FGOM-RTDETR: Far-Shore-Guided Object-Focusing Multiscale Network With Real-Time Detection Transformer for Infrared Ship Target Detection
文献类型：期刊论文
| 作者 | Wang, Haobin1,2,3; Tang, Bo-Hui1,2,3,4; Cai, Fangliang1,2,3; Li, Menghua1,2,3; Zhang, Zheng1,2,3; Fan, Dong1,2,3 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2026 |
| 卷号 | 64页码:5002916 |
| 关键词 | Marine vehicles Feature extraction Accuracy Real-time systems Monitoring Remote sensing Object detection Laboratories Deep learning Transformers Coordinate attention golden feature pyramid network (CAGoldFPN) far-shore-guided object-focusing multiscale network with real-time detection Transformer (FGOM-RTDETR) feature reparameterization (FRep) infrared ship detection multiscale feature fusion multiscale stacked network (MuSSNet) RTDETR |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2026.3663601 |
| 产权排序 | 4 |
| 文献子类 | Article |
| 英文摘要 | Infrared ship detection plays a critical role in both civilian and military applications, including tracking, collision avoidance, and maritime security. However, challenges such as low image resolution and complex backgrounds hinder detection accuracy. This study proposes a novel detection algorithm, far-shore-guided object-focusing multiscale network with real-time detection Transformer (FGOM-RTDETR), which integrates multiscale local and global features. Built upon the RT-DETR framework, our method introduces a feature grouping module (FGOM) to enhance multiscale representation. FGOM consists of three key components: the feature reparameterization (FRep) module, the coordinate attention golden feature pyramid network (CAGoldFPN), and the multiscale stacked network (MuSSNet). The FRep module addresses the loss of channel information caused by the small size of thermal infrared (TIR) ship targets and the complexity of background features. The CAGoldFPN module improves multiscale feature fusion, while MuSSNet mitigates issues of high target similarity and the susceptibility of small targets to being overlooked. Experimental results show that, compared with the baseline RT-DETR model, FGOM-RTDETR achieves notable performance gains: precision improves from 0.921 to 0.942, mAP50 rises from 0.938 to 0.958, and recall increases from 0.923 to 0.934. These results demonstrate that FGOM-RTDETR delivers superior detection performance for infrared ship targets. |
| URL标识 | 查看原文 |
| WOS关键词 | FEATURES ; CNN |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001708161700033 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221247]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Tang, Bo-Hui |
| 作者单位 | 1.Kunming Univ Sci & Technol, Fac Land Resource Engn, Kunming 650093, Peoples R China; 2.Yunnan Key Lab Quantitat Remote Sensing, Kunming 650093, Peoples R China; 3.Yunnan Int Joint Lab Integrated SkyGround Intellig, Kunming 650093, Peoples R China; 4.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Haobin,Tang, Bo-Hui,Cai, Fangliang,et al. FGOM-RTDETR: Far-Shore-Guided Object-Focusing Multiscale Network With Real-Time Detection Transformer for Infrared Ship Target Detection[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2026,64:5002916. |
| APA | Wang, Haobin,Tang, Bo-Hui,Cai, Fangliang,Li, Menghua,Zhang, Zheng,&Fan, Dong.(2026).FGOM-RTDETR: Far-Shore-Guided Object-Focusing Multiscale Network With Real-Time Detection Transformer for Infrared Ship Target Detection.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,64,5002916. |
| MLA | Wang, Haobin,et al."FGOM-RTDETR: Far-Shore-Guided Object-Focusing Multiscale Network With Real-Time Detection Transformer for Infrared Ship Target Detection".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 64(2026):5002916. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。