Farmers may soon have a new weapon in their artillery to help fight against lantana by identifying the species early.
The research project conducted by CQU academic and AI specialist Wie Kiang Hi, developed a system, which uses deep learning algorithms to train the computer to be able to recognise the distinct features of lantana amongst other vegetation.
The model catalogues images and data sourced from existing locations where large numbers of the plants have been found.
Mr Hi had read that lantana was a huge issue for farmers in Australia and wanted to do something to help combat the problem.
Through his research he discovered that early detection of the plant had potential to minimise the spread, reducing the cost of eradication methods as well as preventing crop damage.
"This is akin to teaching the computer to 'see' and distinguish this invasive plant from other vegetation by analysing images," he said.
"I obtained substantial data from third-party sources. The data collection process involved sourcing diverse image datasets of lantana camara from reliable and established repositories and collaborating institutions."
The algorithm used for the project is called YOLO (You Only Look Once), which uses a 'one-shot' approach to enabling real time processing.
Whilst initial stages of research were focused on analysis and model development, there is potential for future on site farm fieldwork.
"My research endeavoured to offer practical solutions for farmers in the ongoing battle against invasive plants," he said.
"By providing an advanced tool for early detection and management, I hope to contribute to sustainable agriculture, preserve native ecosystems, and enhance the resilience of farming communities."
Mr Hi is currently looking for an industry partner to help fund the project .