A Deep Learning-Based SAR Ship Detection

Abstract

In recent years, with the in-depth development of remote sensing technology, ship detection based on remote sensing images has become an important task for coastal countries. Synthetic aperture radar (SAR) is one of the most important active imaging sensors in remote sensing since it is not affected by the clouds, day and night. However, ship targets in SAR images have problems such as unclear contour information, complex background, and strong scattering. Ship detection algorithms based on the convolutional neural networks achieved good results, albeit with many missed and false detections. You only look once (YOLO) is a single-stage target detection algorithm, which has the characteristics of fast speed and high accuracy. In this paper, a YOLOv7-based ship scheme for SAR images is proposed. Numerical experiments on the high-resolution SAR images dataset (HRSID) and SAR ship detection dataset (SSDD) prove the effectiveness of the method, showing that the method can increase the speed without reducing the detection accuracy and recall. In addition, the experimental results also demonstrate the robustness of the model and the ability to detect ship targets in complex marine environment.