SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images
Aircraft detection in synthetic aperture radar (SAR) images is a challenging task due to the discreteness of aircraft scattering characteristics, the diversity of aircraft size, and the interference of complex backgrounds. To address these problems, we propose a novel scattering feature relation enh...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2076 |
| _version_ | 1827671660362203136 |
|---|---|
| author | Peng Zhang Hao Xu Tian Tian Peng Gao Jinwen Tian |
| author_facet | Peng Zhang Hao Xu Tian Tian Peng Gao Jinwen Tian |
| author_sort | Peng Zhang |
| collection | DOAJ |
| description | Aircraft detection in synthetic aperture radar (SAR) images is a challenging task due to the discreteness of aircraft scattering characteristics, the diversity of aircraft size, and the interference of complex backgrounds. To address these problems, we propose a novel scattering feature relation enhancement network (SFRE-Net) in this paper. Firstly, a cascade transformer block (TRsB) structure is adopted to improve the integrity of aircraft detection results by modeling the correlation between feature points. Secondly, a feature-adaptive fusion pyramid structure (FAFP) is proposed to aggregate features of different levels and scales, enable the network to autonomously extract useful semantic information, and improve the multi-scale representation ability of the network. Thirdly, a context attention-enhancement module (CAEM) is designed to improve the positioning accuracy in complex backgrounds. Considering the discreteness of scattering characteristics, the module uses a dilated convolution pyramid structure to improve the receptive field and then captures the position of the aircraft target through the coordinate attention mechanism. Experiments on the Gaofen-3 dataset demonstrate the effectiveness of SFRE-Net with a precision rate of 94.4% and a recall rate of 94.5%. |
| first_indexed | 2024-03-10T03:44:59Z |
| format | Article |
| id | doaj.art-7c9a1aa600074b56a91fdee2109a335c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:44:59Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7c9a1aa600074b56a91fdee2109a335c2023-11-23T09:10:12ZengMDPI AGRemote Sensing2072-42922022-04-01149207610.3390/rs14092076SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR ImagesPeng Zhang0Hao Xu1Tian Tian2Peng Gao3Jinwen Tian4School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaAircraft detection in synthetic aperture radar (SAR) images is a challenging task due to the discreteness of aircraft scattering characteristics, the diversity of aircraft size, and the interference of complex backgrounds. To address these problems, we propose a novel scattering feature relation enhancement network (SFRE-Net) in this paper. Firstly, a cascade transformer block (TRsB) structure is adopted to improve the integrity of aircraft detection results by modeling the correlation between feature points. Secondly, a feature-adaptive fusion pyramid structure (FAFP) is proposed to aggregate features of different levels and scales, enable the network to autonomously extract useful semantic information, and improve the multi-scale representation ability of the network. Thirdly, a context attention-enhancement module (CAEM) is designed to improve the positioning accuracy in complex backgrounds. Considering the discreteness of scattering characteristics, the module uses a dilated convolution pyramid structure to improve the receptive field and then captures the position of the aircraft target through the coordinate attention mechanism. Experiments on the Gaofen-3 dataset demonstrate the effectiveness of SFRE-Net with a precision rate of 94.4% and a recall rate of 94.5%.https://www.mdpi.com/2072-4292/14/9/2076synthetic aperture radaraircraft detectionadaptive feature fusioncontextual coordinate attentionscattering point relation |
| spellingShingle | Peng Zhang Hao Xu Tian Tian Peng Gao Jinwen Tian SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images Remote Sensing synthetic aperture radar aircraft detection adaptive feature fusion contextual coordinate attention scattering point relation |
| title | SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images |
| title_full | SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images |
| title_fullStr | SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images |
| title_full_unstemmed | SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images |
| title_short | SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images |
| title_sort | sfre net scattering feature relation enhancement network for aircraft detection in sar images |
| topic | synthetic aperture radar aircraft detection adaptive feature fusion contextual coordinate attention scattering point relation |
| url | https://www.mdpi.com/2072-4292/14/9/2076 |
| work_keys_str_mv | AT pengzhang sfrenetscatteringfeaturerelationenhancementnetworkforaircraftdetectioninsarimages AT haoxu sfrenetscatteringfeaturerelationenhancementnetworkforaircraftdetectioninsarimages AT tiantian sfrenetscatteringfeaturerelationenhancementnetworkforaircraftdetectioninsarimages AT penggao sfrenetscatteringfeaturerelationenhancementnetworkforaircraftdetectioninsarimages AT jinwentian sfrenetscatteringfeaturerelationenhancementnetworkforaircraftdetectioninsarimages |