EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RSE-YOLOv8: An Algorithm for Underwater Biological Target Detection

Peihang Song, Lei Zhao, Heng Li, Xiaojun Xue, Hui Liu

Sensors · 18.09.2024 · 24 (18) · 6030

DOI: 10.3390/s24186030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.09.2024. Verfasst von Peihang Song und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650504, China. Hauptthemen laut MEDLINE: Algorithms, Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Science and Technology Department Basic Research Project - General Project, Yunnan Provincial Science and Technology Department Basic Research Project-General Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater target detection is of great significance in underwater ecological assessment and resource development. To better protect the environment and optimize the development of underwater resources, we propose a new underwater target detection model with several innovations based on the YOLOv8 framework. Firstly, the SAConv convolutional operation is introduced to redesign C2f, the core module of YOLOv8, to enhance the network’s feature extraction capability for targets of different scales. Secondly, we propose the RFESEConv convolution module instead of the conventional convolution operation in neural networks to cope with the degradation of image channel information in underwater images caused by light refraction and reflection. Finally, we propose an ESPPF module to further enhance the model’s multi-scale feature extraction efficiency. Simultaneously, the overall parameters of the model are reduced. Compared to the baseline model, the proposed one demonstrates superior advantages when deployed on underwater devices with limited computational resources. The experimental results show that we have achieved significant detection accuracy on the underwater dataset, with an mAP@50 of 78% and an mAP@50:95 of 43.4%. Both indicators are 2.1% higher compared to the baseline models. Additionally, the proposed model demonstrates superior performance on other datasets, showcasing its strong generalization capability and robustness. This research provides new ideas and methods for underwater target detection and holds important application value.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeural Networks, ComputerImage Processing, Computer-Assisted

Stichwörter der Autor:innen

RFAConvSAConvSPPFYOLOv8underwater detection

Autor:innen und Institutionen

  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650504, China.

Förderung

  • Yunnan Provincial Science and Technology Department Basic Research Project - General Project
  • Yunnan Provincial Science and Technology Department Basic Research Project-General Project

Zitieren

APA

Song, P., Zhao, L., Li, H., Xue, X., & Liu, H. (2024). RSE-YOLOv8: An Algorithm for Underwater Biological Target Detection. Sensors, 24(18), 6030. https://doi.org/10.3390/s24186030

Vancouver

Song P, Zhao L, Li H, Xue X, Liu H. RSE-YOLOv8: An Algorithm for Underwater Biological Target Detection. Sensors. 2024;24(18):6030. doi:10.3390/s24186030

BibTeX
@article{Song2024,
  author = {Song, Peihang and Zhao, Lei and Li, Heng and Xue, Xiaojun and Liu, Hui},
  title = {RSE-YOLOv8: An Algorithm for Underwater Biological Target Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {18},
  pages = {6030},
  doi = {10.3390/s24186030}
}
Kostenlos starten →