Cotton Leaf Spot Detection Based on an Improved YOLOv11n Model
Journal of Imaging · 27.06.2026 · 12 (7) · 284
DOI: 10.3390/jimaging12070284 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 27.06.2026. Verfasst von Yaxin Xie und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Innovation and Entrepreneurship Training Program for Undergraduates(Key Project), Provincial Innovation and Entrepreneurship Training Program for Undergraduates.
Abstract (Originalsprache)
In cotton disease detection, the complex farmland environment and the varying scales of disease spots, especially the presence of small-target disease spots, limit the detection accuracy of lightweight models. To address this issue, an improved YOLOv11n detection algorithm is proposed. First, the backbone network is reconstructed using the GhostConv (G-conv) module, which generates redundant feature maps through linear operations, thereby reducing computational complexity. Second, an Adaptive Calibration and Feature Fusion Architecture Head (ACFFA) with prior calibration and cross-scale fusion capabilities is constructed in the detection stage to handle the problem of varying disease spot scales. Furthermore, the Adaptive Scale-aware Wise Intersection over Union (AS-WIoU) loss function, improved from WIoUv3, is introduced to enhance the stability of bounding box regression and improve detection accuracy for low-resolution, small-target lesions. Experimental results show that on the cotton disease dataset constructed based on the Mendeley Data database, the proposed model achieves mAP50 and mAP50-95 of 90.30% and 73.84%, respectively, with precision and recall of 92.33% and 87.68%, and a parameter count of 3.81 M. The algorithm significantly improves detection accuracy while maintaining efficient inference, making it suitable for real-time monitoring tasks on agricultural embedded terminals.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China.
Förderung
- National Natural Science Foundation of China
- National Innovation and Entrepreneurship Training Program for Undergraduates(Key Project)
- Provincial Innovation and Entrepreneurship Training Program for Undergraduates
- Zhejiang Sci-Tech University Undergraduate Scientific and Technological Innovation Program
Zitieren
APA
Xie, Y., Zhang, M., Han, Y., Dai, L., Fu, H., & Xu, L. (2026). Cotton Leaf Spot Detection Based on an Improved YOLOv11n Model. Journal of Imaging, 12(7), 284. https://doi.org/10.3390/jimaging12070284
Vancouver
Xie Y, Zhang M, Han Y, Dai L, Fu H, Xu L. Cotton Leaf Spot Detection Based on an Improved YOLOv11n Model. Journal of Imaging. 2026;12(7):284. doi:10.3390/jimaging12070284
BibTeX
@article{Xie2026,
author = {Xie, Yaxin and Zhang, Mingyu and Han, Yonghua and Dai, Le and Fu, Haifeng and Xu, Lu},
title = {Cotton Leaf Spot Detection Based on an Improved YOLOv11n Model},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {284},
doi = {10.3390/jimaging12070284}
}
EUVIMED