EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cotton Boll Extraction and Boll Number Estimation from UAV RGB Imagery Before and After Defoliation

Na Su, Maoguang Chen, Caixia Yin, Ke Wang, Siyuan Chen, Zhenyang Wang, Liyang Liu, Yue Zhao, Qiuxiang Tang

Agronomy · 14.03.2026 · 16 (6) · 617

DOI: 10.3390/agronomy16060617 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 14.03.2026. Verfasst von Na Su und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Major Science and Technology Project, National Modern Agricultural Industry Technology System-Cotton Industry Technology System, Xinjiang Agriculture Research System-03.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate cotton boll identification and boll number estimation from UAV imagery are essential for large-scale yield prediction and precision management, yet severe leaf occlusion and complex canopy backgrounds often hinder robust performance. Here, UAV RGB images were acquired 3 days before defoliant application and at 3, 6, 9, 12, 15, and 18 days after defoliation. Cotton bolls were extracted using Mahalanobis distance, a support vector machine, and a neural network. Boll number was then estimated using an improved random forest model with multi-feature fusion. Across all defoliation stages, the NN produced the most accurate and stable boll extraction, achieving a maximum Kappa of 0.914, an overall accuracy of 95.77%, and an F1 score of 0.96. Extraction accuracy increased rapidly from 3 to 9 days after application and stabilized from 12 to 18 days. For boll number estimation, fusing the boll pixel ratio with color indices and texture features improved accuracy and consistency over time; the best performance was obtained at 18 days after application (R2 = 0.7264; rRMSE = 4.9%). Overall, imagery acquired 15–18 days after defoliation provided the most reliable estimation window, supporting operational pre-harvest assessment and harvest-timing decisions.

Förderung

  • Xinjiang Uygur Autonomous Region Major Science and Technology Project
  • National Modern Agricultural Industry Technology System-Cotton Industry Technology System
  • Xinjiang Agriculture Research System-03
  • Xinjiang “Tianshan Talents” Training Program

Zitieren

APA

Su, N., Chen, M., Yin, C., Wang, K., Chen, S., Wang, Z., Liu, L., Zhao, Y., & Tang, Q. (2026). Cotton Boll Extraction and Boll Number Estimation from UAV RGB Imagery Before and After Defoliation. Agronomy, 16(6), 617. https://doi.org/10.3390/agronomy16060617

Vancouver

Su N, Chen M, Yin C, Wang K, Chen S, Wang Z, et al. Cotton Boll Extraction and Boll Number Estimation from UAV RGB Imagery Before and After Defoliation. Agronomy. 2026;16(6):617. doi:10.3390/agronomy16060617

BibTeX
@article{Su2026,
  author = {Su, Na and Chen, Maoguang and Yin, Caixia and Wang, Ke and Chen, Siyuan and Wang, Zhenyang and Liu, Liyang and Zhao, Yue and Tang, Qiuxiang},
  title = {Cotton Boll Extraction and Boll Number Estimation from UAV RGB Imagery Before and After Defoliation},
  journal = {Agronomy},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {617},
  doi = {10.3390/agronomy16060617}
}
Kostenlos starten →