An Improved YOLOv5 Method for Shipwreck Target Detection by Side-Scan Sonar Images

被引：0
|
作者：
Tang Y. [1 ,2 ]
Bian S. [1 ]
Zhai G. [3 ]
Liu M. [4 ]
Zhang W. [5 ]
机构：
[1] College of Electrical Engineering, Naval University of Engineering, Wuhan
[2] 92116 Troops, Hulu Peninsula
[3] Naval Institute of Oceangraphic Surveying and Mapping, Tianjin
[4] 91001 Troops, Beijing
[5] 31016 Troops, Beijing
来源：
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | 2024年 / 49卷 / 06期
关键词：
genetic algo⁃ rithm; K-means algorithm; loss function; object detection; shipwreck; side-scan sonar; YOLOv5; model;
D O I：
10.13203/j.whugis20210353
中图分类号：
学科分类号：
摘要：
Objectives: The side-scan sonar shipwreck detection method based on the YOLOv3 model has the problems of high miss-alarm rate of small targets, heavy model weight, and slow detection speed that fails to meet real-time requirements. Methods: This paper introduces the YOLOv5 algorithm and pro⁃ poses an improved YOLOv5 model according to the characteristics of the side-scan sonar shipwreck da⁃ teset. We test YOLOv5a, YOLOv5b, YOLOv5c, YOLOv5d, YOLOv5s, YOLOv5m, YOLOv5l and YOLOv5x under the basic framework of YOLOv5 with eight different depth and width model structures. Then we choose the best structure by using genetic algorithm and K-means algorithm to optimize the detec⁃ tion frame, and to improve the loss function through complete intersection over union. Results: The results show that under the different range of intersection over union as 0.5 and 0.5-0.95,the average precisions of the improved YOLOv5a model are increased by about 0.3% and 0.6% than that of the original model,re⁃ spectively. Compared with the YOLOv3 model, the average precisions of the improved YOLOv5a model are increased by 4.2% and 6.1%, respectively, and the detection speed reaches 426 frames per second which is almost doubled that of YOLOv3. Conclusions: The proposed method is more conducive to practical appli⁃ cations and engineering deployment. © 2024 Editorial Department of Geomatics and Information Science of Wuhan University. All rights reserved.
引用
收藏
页码：977 / 985
页数：8
相关论文
共 21 条
  • [1] Jianhu Zhao, Juanjuan Li, Meng Li, Progress and Future Trend of Hydrographic Surveying and Charting ［J］, Journal of Geomatics, 34, 4, pp. 25-27, (2009)
  • [2] Jiu Wang, Jingtao Cao, Bingwu Lu, Et al., Under⁃ water Target Detection Project Equipment Applica⁃ tion and Development Trend［J］, Pearl River Water Transport, 11, pp. 43-44, (2016)
  • [3] Zhengrong Chen, Zhenghu Wang, Research on Un⁃ derwater Target Detection Using Side-Scan Sonar and Multibeam Sounding System［J］, Hydrographic Surveying and Charting, 33, 4, pp. 51-54, (2013)
  • [4] Jiu Wang, Jian Zhou, Comprehensive Application of Side-Scan Sonar and Multi-beam System in Ship⁃ wreck Survey［J］, China Water Transport, 10, 8, pp. 35-37, (2010)
  • [5] Chen Liu, The Comparative Analysis of Multibeam Sounding System，Side-Scan Sonar and Mag⁃ netometer in the Wreck Detection［D］, (2015)
  • [6] Jianhu Zhao, Xiao Wang, Hongmei Zhang, An Au⁃ tomatic Bottom Extracting Method for Side-Scan Sonar Image［J］, Geomatics and Information Sci⁃ ence of Wuhan University, 42, 12, pp. 1797-1803, (2017)
  • [7] Fanlin Yang, Jingnan Liu, Jianhu Zhao, Side-Scan Sonar Image Preprocessing Techniques Based on Data Fusion［J］, Geomatics and Information Science of Wuhan University, 29, 5, pp. 402-406, (2004)
  • [8] Dianyao Zhu, Hongyu Bian, Research of Side-Scan Sonar Target Auto Detection［J］, Journal of Jilin University（Information Science Edition, 26, 6, pp. 627-631, (2008)
  • [9] Haibin Li, Huizhong Teng, Haiying Song, Et al., Technology on the Extraction of Seabed Target Based on High Resolution Side-Scan Sonar［J］, Hy⁃ drographic Surveying and Charting, 30, 6, pp. 71-73, (2010)
  • [10] Xiao Wang, Research on Precise Processing of Side Scan Sonar Image and Object Recognition Methods ［D］, (2017)
123