EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A New Pest Detection Method Based on Improved YOLOv5m

Min Dai iD, Md Mehedi Hassan Dorjoy iD, Hong Miao, Shanwen Zhang

Insects · 05.01.2023 · 14 (1) · 54

DOI: 10.3390/insects14010054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Insects, online erschienen am 05.01.2023. Verfasst von Min Dai und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical Engineering, Yangzhou University, Yangzhou 225127, China. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Provincial Key Research and Development Program Modern Agriculture, Jiangsu Agricultural Science and Technology Innovation Fund, Jiangsu Agricultural Science and Technology Independent Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pest detection in plants is essential for ensuring high productivity. Convolutional neural networks (CNN)-based deep learning advancements recently have made it possible for researchers to increase object detection accuracy. In this study, pest detection in plants with higher accuracy is proposed by an improved YOLOv5m-based method. First, the SWin Transformer (SWinTR) and Transformer (C3TR) mechanisms are introduced into the YOLOv5m network so that they can capture more global features and can increase the receptive field. Then, in the backbone, ResSPP is considered to make the network extract more features. Furthermore, the global features of the feature map are extracted in the feature fusion phase and forwarded to the detection phase via a modification of the three output necks C3 into SWinTR. Finally, WConcat is added to the fusion feature, which increases the feature fusion capability of the network. Experimental results demonstrate that the improved YOLOv5m achieved 95.7% precision rate, 93.1% recall rate, 94.38% F1 score, and 96.4% Mean Average Precision (mAP). Meanwhile, the proposed model is significantly better than the original YOLOv3, YOLOv4, and YOLOv5m models. The improved YOLOv5m model shows greater robustness and effectiveness in detecting pests, and it could more precisely detect different pests from the dataset.

Schlagwörter

Stichwörter der Autor:innen

YOLOv5mconvolutional neural networksdeep learningpest detection

Autor:innen und Institutionen

  • College of Mechanical Engineering, Yangzhou University, Yangzhou 225127, China.

ORCID-Profile: Min Dai, Md Mehedi Hassan Dorjoy

Förderung

  • Jiangsu Provincial Key Research and Development Program Modern Agriculture
  • Jiangsu Agricultural Science and Technology Innovation Fund
  • Jiangsu Agricultural Science and Technology Independent Innovation

Zitieren

APA

Dai, M., Dorjoy, M. M. H., Miao, H., & Zhang, S. (2023). A New Pest Detection Method Based on Improved YOLOv5m. Insects, 14(1), 54. https://doi.org/10.3390/insects14010054

Vancouver

Dai M, Dorjoy MMH, Miao H, Zhang S. A New Pest Detection Method Based on Improved YOLOv5m. Insects. 2023;14(1):54. doi:10.3390/insects14010054

BibTeX
@article{Dai2023,
  author = {Dai, Min and Dorjoy, Md Mehedi Hassan and Miao, Hong and Zhang, Shanwen},
  title = {A New Pest Detection Method Based on Improved YOLOv5m},
  journal = {Insects},
  year = {2023},
  volume = {14},
  number = {1},
  pages = {54},
  doi = {10.3390/insects14010054}
}
Kostenlos starten →