A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection
Thanks to the excellent feature representation capabilities of neural networks, target detection methods based on deep learning are now widely applied in synthetic aperture radar (SAR) ship detection. However, the multi-scale variation, small targets with complex background such as islands, sea clut...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3829 |
| _version_ | 1827618392845058048 |
|---|---|
| author | Xiuqin Li Dong Li Hongqing Liu Jun Wan Zhanye Chen Qinghua Liu |
| author_facet | Xiuqin Li Dong Li Hongqing Liu Jun Wan Zhanye Chen Qinghua Liu |
| author_sort | Xiuqin Li |
| collection | DOAJ |
| description | Thanks to the excellent feature representation capabilities of neural networks, target detection methods based on deep learning are now widely applied in synthetic aperture radar (SAR) ship detection. However, the multi-scale variation, small targets with complex background such as islands, sea clutter, and inland facilities in SAR images increase the difficulty for SAR ship detection. To increase the detection performance, in this paper, a novel deep learning network for SAR ship detection, termed as attention-guided balanced feature pyramid network (A-BFPN), is proposed to better exploit semantic and multilevel complementary features, which consists of the following two main steps. First, in order to reduce interferences from complex backgrounds, the enhanced refinement module (ERM) is developed to enable BFPN to learn the dependency features from the channel and space dimensions, respectively, which enhances the representation of ship objects. Second, the channel attention-guided fusion network (CAFN) model is designed to obtain optimized multi-scale features and reduce serious aliasing effects in hybrid feature maps. Finally, we illustrate the effectiveness of the proposed method, adopting the existing SAR Ship Detection Dataset (SSDD) and Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0). Experimental results show that the proposed method is superior to the existing algorithms, especially for multi-scale small ship targets under complex background. |
| first_indexed | 2024-03-09T10:05:56Z |
| format | Article |
| id | doaj.art-e6b16b21fbe14513af89eb3fa981f035 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:05:56Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e6b16b21fbe14513af89eb3fa981f0352023-12-01T23:08:58ZengMDPI AGRemote Sensing2072-42922022-08-011415382910.3390/rs14153829A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship DetectionXiuqin Li0Dong Li1Hongqing Liu2Jun Wan3Zhanye Chen4Qinghua Liu5School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaChongqing Key Laboratory of Mobile Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaGuangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, Guilin 541004, ChinaThanks to the excellent feature representation capabilities of neural networks, target detection methods based on deep learning are now widely applied in synthetic aperture radar (SAR) ship detection. However, the multi-scale variation, small targets with complex background such as islands, sea clutter, and inland facilities in SAR images increase the difficulty for SAR ship detection. To increase the detection performance, in this paper, a novel deep learning network for SAR ship detection, termed as attention-guided balanced feature pyramid network (A-BFPN), is proposed to better exploit semantic and multilevel complementary features, which consists of the following two main steps. First, in order to reduce interferences from complex backgrounds, the enhanced refinement module (ERM) is developed to enable BFPN to learn the dependency features from the channel and space dimensions, respectively, which enhances the representation of ship objects. Second, the channel attention-guided fusion network (CAFN) model is designed to obtain optimized multi-scale features and reduce serious aliasing effects in hybrid feature maps. Finally, we illustrate the effectiveness of the proposed method, adopting the existing SAR Ship Detection Dataset (SSDD) and Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0). Experimental results show that the proposed method is superior to the existing algorithms, especially for multi-scale small ship targets under complex background.https://www.mdpi.com/2072-4292/14/15/3829deep learningsynthetic aperture radar (SAR)balanced feature pyramid network (BFPN)ship detection |
| spellingShingle | Xiuqin Li Dong Li Hongqing Liu Jun Wan Zhanye Chen Qinghua Liu A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection Remote Sensing deep learning synthetic aperture radar (SAR) balanced feature pyramid network (BFPN) ship detection |
| title | A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection |
| title_full | A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection |
| title_fullStr | A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection |
| title_full_unstemmed | A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection |
| title_short | A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection |
| title_sort | a bfpn an attention guided balanced feature pyramid network for sar ship detection |
| topic | deep learning synthetic aperture radar (SAR) balanced feature pyramid network (BFPN) ship detection |
| url | https://www.mdpi.com/2072-4292/14/15/3829 |
| work_keys_str_mv | AT xiuqinli abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection AT dongli abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection AT hongqingliu abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection AT junwan abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection AT zhanyechen abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection AT qinghualiu abfpnanattentionguidedbalancedfeaturepyramidnetworkforsarshipdetection |