EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields

Jinyong Huang, Xu Xia, Zhihua Diao, Xingyi Li, Suna Zhao, Jingcheng Zhang, Baohua Zhang, Guoqiang Li

Agronomy · 22.12.2024 · 14 (12) · 3062

DOI: 10.3390/agronomy14123062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 22.12.2024. Verfasst von Jinyong Huang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the issue of the computational intensity and deployment difficulties associated with weed detection models, a lightweight target detection model for weeds based on YOLOv8s in maize fields was proposed in this study. Firstly, a lightweight network, designated as Dualconv High Performance GPU Net (D-PP-HGNet), was constructed on the foundation of the High Performance GPU Net (PP-HGNet) framework. Dualconv was introduced to reduce the computation required to achieve a lightweight design. Furthermore, Adaptive Feature Aggregation Module (AFAM) and Global Max Pooling were incorporated to augment the extraction of salient features in complex scenarios. Then, the newly created network was used to reconstruct the YOLOv8s backbone. Secondly, a four-stage inverted residual moving block (iRMB) was employed to construct a lightweight iDEMA module, which was used to replace the original C2f feature extraction module in the Neck to improve model performance and accuracy. Finally, Dualconv was employed instead of the conventional convolution for downsampling, further diminishing the network load. The new model was fully verified using the established field weed dataset. The test results showed that the modified model exhibited a notable improvement in detection performance compared with YOLOv8s. Accuracy improved from 91.2% to 95.8%, recall from 87.9% to 93.2%, and mAP@0.5 from 90.8% to 94.5%. Furthermore, the number of GFLOPs and the model size were reduced to 12.7 G and 9.1 MB, respectively, representing a decrease of 57.4% and 59.2% compared to the original model. Compared with the prevalent target detection models, such as Faster R-CNN, YOLOv5s, and YOLOv8l, the new model showed superior performance in accuracy and lightweight. The new model proposed in this paper effectively reduces the cost of the required hardware to achieve accurate weed identification in maize fields with limited resources.

Förderung

  • Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs

Zitieren

APA

Huang, J., Xia, X., Diao, Z., Li, X., Zhao, S., Zhang, J., Zhang, B., & Li, G. (2024). A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields. Agronomy, 14(12), 3062. https://doi.org/10.3390/agronomy14123062

Vancouver

Huang J, Xia X, Diao Z, Li X, Zhao S, Zhang J, et al. A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields. Agronomy. 2024;14(12):3062. doi:10.3390/agronomy14123062

BibTeX
@article{Huang2024,
  author = {Huang, Jinyong and Xia, Xu and Diao, Zhihua and Li, Xingyi and Zhao, Suna and Zhang, Jingcheng and Zhang, Baohua and Li, Guoqiang},
  title = {A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields},
  journal = {Agronomy},
  year = {2024},
  volume = {14},
  number = {12},
  pages = {3062},
  doi = {10.3390/agronomy14123062}
}
Kostenlos starten →