EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Stage-Aware Cascaded Detection–Segmentation Framework for Leaf Phenotyping and Leaf Dry Biomass Estimation of Pepper Seedlings

Han Li, Dongyuan Shi iD, Hui Shi, Ming Li iD, Ming Diao iD

Plants · 20.06.2026 · 15 (12) · 1912

DOI: 10.3390/plants15121912 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plants, online erschienen am 20.06.2026. Verfasst von Han Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Agriculture, Shihezi University, Shihezi 832003, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shihezi University, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantitative phenotyping of pepper seedlings is important for greenhouse plug tray seedling cultivation, but it remains constrained by inefficient manual monitoring, complex greenhouse backgrounds, and growth-stage-dependent discrepancies between two-dimensional image traits and actual leaf biomass. In this study, a cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping. The framework integrated Visual Dynamic Momentum YOLO (VDM-YOLO) for individual seedling localization and growth-stage recognition, Variance Guided Strip Ghost Gated UNet (VSG-UNet) for lightweight, high-resolution leaf segmentation, and a stage-aware correction model for leaf dry biomass estimation. In performance evaluation, VDM-YOLO achieved a mean average precision at an intersection over union threshold of 0.5 (mAP0.5) of 89.27%, improving mAP0.5 by 1.82 percentage points over YOLOv12. VSG-UNet achieved a mean intersection over union (mIoU) of 83.9% and a Dice coefficient of 81.8%, while reducing floating point operations (FLOPs) and parameters by 44.2% and 61.2%, respectively, compared with U-Net. After stage-aware calibration, the coefficient of determination (R2) between segmented area and leaf dry weight increased from 0.764 to 0.813, and the root mean square error (RMSE) decreased from 0.0210 g to 0.0190 g. These results demonstrated that the proposed framework provided a proof of concept approach based on RGB images for the nondestructive assessment of leaf area and leaf dry biomass in pepper seedlings under restricted experimental conditions.

Schlagwörter

Stichwörter der Autor:innen

deep learningleaf dry biomass estimationpepper seedlingsphenotypic correctionsemantic segmentation

Autor:innen und Institutionen

  • College of Agriculture, Shihezi University, Shihezi 832003, China.
  • Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China.
  • Department of Informatics, University of Almería, CeiA3, CIESOL, 04120 Almería, Spain.

ORCID-Profile: Dongyuan Shi, Ming Li, Ming Diao

Förderung

  • Shihezi University
  • National Key Research and Development Program of China

Zitieren

APA

Li, H., Shi, D., Shi, H., Li, M., & Diao, M. (2026). A Stage-Aware Cascaded Detection–Segmentation Framework for Leaf Phenotyping and Leaf Dry Biomass Estimation of Pepper Seedlings. Plants, 15(12), 1912. https://doi.org/10.3390/plants15121912

Vancouver

Li H, Shi D, Shi H, Li M, Diao M. A Stage-Aware Cascaded Detection–Segmentation Framework for Leaf Phenotyping and Leaf Dry Biomass Estimation of Pepper Seedlings. Plants. 2026;15(12):1912. doi:10.3390/plants15121912

BibTeX
@article{Li2026,
  author = {Li, Han and Shi, Dongyuan and Shi, Hui and Li, Ming and Diao, Ming},
  title = {A Stage-Aware Cascaded Detection–Segmentation Framework for Leaf Phenotyping and Leaf Dry Biomass Estimation of Pepper Seedlings},
  journal = {Plants},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {1912},
  doi = {10.3390/plants15121912}
}
Kostenlos starten →