Chinese Journal of Ship Research, Volume. 19, Issue 6, 284(2024)
Research on small target ship recognition based on feature fusion method and hybrid attention model
Figures & Tables(21)
![[in Chinese]](/Images/icon/loading.gif){kind=icon}
Table 1. Ship target classification by size
View tableView in ArticleTable 1. Ship target classification by size
目标面积 （像素×像素） 目标分类 ≥200×200 大船舶目标 200×200～100×100 中等船舶目标 100×100～50×50 小船舶目标 50×50～20×20 微小船舶目标 20×20～10×10 极小船舶目标
Table 2. AP comparison of different improvement processes in experiment
View tableView in ArticleTable 2. AP comparison of different improvement processes in experiment
目标类型 YOLOv5 YOLOv5 图像增强 YOLOv5 图像增强 运动特征融合 YOLOv5 图像增强 运动特征融合 混合注意力 大船舶 0.980 0.989 0.992 0.997 中等船舶 0.938 0.941 0.953 0.964 小船舶 0.713 0.757 0.798 0.874 微小船舶 0.331 0.359 0.545 0.708 极小船舶 0.028 0.032 0.287 0.438
Tools
Get Citation
Copy Citation Text
Ronghui YAN, Qian GUO, Ming LEI, Yanxiang CAI, Jianfeng YANG. Research on small target ship recognition based on feature fusion method and hybrid attention model[J]. Chinese Journal of Ship Research, 2024, 19(6): 284
Paper Information
Category: Weapon, Electronic and Information System
Received: Aug. 2, 2023
Accepted: --
Published Online: Mar. 14, 2025
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20