Computer Vision-Based Leaf Growth Monitoring System of Aeroponic-Grown Potato Plant

Abstract

Leaf area is a key indicator of plant health and development. However, manual measurement is time-consuming and labor-intensive, especially when monitoring aeroponic-grown potato plants with multiple leaves over extended periods. This study applied a computer vision-based system to automate leaf growth monitoring using the YOLO (You Only Look Once) v8 framework. A dataset was collected from a controlled aeroponic system: 25 images of young leaves (4,869 individual leaf segments) and 35 of mature leaves (12,368 segments). Based on evaluation of various YOLOv8 model configurations, the best model achieved a mask mAP@50 of 0.396 and 0.250 for young leaves and mature leaves, respectively. The challenge to track the mature canopy was due to severe leaf occlusion and self-similarity in dense foliage. Despite the challenge, this study demonstrates proof of concept for tracking early leaf growth and highlights the significant computer vision challenges posed by dense, mature canopies in aeroponic systems.

Plant phenotyping relevance

植物の葉面積・葉成長をコンピュータビジョンで自動追跡する手法の開発と評価が中心であり、植物表現型の取得方法を直接扱っている。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.