EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Zhuxi Lyu, Anjiang Lu, Yinglong Ma

Applied Sciences · 07.06.2024 · 14 (12) · 5002

DOI: 10.3390/app14125002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.06.2024. Verfasst von Zhuxi Lyu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Undergraduate Training Programs for Innovation and Entrepreneurship of Guizhou University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8 MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, and is suitable for complex vegetable field environments and resource-limited laser weeding devices.

Förderung

  • Undergraduate Training Programs for Innovation and Entrepreneurship of Guizhou University

Zitieren

APA

Lyu, Z., Lu, A., & Ma, Y. (2024). Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Applied Sciences, 14(12), 5002. https://doi.org/10.3390/app14125002

Vancouver

Lyu Z, Lu A, Ma Y. Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Applied Sciences. 2024;14(12):5002. doi:10.3390/app14125002

BibTeX
@article{Lyu2024,
  author = {Lyu, Zhuxi and Lu, Anjiang and Ma, Yinglong},
  title = {Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {12},
  pages = {5002},
  doi = {10.3390/app14125002}
}
Kostenlos starten →