EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Shrimp Larvae Counting Based on Improved YOLOv5 Model with Regional Segmentation

Hongchao Duan, Jun Wang, Yuan Zhang, Xiangyu Wu, Tao Peng, Xuhao Liu, Delong Deng

Sensors · 30.09.2024 · 24 (19) · 6328

DOI: 10.3390/s24196328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.09.2024. Verfasst von Hongchao Duan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Optical and Electromagnetic Research, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou 510006, Ch…. Hauptthemen laut MEDLINE: Larva, Algorithms. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Counting shrimp larvae is an essential part of shrimp farming. Due to their tiny size and high density, this task is exceedingly difficult. Thus, we introduce an algorithm for counting densely packed shrimp larvae utilizing an enhanced You Only Look Once version 5 (YOLOv5) model through a regional segmentation approach. First, the C2f and convolutional block attention modules are used to improve the capabilities of YOLOv5 in recognizing the small shrimp. Moreover, employing a regional segmentation technique can decrease the receptive field area, thereby enhancing the shrimp counter’s detection performance. Finally, a strategy for stitching and deduplication is implemented to tackle the problem of double counting across various segments. The findings from the experiments indicate that the suggested algorithm surpasses several other shrimp counting techniques in terms of accuracy. Notably, for high-density shrimp larvae in large quantities, this algorithm attained an accuracy exceeding 98%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LarvaAlgorithmsAnimalsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

YOLOv5attention mechanismregional segmentationrepeat shrimp removalshrimp larvae counting

Autor:innen und Institutionen

  • Centre for Optical and Electromagnetic Research, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou 510006, China.

Zitieren

APA

Duan, H., Wang, J., Zhang, Y., Wu, X., Peng, T., Liu, X., & Deng, D. (2024). Shrimp Larvae Counting Based on Improved YOLOv5 Model with Regional Segmentation. Sensors, 24(19), 6328. https://doi.org/10.3390/s24196328

Vancouver

Duan H, Wang J, Zhang Y, Wu X, Peng T, Liu X, et al. Shrimp Larvae Counting Based on Improved YOLOv5 Model with Regional Segmentation. Sensors. 2024;24(19):6328. doi:10.3390/s24196328

BibTeX
@article{Duan2024,
  author = {Duan, Hongchao and Wang, Jun and Zhang, Yuan and Wu, Xiangyu and Peng, Tao and Liu, Xuhao and Deng, Delong},
  title = {Shrimp Larvae Counting Based on Improved YOLOv5 Model with Regional Segmentation},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6328},
  doi = {10.3390/s24196328}
}
Kostenlos starten →