EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Underwater Target Detection Algorithm Based on Feature Fusion Enhancement

Liang Chen, Tao Yin, Shaowu Zhou, Guo Yi, Di Fan, Jin Zhao

Electronics · 21.06.2023 · 12 (13) · 2756

DOI: 10.3390/electronics12132756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 21.06.2023. Verfasst von Liang Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Postgraduate Scientific Research Innovation Project of Hunan Province, National Natural Science Foundation of China, A Project Supported by Scientific Research Fund of Hunan Provincial Education Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater robots that use optical images for dynamic target detection often encounter image blurring, poor contrast, and indistinct target features. As a result, the underwater robots have poor detection performance with a high rate of missed detections. To overcome these issues, a feature-enhanced algorithm for underwater target detection has been proposed in this paper. Based on YOLOv7, a feature enhancement module utilizing a triple-attention mechanism is developed to improve the network’s feature extraction ability without increasing the computational or algorithmic parameter quantity. Moreover, comprehensively considering the impact of a redundant feature in the images on detection accuracy, the ASPPCSPC structure was built. A parallel spatial convolutional pooling structure based on the original feature pyramid fusion structure, SPPCSPC, is introduced. The GhostNet network was utilized to optimize its convolution module, which reduces the model’s parameter quantity and optimizes the feature map. Furthermore, a Cat-BiFPN structure was designed to address the problem of fine-grained information loss in YOLOv7 feature fusion by adopting a weighted nonlinear fusion strategy to enhance the algorithm’s adaptability. Using the UPRC offshore dataset for validation, the algorithm’s detection accuracy was increased by 2.9%, and the recall rate was improved by 2.3% compared to the original YOLOv7 algorithm. In addition, the model quantity is reduced by 11.2%, and the model size is compressed by 10.9%. The experimental results significantly establish the validity of the proposed algorithm.

Förderung

  • Postgraduate Scientific Research Innovation Project of Hunan Province
  • National Natural Science Foundation of China
  • A Project Supported by Scientific Research Fund of Hunan Provincial Education Department

Zitieren

APA

Chen, L., Yin, T., Zhou, S., Yi, G., Fan, D., & Zhao, J. (2023). Underwater Target Detection Algorithm Based on Feature Fusion Enhancement. Electronics, 12(13), 2756. https://doi.org/10.3390/electronics12132756

Vancouver

Chen L, Yin T, Zhou S, Yi G, Fan D, Zhao J. Underwater Target Detection Algorithm Based on Feature Fusion Enhancement. Electronics. 2023;12(13):2756. doi:10.3390/electronics12132756

BibTeX
@article{Chen2023,
  author = {Chen, Liang and Yin, Tao and Zhou, Shaowu and Yi, Guo and Fan, Di and Zhao, Jin},
  title = {Underwater Target Detection Algorithm Based on Feature Fusion Enhancement},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {13},
  pages = {2756},
  doi = {10.3390/electronics12132756}
}
Kostenlos starten →