EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Feature Enhancement for Robust Weed Detection in Complex Cotton Fields

Jun Tie, Shuangyang Li, Lu Zheng, Pingting Chen, Zhiqing Luo, Huiran Tong, Zhihong Wang

Agronomy · 11.11.2026 · 16 (22) · 2267

DOI: 10.3390/agronomy16222267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 11.11.2026. Verfasst von Jun Tie und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Foreign Expert Project in Hubei Province in 2025, Fund for Research Platform of South-Central Minzu University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precise weed detection in complex cotton fields is a critical prerequisite for site-specific weed control and precision management. To address the challenges of small weed targets, high inter-class similarity, occlusion, and illumination variations that affect detection accuracy in cotton fields, this paper proposes CWD-YOLO, an improved model based on YOLO26n. CWD-YOLO reconstructs the original backbone network using GhostNetV3 to enhance low-level visual feature extraction, integrates TSSA into the C2PSA module to strengthen high-level semantic feature representation, and adopts AssemFormer in the C3k2 feature fusion stage to improve multi-scale local–global feature fusion. These designs enhance the detection of small, weak-feature, and occluded weed targets. On the CottonWeedDet12 benchmark dataset, CWD-YOLO achieved Precision, Recall, mAP@0.5, and mAP@0.5:0.95 values of 94.3%, 87.9%, 93.1%, and 87.6%, respectively, outperforming the baseline YOLO26n by 2.9, 2.7, 2.0, and 1.5 percentage points. Furthermore, in multi-dataset adaptability experiments on three external weed datasets, namely 3WDataset, 6WEED, and 3SeasonWeedDet10, CWD-YOLO consistently outperformed the baseline model, indicating its adaptability to different weed detection scenarios. The experimental results demonstrate that CWD-YOLO effectively improves weed detection accuracy in complex cotton fields and provides an effective method for precise field weed identification.

Förderung

  • National Key Research and Development Program of China
  • Foreign Expert Project in Hubei Province in 2025
  • Fund for Research Platform of South-Central Minzu University
  • National Innovation and Entrepreneurship Training Program for College Stu-dents

Zitieren

APA

Tie, J., Li, S., Zheng, L., Chen, P., Luo, Z., Tong, H., & Wang, Z. (2026). Multi-Scale Feature Enhancement for Robust Weed Detection in Complex Cotton Fields. Agronomy, 16(22), 2267. https://doi.org/10.3390/agronomy16222267

Vancouver

Tie J, Li S, Zheng L, Chen P, Luo Z, Tong H, et al. Multi-Scale Feature Enhancement for Robust Weed Detection in Complex Cotton Fields. Agronomy. 2026;16(22):2267. doi:10.3390/agronomy16222267

BibTeX
@article{Tie2026,
  author = {Tie, Jun and Li, Shuangyang and Zheng, Lu and Chen, Pingting and Luo, Zhiqing and Tong, Huiran and Wang, Zhihong},
  title = {Multi-Scale Feature Enhancement for Robust Weed Detection in Complex Cotton Fields},
  journal = {Agronomy},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {2267},
  doi = {10.3390/agronomy16222267}
}
Kostenlos starten →