Water Column Detection Method at Impact Point Based on Improved YOLOv4 Algorithm

被引:0
作者
Shi, Jiaowei [1 ]
Sun, Shiyan [1 ]
Shi, Zhangsong [1 ]
Zheng, Chaobing [2 ]
She, Bo [1 ]
机构
[1] Naval Univ Engn, Weapon Engn Coll, Wuhan 430034, Peoples R China
[2] Wuhan Univ Sci & Technol, Sch Informat Sci & Engn, Wuhan 430081, Peoples R China
基金
中国国家自然科学基金;
关键词
YOLOv4; Hoffman line detection; DBSCAN cluster algorithm; K-means cluster algorithm; CBMA; water column detection;
D O I
10.3390/su142215329
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
For a long time, the water column at the impact point of a naval gun firing at the sea has mainly depended on manual detection methods for locating, which has problems such as low accuracy, subjectivity and inefficiency. In order to solve the above problems, this paper proposes a water column detection method based on an improved you-only-look-once version 4 (YOLOv4) algorithm. Firstly, the method detects the sea antenna through the Hoffman line detection method to constrain the sensitive area in the current detection image so as to improve the accuracy of water column detection; secondly, density-based spatial clustering of applications with noise (DBSCAN) + K-means clustering algorithm is used to obtain a better prior bounding box, which is input into the YOLOv4 network to improve the positioning accuracy of the water column; finally, the convolutional block attention module (CBAM) is added in the PANet structure to improve the detection accuracy of the water column. The experimental results show that the above algorithm can effectively improve the detection accuracy and positioning accuracy of the water column at the impact point.
引用
收藏
页数:15
相关论文
共 26 条
[1]   An intelligent water level monitoring method based on SSD algorithm [J].
Bai, Ganggang ;
Hou, Jingming ;
Zhang, Yangwei ;
Li, Bingyao ;
Han, Hao ;
Wang, Tian ;
Hinkelmann, Reinhard ;
Zhang, Dawei ;
Guo, Leiqiang .
MEASUREMENT, 2021, 185
[2]  
Bochkovskiy A., 2004, arXiv
[3]   Fast vehicle detection algorithm in traffic scene based on improved SSD [J].
Chen, Zhichao ;
Guo, Haoqi ;
Yang, Jie ;
Jiao, Haining ;
Feng, Zhicheng ;
Chen, Lifang ;
Gao, Tao .
MEASUREMENT, 2022, 201
[4]   A lightweight vehicles detection network model based on YOLOv5 [J].
Dong, Xudong ;
Yan, Shuai ;
Duan, Chaoqun .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 113
[5]  
Fang Z.-P., 2018, COMPUT ENG APPL, V54, P11
[6]   Improved YOLOv4 Marine Target Detection Combined with CBAM [J].
Fu, Huixuan ;
Song, Guoqing ;
Wang, Yuchao .
SYMMETRY-BASEL, 2021, 13 (04)
[7]   Ship Target Detection Based on Improved YOLO Network [J].
Huang, Hong ;
Sun, Dechao ;
Wang, Renfang ;
Zhu, Chun ;
Liu, Bangquan .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
[8]  
Huang Z., 2020, COMPLEXITY, V23, P4
[9]   Surface defect detection of steel strips based on improved YOLOv4 [J].
Li, Mengjiao ;
Wang, Hao ;
Wan, Zhibo .
COMPUTERS & ELECTRICAL ENGINEERING, 2022, 102
[10]   Improved YOLOv4 algorithm for safety management of on-site power system work [J].
Li Qiang ;
Zhao Feng ;
Xu Zhongping ;
Li Kexin ;
Wang Jing ;
Liu Haofeng ;
Qin Liang ;
Liu Kaipei .
ENERGY REPORTS, 2022, 8 :739-746