A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR Images
文献类型：期刊论文
| 作者 | Li, Qinzuo3; Xiao, Dengjun3; Shi, Fangying1,2 |
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2022 |
| 卷号 | 10页码:128562-128578 |
| 关键词 | Ship detection YOLO coordinate attention decoupled head SAR |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2022.3222364 |
| 通讯作者 | Xiao, Dengjun(xiaodj@aircas.ac.cn) |
| 英文摘要 | Currently, deep learning-based synthetic aperture radar (SAR) image ship target detection methods have been widely used in the field of SAR image ship detection. However, these methods suffer from high model complexity and poor performance when detecting small dense targets. To address this problem, this paper proposes a ship target detection algorithm based on the improved YOLO (You Only Look Once) algorithm. In addition, considering the real-time requirements and computational constraints in mobile applications, the YOLOv4 network is modified to make it more lightweight. Moreover, decoupled head and coordinate attention are introduced to preserve YOLOv4's superb detection performance as much as possible after lightweighting it. First, as the detection head of the YOLOv4 degrades the performance, this study decouples the classification and regression tasks. Second, since the channel attention mechanism ignores the spatial position information, coordinate attention is used to obtain long-range dependencies and accurate position information in the spatial domain. Moreover, the effects of the coordinate attention mechanism in different hierarchical YOLOv4 structures are analyzed. Furthermore, on the basis of the YOLOv4 backbone, another lightweight backbone is added to the model structure to improve model detection performance. Experimental results on the SAR ship detection dataset (SSDD) and the high-resolution SAR images dataset (HRSID) demonstrate that the proposed method can achieve high detection accuracy in complex scenes. The proposed lightweight model has fewer parameters compared to the original YOLOv4 structure. Furthermore, two massive SAR images are used to confirm the proposed model's migration application performance. The experimental results demonstrate that the proposed model has a strong migration ability and can be used in maritime monitoring. |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000895891300001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/188038]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Xiao, Dengjun |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China 3.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Qinzuo,Xiao, Dengjun,Shi, Fangying. A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR Images[J]. IEEE ACCESS,2022,10:128562-128578. |
| APA | Li, Qinzuo,Xiao, Dengjun,&Shi, Fangying.(2022).A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR Images.IEEE ACCESS,10,128562-128578. |
| MLA | Li, Qinzuo,et al."A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR Images".IEEE ACCESS 10(2022):128562-128578. |
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。