EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLOv8 Model for Weed Detection in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion

Yinzeng Liu, Fandi Zeng iD, Hongwei Diao iD, Junke Zhu, Dong Ji iD, Xijie Liao, Zhihuan Zhao

Sensors · 05.07.2024 · 24 (13) · 4379

DOI: 10.3390/s24134379 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.07.2024. Verfasst von Yinzeng Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Mechanical and Electronic Engineering College, Shandong Agriculture and Engineering University, Jinan 250100, China. Hauptthemen laut MEDLINE: Triticum, Plant Weeds. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Supported by Program for Innovative Research Team in SDAEU, Program for Innovative Research Team in SDAEU, the project under the application demonstration and promotion of automatic driving system for agricultural machinery in Linxia State.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate weed detection is essential for the precise control of weeds in wheat fields, but weeds and wheat are sheltered from each other, and there is no clear size specification, making it difficult to accurately detect weeds in wheat. To achieve the precise identification of weeds, wheat weed datasets were constructed, and a wheat field weed detection model, YOLOv8-MBM, based on improved YOLOv8s, was proposed. In this study, a lightweight visual converter (MobileViTv3) was introduced into the C2f module to enhance the detection accuracy of the model by integrating input, local (CNN), and global (ViT) features. Secondly, a bidirectional feature pyramid network (BiFPN) was introduced to enhance the performance of multi-scale feature fusion. Furthermore, to address the weak generalization and slow convergence speed of the CIoU loss function for detection tasks, the bounding box regression loss function (MPDIOU) was used instead of the CIoU loss function to improve the convergence speed of the model and further enhance the detection performance. Finally, the model performance was tested on the wheat weed datasets. The experiments show that the YOLOv8-MBM proposed in this paper is superior to Fast R-CNN, YOLOv3, YOLOv4-tiny, YOLOv5s, YOLOv7, YOLOv9, and other mainstream models in regards to detection performance. The accuracy of the improved model reaches 92.7%. Compared with the original YOLOv8s model, the precision, recall, mAP1, and mAP2 are increased by 10.6%, 8.9%, 9.7%, and 9.3%, respectively. In summary, the YOLOv8-MBM model successfully meets the requirements for accurate weed detection in wheat fields.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriticumPlant WeedsNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

BiFPNMobileViTv3deep learningweed detectionwheat weeds

Autor:innen und Institutionen

  • Mechanical and Electronic Engineering College, Shandong Agriculture and Engineering University, Jinan 250100, China.
  • School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, China.

ORCID-Profile: Fandi Zeng, Hongwei Diao, Dong Ji

Förderung

  • Supported by Program for Innovative Research Team in SDAEU
  • Program for Innovative Research Team in SDAEU
  • the project under the application demonstration and promotion of automatic driving system for agricultural machinery in Linxia State

Zitieren

APA

Liu, Y., Zeng, F., Diao, H., Zhu, J., Ji, D., Liao, X., & Zhao, Z. (2024). YOLOv8 Model for Weed Detection in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion. Sensors, 24(13), 4379. https://doi.org/10.3390/s24134379

Vancouver

Liu Y, Zeng F, Diao H, Zhu J, Ji D, Liao X, et al. YOLOv8 Model for Weed Detection in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion. Sensors. 2024;24(13):4379. doi:10.3390/s24134379

BibTeX
@article{Liu2024,
  author = {Liu, Yinzeng and Zeng, Fandi and Diao, Hongwei and Zhu, Junke and Ji, Dong and Liao, Xijie and Zhao, Zhihuan},
  title = {YOLOv8 Model for Weed Detection in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4379},
  doi = {10.3390/s24134379}
}
Kostenlos starten →