Summary

The Australian ginger industry is regionally significant, employs local people in value added processing and had a farm-gate GVP of $32 million in 2015. The Australian Ginger Industry Association’s Industry Production Target aims to lift Australian ginger production from 8,000 to 12,000 tonnes per annum by 2021, while sustaining profitable farm gate prices. Key to achieving this is improving on-farm productivity.
Pests and diseases pose the largest production concern to most ginger growers and are a constant threat to yields. Fusarium, in particular, is a key threat to seed ginger stock, as it can be spread through soil from infected plant material. Identification and removal of diseased seed stock is a labour intensive process, attracting high direct labour costs.
This project will pilot the development of an automated system that aims to identify and sort Fusarium infected seed ginger stock. In doing so, the vision aligns with the Ginger Program’s R&D objective to drive on-farm productivity, and in particular the strategy to harness technological innovation.
The research team will work with ginger growers into a second project to implement, over a 12 month period, in South East Queensland, to ensure that the project outcomes are relevant and applicable across industry. In particular, we have been granted access to Templeton Ginger as a test site throughout all stages of the project, but will seek to work with other ginger growers through the Queensland Ginger Industry Alliance.

Program

Ginger

Research Organisation

Queensland University of Technology

Objective Summary

This project aligns with the Ginger Program’s R&D objective to drive on-farm productivity, by piloting the development of an automated pest and disease management strategy for seed ginger stock. It will harness technological innovation by investigating ginger production mechanisation opportunities, using an automated vision system. The objective is to develop and demonstrate an automated vision system that is capable of robustly identifying signs of Fusarium in seed ginger stock. The research challenges are:

1. Development of a vision system (hardware and algorithm) for robust real-time identification of the presence/absence of Fusarium in cut ginger
2. Automated identification of the bottom/root of each piece of ginger

• Each piece of ginger has a unique shape (i.e. non-uniform)
• Requires a vision-based manipulation task

The above research challenges are aimed at achieving an automation level for “sorting” diseased from non-diseased ginger. Whilst out of scope in this project, the technology developed in this project will provide the foundations for automated cutting ginger stock for inspection and removing disease from the ginger and slicing into seed pieces.