EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BHC-YOLOV8 : improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios

BaiShao Zhan, Xi Xiong, Xiaoli Li, Wei Luo

Frontiers in Plant Science · 02.12.2024 · 15

DOI: 10.3389/fpls.2024.1492504 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 02.12.2024. Verfasst von BaiShao Zhan und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The detection efficiency of tea diseases and defects ensures the quality and yield of tea. However, in actual production, on the one hand, the tea plantation has high mountains and long roads, and the safety of inspection personnel cannot be guaranteed; on the other hand, the inspection personnel have factors such as lack of experience and fatigue, resulting in incomplete and slow testing results. Introducing visual inspection technology can avoid the above problems.

Methods

Firstly, a dynamic sparse attention mechanism (Bi Former) is introduced into the model backbone. It filters out irrelevant key value pairs at the coarse region level, utilizing sparsity to save computation and memory; jointly apply fine region token to token attention in the remaining candidate regions. Secondly, Haar wavelets are introduced to improve the down sampling module. By processing the input information flow horizontally, vertically, and diagonally, the original image is reconstructed. Finally, a new feature fusion network is designed using a multi-head attention mechanism to decompose the main network into several cascaded stages, each stage comprising a sub-backbone for parallel processing of different features. Simultaneously, skip connections are performed on features from the same layer, and unbounded fusion weight normalization is introduced to constrain the range of each weight value.

Results

After the above improvements, the confidence level of the current mainstream models increased by 7.1%, mAP0.5 increased by 8%, and reached 94.5%. After conducting ablation experiments and comparing with mainstream models, the feature fusion network proposed in this paper reduced computational complexity by 10.6 GFlops, increased confidence by 2.7%, and increased mAP0.5 by 3.2%.

Discussion

This paper developed a new network based on YOLOv8 to overcome the difficulties of tea diseases and defects such as small target, multiple occlusion and complex background.

Schlagwörter

Stichwörter der Autor:innen

BiFormerHaarYOLOv8down samplingskip connectionstea

Autor:innen und Institutionen

  • School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, China.
  • College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China.

Zitieren

APA

Zhan, B., Xiong, X., Li, X., & Luo, W. (2024). BHC-YOLOV8 : improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1492504

Vancouver

Zhan B, Xiong X, Li X, Luo W. BHC-YOLOV8 : improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios. Frontiers in Plant Science. 2024;15. doi:10.3389/fpls.2024.1492504

BibTeX
@article{Zhan2024,
  author = {Zhan, BaiShao and Xiong, Xi and Li, Xiaoli and Luo, Wei},
  title = {BHC-YOLOV8 : improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios},
  journal = {Frontiers in Plant Science},
  year = {2024},
  volume = {15},
  doi = {10.3389/fpls.2024.1492504}
}
Kostenlos starten →