Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/11/5/531 |
| _version_ | 1818083364719034368 |
|---|---|
| author | Yuanyuan Wang Chao Wang Hong Zhang Yingbo Dong Sisi Wei |
| author_facet | Yuanyuan Wang Chao Wang Hong Zhang Yingbo Dong Sisi Wei |
| author_sort | Yuanyuan Wang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T19:36:49Z |
| format | Article |
| id | doaj.art-e2152ef61a484992ad012fd7002a7713 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-10T19:36:49Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e2152ef61a484992ad012fd7002a77132022-12-22T01:36:07ZengMDPI AGRemote Sensing2072-42922019-03-0111553110.3390/rs11050531rs11050531Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 ImageryYuanyuan Wang0Chao Wang1Hong Zhang2Yingbo Dong3Sisi Wei4Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaIndependent 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.http://www.mdpi.com/2072-4292/11/5/531synthetic aperture radarship detectionfeature pyramid networksfocal lossGaofen-3 imagery |
| spellingShingle | Yuanyuan Wang Chao Wang Hong Zhang Yingbo Dong Sisi Wei Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery Remote Sensing synthetic aperture radar ship detection feature pyramid networks focal loss Gaofen-3 imagery |
| title | Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery |
| title_full | Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery |
| title_fullStr | Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery |
| title_full_unstemmed | Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery |
| title_short | Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery |
| title_sort | automatic ship detection based on retinanet using multi resolution gaofen 3 imagery |
| topic | synthetic aperture radar ship detection feature pyramid networks focal loss Gaofen-3 imagery |
| url | http://www.mdpi.com/2072-4292/11/5/531 |
| work_keys_str_mv | AT yuanyuanwang automaticshipdetectionbasedonretinanetusingmultiresolutiongaofen3imagery AT chaowang automaticshipdetectionbasedonretinanetusingmultiresolutiongaofen3imagery AT hongzhang automaticshipdetectionbasedonretinanetusingmultiresolutiongaofen3imagery AT yingbodong automaticshipdetectionbasedonretinanetusingmultiresolutiongaofen3imagery AT sisiwei automaticshipdetectionbasedonretinanetusingmultiresolutiongaofen3imagery |