EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Combined Strategy for Detecting Cotton Seedlings in UAV RGB Images Based on GLI Automatic Annotation and Hybrid Architecture Deep Learning

Jinghe Wang, Qingfu Liang, Zaihong Yang, Xinjun Wang, Haoran Yang, Panfeng Wang, Shuhan Huang, Hanyu Cui, Chenyu Li, Pingan Jiang

Remote Sensing · 19.11.2026 · 18 (22) · 3984

DOI: 10.3390/rs18223984 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.11.2026. Verfasst von Jinghe Wang und 9 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Key Research and Development Project, Xinjiang Uygur Autonomous Region Major Science and Technology Special Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate detection of cotton seedlings is essential for monitoring crop establishment. However, manual annotation is time-consuming, and the quality of conventional automatic annotation methods is affected by illumination and background conditions. This study proposes a joint strategy combining green leaf index (GLI) automatic annotation with deep learning detection. Three annotation methods were considered: GLI, excess green minus excess red (ExG–ExR), and hue–saturation–value (HSV). Their nine combinations with three detectors (YOLOv10n, RT-DETR-L, and Mamba-YOLO-B) were evaluated using spatial data partitioning and independent cross-region testing. Under identical post-processing, GLI achieved the highest annotation quality, with an F1 score of 96.18% and a mean intersection over union (IoU) of 89.78% for matched boxes. For initial box drawing only, bounding boxes for 200 targets were generated in 0.399 s, compared with approximately 600 s for manual drawing. Detection accuracy was assessed using mean average precision (mAP) at IoU thresholds from 0.50 to 0.95 (mAP@0.5:0.95). Across three random seeds, Mamba-YOLO + GLI achieved the highest mean source-region mAP@0.5:0.95, at 0.8020. In cross-region testing, Mamba-YOLO + GLI achieved the best detection and counting performance, with an mAP@0.5:0.95 of 0.3446. However, its detection accuracy remained substantially lower than in source-region testing. These results demonstrate that GLI automatic annotation can provide effective training labels for cotton seedling detection. Among the evaluated combinations, Mamba-YOLO + GLI achieved the highest mean source-region mAP@0.5:0.95 and the highest cross-region mAP@0.5:0.95.

Förderung

  • Xinjiang Uygur Autonomous Region Key Research and Development Project
  • Xinjiang Uygur Autonomous Region Major Science and Technology Special Project

Zitieren

APA

Wang, J., Liang, Q., Yang, Z., Wang, X., Yang, H., Wang, P., Huang, S., Cui, H., Li, C., & Jiang, P. (2026). A Combined Strategy for Detecting Cotton Seedlings in UAV RGB Images Based on GLI Automatic Annotation and Hybrid Architecture Deep Learning. Remote Sensing, 18(22), 3984. https://doi.org/10.3390/rs18223984

Vancouver

Wang J, Liang Q, Yang Z, Wang X, Yang H, Wang P, et al. A Combined Strategy for Detecting Cotton Seedlings in UAV RGB Images Based on GLI Automatic Annotation and Hybrid Architecture Deep Learning. Remote Sensing. 2026;18(22):3984. doi:10.3390/rs18223984

BibTeX
@article{Wang2026,
  author = {Wang, Jinghe and Liang, Qingfu and Yang, Zaihong and Wang, Xinjun and Yang, Haoran and Wang, Panfeng and Huang, Shuhan and Cui, Hanyu and Li, Chenyu and Jiang, Pingan},
  title = {A Combined Strategy for Detecting Cotton Seedlings in UAV RGB Images Based on GLI Automatic Annotation and Hybrid Architecture Deep Learning},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {3984},
  doi = {10.3390/rs18223984}
}
Kostenlos starten →