SSS-YOLO: towards more accurate detection for small ships in SAR image

Aiming at the low detection rate and high false alarm in small ship detection in SAR images, we propose a small-scale ship detection algorithm based on convolutional neural network in this paper. First, we redesign the feature extraction network according to the characters of ship targets in SAR images. The modified network can enrich the spatial and semantics information of small ships. Then, we propose the Path Argumentation Fusion Network (PAFN) to improve the fusion of different feature maps. PAFN uses bottom-up and top-down ways to fuse more location information and semantic information. Both these two optimizations can enhance the detection for small ships. We evaluate our model based on the open SAR-Ship-Dataset and Gaofen-3 SAR images. The experiment results show that our method has excellent performance for small ship detection compared with other deep learning models. Our model improves AP by 6.5% and has higher detection efficiency compared with the baseline YOLOv3 model.

Automated summary

This paper presents a small-scale ship detection algorithm based on convolutional neural network, focusing on optimizing the detection of small ships in synthetic aperture radar images. The proposed method, evaluated on open datasets, shows superior performance compared to other deep learning models, with a 6.5% improvement in Average Precision and higher detection efficiency than the baseline YOLOv3 model.