• Home
  • Search
  • Shipwreck Target Recognition in Side-Scan Sonar Images by Improved YOLOv3 Model Based on Transfer Learning
  • Cite Icon89
  • https://doi.org/10.1109/access.2020.3024813Copy DOI Icon

Shipwreck Target Recognition in Side-Scan Sonar Images by Improved YOLOv3 Model Based on Transfer Learning

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

When used to recognize side-scan sonar images of shipwreck targets, the Faster R-CNN model is time-consuming and has low efficiency and a high missed detection rate for small targets. Considering that existing datasets of side-scan sonar images of shipwreck targets are small, we propose a YOLOv3 model that can automatically recognize side-scan sonar images of shipwreck targets based on transfer learning. Based on the Darknet-53 network, we froze part of the convolutional layer of the YOLOv3 model trained on COCO dataset images, and conducted transfer learning. Multi-scale training of shallow feature fusion was done based on multi-scale feature fusion with Feature Pyramid Networks (FPN) support, and the proportion of recognized shallow features of shipwreck targets increased. Meanwhile, the parameters and sizes of target anchor boxes were reset using K-means clustering, which allowed us to improve the speed of target recognition and the precision of smaller target recognition and positioning. Lastly, the binary classification cross entropy function was used to improve the loss function of the YOLOv3 algorithm. Experimental results show that under the same recognition target, the average precision (AP) value of the YOLOv3 model based on transfer learning reached 89.49%, which is an improvement of 0.31% and 1.77%, respectively, compared with the Faster R-CNN model and the traditional YOLOv3 model. Moreover, the YOLOv3 model based on transfer learning had the highest harmonic mean (F1), reaching 90.71%, which is 3.96% and 1.63% higher, respectively, than the harmonic means of the Faster R-CNN and the traditional YOLOv3 model. Lastly, the traditional YOLOv3 model takes an average 0.17s to identify a target. In contrast, the Faster R-CNN model takes an average of 2.8s to identify a target. Hence, our transfer learning YOLOv3 model greatly improves detection efficiency, meets the needs of real-time target recognition, and ultimately has better overall performance than existing methods.

Similar Papers
  • PDF
  • Research Article
  • Citations10

Multitarget Intelligent Recognition of Petrographic Thin Section Images Based on Faster RCNN

  • Jun 28, 2023
  • Minerals
  • Hanyu Wang +4
  • Research Article
  • Citations59

Automated rail surface crack analytics using deep data-driven models and transfer learning

  • Mar 31, 2021
  • Sustainable Cities and Society
  • Zhong Zheng +3
  • PDF
  • Research Article
  • Citations131

Multi-Scale Feature Fusion Convolutional Neural Network for Indoor Small Target Detection

  • May 19, 2022
  • Frontiers in Neurorobotics
  • Li Huang +7
  • Research Article
  • Citations19

Monitoring of key Camellia Oleifera phenology features using field cameras and deep learning

  • Feb 28, 2024
  • Computers and Electronics in Agriculture
  • Haoran Li +3
  • Conference Article
  • Citations20

Wreckage Target Recognition in Side-scan Sonar Images Based on an Improved Faster R-CNN Model

  • Oct 01, 2020
  • Tang Yulin +4
  • PDF
  • Research Article
  • Citations53

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

  • Jan 18, 2023
  • Remote Sensing
  • Xing Du +4
  • Research Article

A Study on Comparative Analysis of Object Detection-based Real-Time Wildfire and Class B Fire Detection Performance

  • Jun 30, 2024
  • International Journal of Fire Science and Engineering
  • Sugi Choi +3
  • Research Article
  • Citations10

Comparison and Optimization of Rail Defect Detection Methods Based on Object Detection Model

  • Jan 02, 2025
  • Tribology Transactions
  • Hongwei Zhang +6
  • Conference Article

Research on Multi-scale Feature Fusion based on High-Resolution Branch Enhancement for Small Target Ship Detection

  • Dec 05, 2025
  • Jiang Ye +4
  • PDF
  • Research Article
  • Citations1

Detection of human sperm cells using deep learning-based object detection methods

  • Jan 01, 2024
  • Pamukkale University Journal of Engineering Sciences
  • Mecit Yuzkat +2
  • Research Article
  • Citations5

Walnut Ripeness Detection Based on Coupling Information and Lightweight YOLOv4

  • Jan 10, 2022
  • International Journal of Circuits, Systems and Signal Processing
  • Kaixuan Cui +3
  • PDF
  • Research Article
  • Citations6

Detection of Residual Film on the Field Surface Based on Faster R-CNN Multiscale Feature Fusion

  • May 30, 2023
  • Agriculture
  • Tong Zhou +6
  • Research Article
  • Citations5

An improved SSD lightweight network with coordinate attention for aircraft target recognition in scene videos

  • Jan 10, 2024
  • Journal of Intelligent & Fuzzy Systems
  • Weidong Li +4
  • Research Article
  • Citations2

Complex overlapping pedestrian target detection network based on the yolov3 model

  • Apr 10, 2024
  • Transactions on Computer Science and Intelligent Systems Research
  • Yuchi Zhang
  • PDF
  • Research Article
  • Citations51

A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification

  • Jan 13, 2022
  • Remote Sensing
  • Zhen Cheng +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.