EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO-SW: A Real-Time Weed Detection Model for Soybean Fields Using Swin Transformer and RT-DETR

Yizhou Shuai, Jingsha Shi, Yi Li, Shaohao Zhou, Lihua Zhang, Jiong Mu

Agronomy · 16.07.2025 · 15 (7) · 1712

DOI: 10.3390/agronomy15071712 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 16.07.2025. Verfasst von Yizhou Shuai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate weed detection in soybean fields is essential for enhancing crop yield and reducing herbicide usage. This study proposes a YOLO-SW model, an improved version of YOLOv8, to address the challenges of detecting weeds that are highly similar to the background in natural environments. The research stands out for its novel integration of three key advancements: the Swin Transformer backbone, which leverages local window self-attention to achieve linear O(N) computational complexity for efficient global context capture; the CARAFE dynamic upsampling operator, which enhances small target localization through context-aware kernel generation; and the RTDETR encoder, which enables end-to-end detection via IoU-aware query selection, eliminating the need for complex post-processing. Additionally, a dataset of six common soybean weeds was expanded to 12,500 images through simulated fog, rain, and snow augmentation, effectively resolving data imbalance and boosting model robustness. The experimental results highlight both the technical superiority and practical relevance: YOLO-SW achieves 92.3% mAP@50 (3.8% higher than YOLOv8), with recognition accuracy and recall improvements of 4.2% and 3.9% respectively. Critically, on the NVIDIA Jetson AGX Orin platform, it delivers a real-time inference speed of 59 FPS, making it suitable for seamless deployment on intelligent weeding robots. This low-power, high-precision solution not only bridges the gap between deep learning and precision agriculture but also enables targeted herbicide application, directly contributing to sustainable farming practices and environmental protection.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Shuai, Y., Shi, J., Li, Y., Zhou, S., Zhang, L., & Mu, J. (2025). YOLO-SW: A Real-Time Weed Detection Model for Soybean Fields Using Swin Transformer and RT-DETR. Agronomy, 15(7), 1712. https://doi.org/10.3390/agronomy15071712

Vancouver

Shuai Y, Shi J, Li Y, Zhou S, Zhang L, Mu J. YOLO-SW: A Real-Time Weed Detection Model for Soybean Fields Using Swin Transformer and RT-DETR. Agronomy. 2025;15(7):1712. doi:10.3390/agronomy15071712

BibTeX
@article{Shuai2025,
  author = {Shuai, Yizhou and Shi, Jingsha and Li, Yi and Zhou, Shaohao and Zhang, Lihua and Mu, Jiong},
  title = {YOLO-SW: A Real-Time Weed Detection Model for Soybean Fields Using Swin Transformer and RT-DETR},
  journal = {Agronomy},
  year = {2025},
  volume = {15},
  number = {7},
  pages = {1712},
  doi = {10.3390/agronomy15071712}
}
Kostenlos starten →