EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Small-Sample Target Detection Method of Side-Scan Sonar Based on CycleGAN and Improved YOLOv8

Ye Zheng, Jun Yan, Junxia Meng, Ming Liang

Applied Sciences · 24.02.2025 · 15 (5) · 2396

DOI: 10.3390/app15052396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 24.02.2025. Verfasst von Ye Zheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Anhui Province, University Natural Science Research Key Project of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Because of their low cost and ease of deployment, side-scan sonars is one of the most widely used underwater survey instruments. However, the complexity of the marine environment and the difficulty in target acquisition limit the detection accuracy of side-scan sonars. To address these issues, this study proposes a small-sample target detection method of side-scan sonar images using the Cycle-Consistent Generative Adversarial Network (CycleGAN) model and the improved YOLOv8 model. First, considering the difficulty in obtaining side-scan sonar target images, the proposed method uses the CycleGAN model to generate pseudo-side-scan sonar images from optical images for data augmentation. Second, the original YOLOv8 model is revised by adding attention mechanisms, employing deformable convolution networks, and updating the loss function to improve the target detection accuracy of side-scan sonar images. Experimental results demonstrated the effectiveness of the CycleGAN model in generating pseudo-side-scan sonar images and better performance of the improved YOLOv8 model in the target detection of side-scan images. Moreover, the combination of data augmentation and the improved YOLOv8 model can remarkably increase the target detection accuracy of side-scan images. The proposed methods can effectively improve the target detection efficiency of underwater sonars in marine surveying.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Anhui Province
  • University Natural Science Research Key Project of Anhui Province
  • University Synergy Innovation Program of Anhui Province
  • Key Research and Development Project of Anhui Province
  • Natural Science Residual Fund Project of Anhui Jianzhu University

Zitieren

APA

Zheng, Y., Yan, J., Meng, J., & Liang, M. (2025). A Small-Sample Target Detection Method of Side-Scan Sonar Based on CycleGAN and Improved YOLOv8. Applied Sciences, 15(5), 2396. https://doi.org/10.3390/app15052396

Vancouver

Zheng Y, Yan J, Meng J, Liang M. A Small-Sample Target Detection Method of Side-Scan Sonar Based on CycleGAN and Improved YOLOv8. Applied Sciences. 2025;15(5):2396. doi:10.3390/app15052396

BibTeX
@article{Zheng2025,
  author = {Zheng, Ye and Yan, Jun and Meng, Junxia and Liang, Ming},
  title = {A Small-Sample Target Detection Method of Side-Scan Sonar Based on CycleGAN and Improved YOLOv8},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {5},
  pages = {2396},
  doi = {10.3390/app15052396}
}
Infokarte | EUVIMED

Artikeldaten derzeit nicht verfügbar.

Recherche