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

• Published in: Remote sensing (Basel, Switzerland) Vol. 11; no. 5; p. 531
• Main Authors: Wang, Yuanyuan, Wang, Chao, Zhang, Hong, Dong, Yingbo, Wei, Sisi
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.03.2019
• Subjects: Accuracy; Clutter; Datasets; Deep learning; False alarms; Feature extraction; feature pyramid networks; focal loss; Gaofen-3 imagery; Image detection; International conferences; Machine learning; Mathematical models; Methods; Neural networks; Pattern recognition; Radar imaging; Remote sensing; Robustness; Satellite constellations; Satellite imagery; Satellite observation; Satellites; Sensors; Shape recognition; ship detection; Ships; Small satellites; Statistical analysis; Statistical models; Surveillance radar; Synthetic aperture radar; Weather; Beijing China; United States > US; China; Mediterranean Area
• DOI: 10.3390/rs11050531
• ISSN: 2072-4292

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.