Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
Kun Fu, Jiamei Fu, Zhirui Wang, Xian Sun
Abstract
Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this paper, a novel ship detection method based on the scattering keypoints guided network (SKG-Net) is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the issue of imaging variability. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection data set (GF3SDD). Meanwhile, the SAR ship detection data set (SSDD) is introduced to verify the generalization ability of the detector. Experimental results on these two data sets show that the proposed method achieves the state-of-the-art performance.