Did you know that the Moggill Koala Rehabilitation Centre and the Lone Pine Sanctuary in Fig Tree Pocket are harnessing the power of Artificial Intelligence (AI) by using facial recognition technology to help save the koalas?
Efforts to bolster the survival of koalas are now complemented by the innovative work of a team of Griffith University AI researchers and ecologists, who have secured funding to advance their ‘facial recognition’ camera technology at koala crossing locations across South East Queensland (SEQ).
For the third consecutive year, these researchers are working to deploy state-of-the-art “facial recognition” camera technology at strategic koala crossing locations across SEQ.
This groundbreaking initiative aims to monitor and understand how koalas utilise these crossing points, ultimately providing invaluable research-based insights to help safeguard this declining population.
Leading this pioneering study is Professor Jun Zhou from Griffith’s School of Information and Communication Technology. The project’s inception was made possible by a $90,000 Community Sustainability Action Grant awarded by the Queensland Government’s Department of Environment and Science in March 2021, followed by an additional $100,000 grant from DES in June 2023.
“This project extends our innovative AI-powered koala monitoring system to cover wider areas of koala habitat in South East Queensland, and engage with 14 local community groups across 10 local government areas to facilitate the installation and maintenance of the camera network,” Professor Zhou shared.
In July 2021, the team successfully deployed 24 AI-powered cameras at strategic koala crossing locations within the Redland City Council area. These cameras automatically activate in response to koala movement, capturing hundreds of videos and images which are then transmitted to a server at Griffith University.
The AI technology developed by the research team studies these videos and images, enabling it to identify individual koalas.
Caroline Moss, Queensland Rail Group Senior Manager Environment & Sustainability, emphasized the significance of this research.
“A research project like this helps us to understand how this technology can be applied, not only here in the Redlands, but where appropriate in other locations, given that Queensland Rail operates a really large network,” she said.
To ensure the AI can accurately distinguish one koala from another based on their appearance and movements, the research team collaborated closely with conservation groups such as the Koala Action Group Redlands, Daisy Hill Koala Centre, Moggill Koala Rehabilitation Centre, and Currumbin Wildlife Sanctuary.
“We can see from the data that koalas are in trouble here. They’ve recently been listed as endangered in Australia, and Southeast Queensland was formally a hotspot. The driver of that decline has been urbanisation,” Dr. Douglas Kerlin, a co-researcher, said.
The research project is particularly relevant during the breeding season when koalas face increased risks, including collisions with vehicles.
“We’re all about sharing information, and it’s really good to be able to put people in contact and create that conduit between researchers so that everyone can get to the same goal faster,” Frank Mikula from Lone Pine Koala Sanctuary near Kenmore, highlighted the importance of collaboration.
“The technology does the heavy lifting for us, and that’s really important moving forward.
“With increased knowledge about how koalas are crossing roads, we can better inform mitigation and management so that we can ensure a better long-term future for koalas.”
Published 2-Oct-2023
