Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion
Due to the unique imaging mechanism of SAR, targets in SAR images present complex scattering characteristics. As a result, intelligent target detection in SAR images has been facing many challenges, which mainly lie in the insufficient exploitation of target characteristics, inefficient characteriza...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/112 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548976410591232 |
|---|---|
| author | Qiaoyu Liu Ziqi Ye Chenxiang Zhu Dongxu Ouyang Dandan Gu Haipeng Wang |
| author_facet | Qiaoyu Liu Ziqi Ye Chenxiang Zhu Dongxu Ouyang Dandan Gu Haipeng Wang |
| author_sort | Qiaoyu Liu |
| collection | DOAJ |
| description | Due to the unique imaging mechanism of SAR, targets in SAR images present complex scattering characteristics. As a result, intelligent target detection in SAR images has been facing many challenges, which mainly lie in the insufficient exploitation of target characteristics, inefficient characterization of scattering features, and inadequate reliability of decision models. In this respect, we propose an intelligent target detection method based on multi-level fusion, where pixel-level, feature-level, and decision-level fusions are designed for enhancing scattering feature mining and improving the reliability of decision making. The pixel-level fusion method through the channel fusion of original images and their features after scattering feature enhancement represents an initial exploration of image fusion. Two feature-level fusion methods are conducted using respective migratable fusion blocks, namely DBAM and FDRM, presenting higher-level fusion. Decision-level fusion based on DST can not only consolidate complementary strengths in different models but also incorporate human or expert involvement in proposition for guiding effective decision making. This represents the highest-level fusion integrating results by proposition setting and statistical analysis. Experiments of different fusion methods integrating different features were conducted on typical target detection datasets. As shown in the results, the proposed method increases the mAP by 16.52%, 7.1%, and 3.19% in ship, aircraft, and vehicle target detection, demonstrating high effectiveness and robustness. |
| format | Article |
| id | doaj-art-25caf10ec6594651853c63ef4c1bc0d2 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-25caf10ec6594651853c63ef4c1bc0d22025-01-10T13:20:16ZengMDPI AGRemote Sensing2072-42922025-01-0117111210.3390/rs17010112Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level FusionQiaoyu Liu0Ziqi Ye1Chenxiang Zhu2Dongxu Ouyang3Dandan Gu4Haipeng Wang5Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaNational Key Laboratory of Scattering and Radiation, Shanghai 200438, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaDue to the unique imaging mechanism of SAR, targets in SAR images present complex scattering characteristics. As a result, intelligent target detection in SAR images has been facing many challenges, which mainly lie in the insufficient exploitation of target characteristics, inefficient characterization of scattering features, and inadequate reliability of decision models. In this respect, we propose an intelligent target detection method based on multi-level fusion, where pixel-level, feature-level, and decision-level fusions are designed for enhancing scattering feature mining and improving the reliability of decision making. The pixel-level fusion method through the channel fusion of original images and their features after scattering feature enhancement represents an initial exploration of image fusion. Two feature-level fusion methods are conducted using respective migratable fusion blocks, namely DBAM and FDRM, presenting higher-level fusion. Decision-level fusion based on DST can not only consolidate complementary strengths in different models but also incorporate human or expert involvement in proposition for guiding effective decision making. This represents the highest-level fusion integrating results by proposition setting and statistical analysis. Experiments of different fusion methods integrating different features were conducted on typical target detection datasets. As shown in the results, the proposed method increases the mAP by 16.52%, 7.1%, and 3.19% in ship, aircraft, and vehicle target detection, demonstrating high effectiveness and robustness.https://www.mdpi.com/2072-4292/17/1/112synthetic aperture radar (SAR)target detectionscattering featuresfeature fusionimage fusion |
| spellingShingle | Qiaoyu Liu Ziqi Ye Chenxiang Zhu Dongxu Ouyang Dandan Gu Haipeng Wang Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion Remote Sensing synthetic aperture radar (SAR) target detection scattering features feature fusion image fusion |
| title | Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion |
| title_full | Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion |
| title_fullStr | Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion |
| title_full_unstemmed | Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion |
| title_short | Intelligent Target Detection in Synthetic Aperture Radar Images Based on Multi-Level Fusion |
| title_sort | intelligent target detection in synthetic aperture radar images based on multi level fusion |
| topic | synthetic aperture radar (SAR) target detection scattering features feature fusion image fusion |
| url | https://www.mdpi.com/2072-4292/17/1/112 |
| work_keys_str_mv | AT qiaoyuliu intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion AT ziqiye intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion AT chenxiangzhu intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion AT dongxuouyang intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion AT dandangu intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion AT haipengwang intelligenttargetdetectioninsyntheticapertureradarimagesbasedonmultilevelfusion |