Barley Head Detection Using UAV Imagery and YOLOv10

Abstract

Abstract Barley head detection is a crucial task for agricultural applications such as yield estimation and crop monitoring. Unlike wheat, automated barley head detection has not been extensively studied due to challenges posed by its complex head structures and the lack of annotated datasets. In this paper, we leverage YOLOv10, a state-of-the-art object detection framework, to detect barley heads from high-resolution images captured using UAVs. Our dataset, consisting of UAV-captured images and supplemented with the Global Wheat Head Dataset, provides a robust foundation for model training. The proposed approach achieves a mean Average Precision of 0.83 at Intersection of Union 0.5, setting a new benchmark for barley head detection. This work contributes to advancing automated crop monitoring systems in precision agriculture.

Plant phenotyping relevance

UAV画像からオオムギ穂を検出するYOLOv10手法とデータセットを中心に開発・評価しており、植物器官の画像ベース表現型取得に該当する。

Code and data availability

The paper describes a novel UAV barley head dataset (80 images, ~5,000 annotated heads) and a YOLOv10 model, and states the dataset is publicly available, but no actual public URL, repository, or identifier for the dataset or trained model appears in the supplied blocks. The only URL present (app.hasty.ai) is the third

No evidence-backed public reproduction asset is currently recorded.