A Robust Anchor-Free Detection Method for SAR Ship Targets With Lightweight CNN

To address the challenges of compromised detection accuracy caused by near-shore clutter in synthetic aperture radar (SAR) ship detection and the limited deployability of complex algorithms on embedded systems, this article proposes Lightweight-YOLOX (L-YOLOX), a lightweight SAR target detection algorithm optimized for terminal devices. First, we devise a new feature extraction module based on the MobileNetV3 block to reduce the parameters of traditional YOLOX while strengthening feature representation. Additionally, we incorporate a cross-channel local connection structure to construct an efficient lightweight feature extraction backbone, which is beneficial to improving the network’s ability to fuse SAR ship target information. Next, we develop a multiscale detection block by using a feature pyramid architecture and dilated convolution to improve the network’s multiscale detection performance. Finally, we integrate a lightweight convolutional attention mechanism into YOLOX’s Neck structure to enhance the expression of important target detail information and propose the Alpha-AIoU loss function to optimize the gradient propagation process and the network’s weight update. Ablation experimental results on the SAR Ship Detection Dataset (SSDD) dataset show that our network achieves an average precision (AP) of 90.8%, outperforming Baseline YOLOX with a 70.1% reduction in parameters and a 46.9% decrease in computational cost. Our network also demonstrates a marked enhancement in robustness, validating the effectiveness of our innovations. Some comparative experiments with other state-of-the-art algorithms on SSDD and High High Resolution SAR Images Dataset (HRSID) further confirm the advantages of our network in terms of SAR image lightweight detection performance and generalization capacity.