EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Fish Detection Method for Complex Underwater Scenes

Xiaojing Guo, Yuan Liu, Minghui Wang, Guangyu Zuo, Liwei Kou, Yinke Dou

Journal of Marine Science and Engineering · 17.06.2026 · 14 (12) · 1114

DOI: 10.3390/jmse14121114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 17.06.2026. Verfasst von Xiaojing Guo und 5 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Frontiers Science Center of Polar Science, Shanxi Province Water Conservancy Science and Technology R&D Service Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fish observation is a key component of marine ecological monitoring and is valuable for understanding ecological processes and fish population dynamics. In practical applications, observation equipment is often constrained by limited memory and computational resources, making it difficult to deploy visual detection models with large parameter counts and high computational complexity. Under limited computational resources, existing deep-learning-based fish detection models struggle to balance detection accuracy, model lightweighting, and real-time edge deployment. To address this issue, a lightweight GEM-YOLOv8n model based on YOLOv8n is proposed for fish detection. For high model complexity, insufficient feature representation, and limited bounding box regression accuracy in complex underwater observation scenarios, the model replaces C2f modules and some Conv modules with GhostC2f and GhostConv, introduces the EMA attention mechanism, and adopts MPDIoU loss instead of CIoU. Experimental results show that, compared with YOLOv8n, GEM-YOLOv8n improves Precision, Recall, mAP50, and mAP50–95 by 0.53%, 2.16%, 0.52%, and 0.34% while reducing parameters and FLOPs by 48.0% and 39.5%. These results demonstrate that the proposed model improves detection performance while reducing model complexity. Tests on Jetson Xavier NX demonstrate real-time performance and deployment feasibility, providing a lightweight deployment solution for resource-constrained underwater fish detection.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Frontiers Science Center of Polar Science
  • Shanxi Province Water Conservancy Science and Technology R&D Service Project

Zitieren

APA

Guo, X., Liu, Y., Wang, M., Zuo, G., Kou, L., & Dou, Y. (2026). A Lightweight Fish Detection Method for Complex Underwater Scenes. Journal of Marine Science and Engineering, 14(12), 1114. https://doi.org/10.3390/jmse14121114

Vancouver

Guo X, Liu Y, Wang M, Zuo G, Kou L, Dou Y. A Lightweight Fish Detection Method for Complex Underwater Scenes. Journal of Marine Science and Engineering. 2026;14(12):1114. doi:10.3390/jmse14121114

BibTeX
@article{Guo2026,
  author = {Guo, Xiaojing and Liu, Yuan and Wang, Minghui and Zuo, Guangyu and Kou, Liwei and Dou, Yinke},
  title = {A Lightweight Fish Detection Method for Complex Underwater Scenes},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {12},
  pages = {1114},
  doi = {10.3390/jmse14121114}
}
Kostenlos starten →