EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning–based high-throughput phenotyping for tiller quantification in interspecific bentgrass hybrids using YOLOv8

Dennis W Ferm, Yonghyun Kim, Jinyoung Y Barnaby

Frontiers in Plant Science · 01.05.2026 · 17

DOI: 10.3389/fpls.2026.1810220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 01.05.2026. Verfasst von Dennis W Ferm und 2 weiteren Autor:innen. Beteiligte Einrichtung: Floral and Nursery Plants Research Unit, U.S. National Arboretum, Agricultural Research Services, United States Department of Agriculture, Beltsville…. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Tiller production is a critical determinant of turfgrass canopy density and plant performance, yet manual tiller counting is too labor-intensive for large breeding programs.

Methods

To address this limitation, we evaluated 770 plants from an interspecific bentgrass hybrid population and developed three automated approaches for tiller quantification: a classical edge-based segmentation pipeline and two deep-learning models, Faster R-CNN and YOLOv8. Using a large annotated image dataset, we assessed each method’s accuracy, robustness under occlusion, and computational efficiency.

Results

Although two-stage detectors are often expected to provide superior precision for complex plant structures, the one-stage YOLOv8 model achieved the highest accuracy (R² = 0.97) and processed images substantially faster than Faster R-CNN, while both the edge-based method and Faster R-CNN showed reduced performance in dense canopies.

Discussion

These findings demonstrate that recall-oriented one-stage detection can outperform more complex two-stage models for phenotyping tasks involving fine, highly occluded structures. The resulting workflow provides a reliable, high-throughput solution for generating biologically meaningful tiller counts and offers a transferable framework for integrating image-derived phenotypes into genetic analyses and breeding pipelines across grass species.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8bentgrass hybridscomputer visiondeep learningfaster R-CNNhigh-throughput phenotypingtiller quantificationturfgrass breeding

Autor:innen und Institutionen

  • Floral and Nursery Plants Research Unit, U.S. National Arboretum, Agricultural Research Services, United States Department of Agriculture, Beltsville, MD, United States.

Zitieren

APA

Ferm, D. W., Kim, Y., & Barnaby, J. Y. (2026). Deep learning–based high-throughput phenotyping for tiller quantification in interspecific bentgrass hybrids using YOLOv8. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1810220

Vancouver

Ferm DW, Kim Y, Barnaby JY. Deep learning–based high-throughput phenotyping for tiller quantification in interspecific bentgrass hybrids using YOLOv8. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1810220

BibTeX
@article{Ferm2026,
  author = {Ferm, Dennis W and Kim, Yonghyun and Barnaby, Jinyoung Y},
  title = {Deep learning–based high-throughput phenotyping for tiller quantification in interspecific bentgrass hybrids using YOLOv8},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1810220}
}
Kostenlos starten →