A Robust Tomato Counting Framework for Greenhouse Inspection Robots Using YOLOv8 and Inter-Frame Prediction

Abstract

Accurate tomato yield estimation and ripeness monitoring are critical for optimizing greenhouse management. While manual counting remains labor-intensive and error-prone, this study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments. The proposed method integrates YOLOv8-based detection, depth filtering, and an inter-frame prediction algorithm to address key challenges such as background interference, occlusion, and double-counting. Our approach achieves 97.09% accuracy in tomato cluster detection, with mature and immature single-fruit recognition accuracies of 92.03% and 91.79%, respectively. The multi-target tracking algorithm demonstrates a MOTA (Multiple Object Tracking Accuracy) of 0.954, outperforming conventional methods like YOLOv8+DeepSORT. By fusing odometry data from an inspection robot, this lightweight solution enables real-time yield estimation and maturity classification, offering practical value for precision agriculture.

Plant phenotyping relevance

温室ロボット向けの画像解析フレームワークを中心に、トマト果実の計数、成熟度分類、収量推定という植物器官・状態の定量手法を開発・評価しているため。

Code and data availability

The paper describes a tomato counting framework with a custom greenhouse image dataset (3000 labeled images, 15,000 augmented) and YOLOv8-based analysis, but provides no public data or code. The Data Availability Statement reads 'Not applicable', no repository, DOI, or URL for datasets, code, or models is given, and no

No evidence-backed public reproduction asset is currently recorded.