Real-Time Root Monitoring of Hydroponic Crop Plants: Proof of Concept for a New Image Analysis System

Abstract

This paper presents a new autonomous system that allows for the capturing and analysis of root systems of hydroponic crop plants without removing them from the growing environment. Disturbing the delicate roots of these plants can cause stress and increase the chance of mechanically spreading diseases. The first task carried out was the taking of simple measurements of root thickness and assess the feasibility of this concept. The second task involved inflicting two of four plants with an arbitrarily chosen plant sickness, in this case aluminum toxicity, and autonomously capture pictures of each plant over the course of approximately three weeks. Then, image analysis and machine learning techniques were applied to identify sick plants from healthy plants.