VFMDet: A Visual Filtering Mechanism-Based SAR Ship Detection Model for Complex Environment

In the field of synthetic aperture radar (SAR) image analysis, the main challenges include the difficulty of eliminating the effects of ambient noise, the variability of objects, and the distinction between targets and nontargets. To address these issues, we propose a novel detection model, VFMDet, based on brain-inspired visual filtering mechanism. The model comprises two primary components: a brain-inspired filtering module and a SAR ship detection module. The former contains a bottom-up filtering module responsible for low-level feature extraction, an up-bottom filtering module responsible for high-level feature extraction, and a brain-inspired fusion module responsible for fusing the original image with the filtered feature map. In the SAR ship detection process, to accurately regress the orientation of the ship, we introduce a five-point coding scheme in polar coordinate system. Meanwhile, we introduce a Gaussian heatmap strategy (GHS) that utilizes limited covariance and a Gaussian heatmap loss to solve the problem caused by large-scale variation and dense arrangement of ship target. Finally, we design a multitask loss to help the model complete the end-to-end training. We conducted experiments on the rotating SAR ship detection dataset (RSSDD) and the rotating ship detection dataset (RSDD), and the mean average precision (mAP) improved by 0.27% and 0.89%, respectively, compared with the detection results of the best SAR image rotating object detection model.

I. Introduction

Synthetic aperture radar (SAR) is an active observation system capable of continuously monitoring both land and coastal areas. It processes radar signals to generate SAR images, which have been applied in a variety of applications. Despite advances in SAR image technology, challenges remain in the detection of ships within SAR images [1], [2], specifically. 1)

SAR image has complex background and variable environment, and the noise in the image is difficult to eliminate.

2)

Ship targets in SAR image are densely arranged [3], which makes it challenging to distinguish between them and accurately outline their boundaries.

3)

Ship targets vary greatly in scale in SAR images, posing a significant challenge to the adaptability of models.