Study on Visual Detection Algorithm of Sea Surface Targets Based on Improved YOLOv3

被引:28
|
作者
Liu, Tao [1 ]
Pang, Bo [1 ]
Ai, Shangmao [2 ]
Sun, Xiaoqiang [1 ]
机构
[1] Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Harbin 150001, Peoples R China
[2] Harbin Engn Univ, Coll Shipbldg Engn, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
YOLO v3; anchor-setting; target detection; feature fusion; connection of cross-feature maps; buoys; ships;
D O I
10.3390/s20247263
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Countries around the world have paid increasing attention to the issue of marine security, and sea target detection is a key task to ensure marine safety. Therefore, it is of great significance to propose an efficient and accurate sea-surface target detection algorithm. The anchor-setting method of the traditional YOLO v3 only uses the degree of overlap between the anchor and the ground-truth box as the standard. As a result, the information of some feature maps cannot be used, and the required accuracy of target detection is hard to achieve in a complex sea environment. Therefore, two new anchor-setting methods for the visual detection of sea targets were proposed in this paper: the average method and the select-all method. In addition, cross PANet, a feature fusion structure for cross-feature maps was developed and was used to obtain a better baseline cross YOLO v3, where different anchor-setting methods were combined with a focal loss for experimental comparison in the datasets of sea buoys and existing sea ships, SeaBuoys and SeaShips, respectively. The results showed that the method proposed in this paper could significantly improve the accuracy of YOLO v3 in detecting sea-surface targets, and the highest value of mAP in the two datasets is 98.37% and 90.58%, respectively.
引用
收藏
页码:1 / 14
页数:14
相关论文
共 50 条
  • [21] A detection method for the ridge beast based on improved YOLOv3 algorithm
    Miaole Hou
    Wuchen Hao
    Youqiang Dong
    Yuhang Ji
    Heritage Science, 11
  • [22] Bird Detection Algorithm in Natural Scenes Based on Improved YOLOv3
    Song Ziying
    Yang Kuihe
    Zhang Yu
    LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (18)
  • [23] Research on small target detection algorithm based on improved yolov3
    Ye, Kangquan
    Fang, Zhongbin
    Huang, Xiaojie
    Ma, Xizhe
    Ji, Jing
    Wu, Qiantong
    Xie, Yongjun
    2020 5TH INTERNATIONAL CONFERENCE ON MECHANICAL, CONTROL AND COMPUTER ENGINEERING (ICMCCE 2020), 2020, : 1467 - 1470
  • [24] User interface components detection algorithm based on improved YOLOv3
    Liu Y.-N.
    Wu D.
    Zhu X.-D.
    Zhang Q.-X.
    Li S.-S.
    Guo S.-J.
    Wang C.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2021, 51 (03): : 1026 - 1033
  • [25] Mask Wearing Detection Algorithm Based on Improved Tiny YOLOv3
    Liu, Guohua
    Zhang, Qintao
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2021, 35 (07)
  • [26] A detection method for the ridge beast based on improved YOLOv3 algorithm
    Hou, Miaole
    Hao, Wuchen
    Dong, Youqiang
    Ji, Yuhang
    HERITAGE SCIENCE, 2023, 11 (01)
  • [27] A SAR Image Building Detection Algorithm Based on Improved YOLOv3
    Li X.
    Su J.
    Yang L.
    Su, Juan (suj04@mails.tsinghua.edu.cn), 1600, China Ordnance Society (41): : 1347 - 1359
  • [28] Fisheye Image Object Detection Based on an Improved YOLOv3 Algorithm
    Lei, Xiaodong
    Sun, Beibei
    Peng, Jinzhu
    Zhang, Fangfang
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 5801 - 5805
  • [29] An Improved YOLOv3 Algorithm for Small Target Detection
    Lv, Hui
    Chen, Zhe
    Huang, Shi-Hao
    Journal of Network Intelligence, 2023, 8 (02): : 491 - 504
  • [30] Improved YOLOv3 Algorithm for Ship Target Detection
    Chen, Liankai
    Li, Bangyu
    Qi, Liang
    PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 7288 - 7293