, but has no obvious impact on the ship detection performance in simple scenes.