SAR Ship Instance Segmentation With Dynamic Key Points Information Enhancement

Abstract

There are several unresolved issues in the field of ship instance segmentation in synthetic aperture radar (SAR) images. Firstly, in inshore dense ship area, the problems of missed detections and mask overlap frequently occur. Secondly, in inshore scenes, false alarms occur due to strong clutter interference. In order to address these issues, we propose a novel ship instance segmentation network based on dynamic key points information enhancement. In the detection branch of the network, a dynamic key points module (DKPM) is designed to incorporate the target's geometric information into the parameters of the dynamic mask head using implicit encoding technique. Additionally, we introduce a dynamic key points encoding branch, which encodes the target's strong scattering regions as dynamic key points. It strengthens the network's ability to learn the correspondence between local regions with strong scattering and overall ship targets, effectively mitigating mask overlap issues. Moreover, it enhances the discriminative ability of network between ship targets and clutter interference, leading to a reduction in false alarm rates. To further enhance the dynamic key points information, a instance-wise attention map module (IAMM) is designed, which decodes the key points during the mask prediction period, generating instance-wise attention maps based on two-dimensional Gaussian distribution. This module further enhances the sensibility of network to specific instances. Simulation experiments conducted on the Polygon Segmentation SAR Ship Detection Dataset (PSeg-SSDD) and High Resolution SAR Images Dataset (HRSID) demonstrate the superiority of our proposed method over other state-of-the-art methods in inshore and offshore scenes.