Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery

TLDR

Synthetic aperture radar imagery, independent of daylight and weather, is widely used for ship detection, yet ships appear at multiple scales and conventional methods rely heavily on sea‑clutter models, limiting robustness. This study proposes using the RetinaNet deep‑learning object detector to overcome these limitations. The approach employs a feature‑pyramid network to extract multi‑scale features, applies focal loss to mitigate class imbalance, and is evaluated on 86 Gaofen‑3 scenes across four resolutions plus additional Cosmo‑SkyMed imagery. Results show that RetinaNet achieves efficient multi‑scale ship detection with high accuracy, attaining over 96 % mean average precision and outperforming other detectors, confirming its effectiveness.

Abstract

Independent of daylight and weather conditions, synthetic aperture radar (SAR) imagery is widely applied to detect ships in marine surveillance. The shapes of ships are multi-scale in SAR imagery due to multi-resolution imaging modes and their various shapes. Conventional ship detection methods are highly dependent on the statistical models of sea clutter or the extracted features, and their robustness need to be strengthened. Being an automatic learning representation, the RetinaNet object detector, one kind of deep learning model, is proposed to crack this obstacle. Firstly, feature pyramid networks (FPN) are used to extract multi-scale features for both ship classification and location. Then, focal loss is used to address the class imbalance and to increase the importance of the hard examples during training. There are 86 scenes of Chinese Gaofen-3 Imagery at four resolutions, i.e., 3 m, 5 m, 8 m, and 10 m, used to evaluate our approach. Two Gaofen-3 images and one Constellation of Small Satellite for Mediterranean basin Observation (Cosmo-SkyMed) image are used to evaluate the robustness. The experimental results reveal that (1) RetinaNet not only can efficiently detect multi-scale ships but also has a high detection accuracy; (2) compared with other object detectors, RetinaNet achieves more than a 96% mean average precision (mAP). These results demonstrate the effectiveness of our proposed method.