A preliminary evaluation of machine vision sensing of cotton nodes for automated irrigation control

摘要

Real-time sensing of crop water stress is required to implement site-specific irrigation that responds to crop water needs. This project aims to develop a real-time, plant-based sensor for cotton water stress that has potential use on a variable-rate LMIM which adjusts water application in response to real-time irrigation requirement. A number of plant attributes may be used to infer water stress in cotton. Nodes above white flower and distance between the fourth and fifth mainstem nodes are being targeted in this project because these attributes indicate the balance between vegetative and reproductive growth that is required during crop flowering to optimise yield for cotton.