What’s happening?
What’s happening?
A field trial on the Redlands Coast has confirmed that a prototype artificial intelligence camera built into a smart road sign can detect a koala crossing a road in real time.
The system forms part of research led by Griffith University that aims to improve wildlife monitoring at high use transport crossings.
Researchers from Griffith’s School of Information and Communication Technology carried out the trial with partners including the New South Wales Department of Climate Change, Energy, the Environment and Water, Telstra and Redland City Council.
The project is part of a broader initiative funded under the New South Wales Koala Strategy, which supports efforts to reduce koala road fatalities and assist population recovery.
The technology analyses live video footage using artificial intelligence to identify koalas as they move near or across roads.
The successful detection during the trial confirmed the system can operate effectively in real road environments.
Why it matters
Traditional wildlife road signs are static and often fail to reflect the unpredictable nature of koala movement.
Deputy Head of the School of ICT, Professor Jun Zhou, said repeated exposure to static signs can reduce driver attention.
“Drivers become desensitised after repeated exposure to signs without encountering wildlife, reducing their responsiveness when real hazards arise,” Professor Zhou said.
“This issue is further amplified during low-light conditions, particularly between dusk and dawn, when koalas are most active, and visibility is poor.”
Koalas continue to face serious threats, including habitat loss, disease, dog attacks and road mortality.
Urban development has increased the likelihood of koalas crossing roads, raising the risk of vehicle strikes.
Professor Zhou said the successful detection confirmed the system’s potential.
“The successful detection of a koala proves the concept works,” Professor Zhou said.
“With further investment, this pilot can be expanded into a scalable solution that protects more wildlife and improves public safety across high-risk corridors.
“This is more than a tech milestone; it’s a turning point. We now have the ability to intervene before tragedy strikes. Expanding this system could be a game-changer for koala conservation and road safety.”
“By creating responsive infrastructure that adapts to koala behaviour, we’re aiming to reduce road fatalities and safeguard one of Australia’s most iconic species.”
Local impact
The technology trial took place on the Redlands Coast, where koalas regularly move through areas near roads.
The development follows research contributed by Griffith University’s Dr Douglas Kerlin.
His research found the koala population in Redland City Council had stabilised, with no evidence of continued decline since 2018.
Redland City Council Mayor Jos Mitchell said the findings reflected years of investment in conservation and research.
By the numbers
-
Since March 2025, Griffith University researchers have been trialling the AI detection system on the Redlands Coast. The system uses edge computing and real-time video analysis to detect koalas approaching or crossing roads.
-
One real-time koala detection was successfully recorded during the trial. This detection confirmed the technology can identify koalas in real world road environments.
-
Since 2018, research led by Dr Douglas Kerlin has found the koala population within Redland City Council has stabilised, with no evidence of continued decline.
Zoom in
The system uses edge computing, a decentralised IT architecture that processes data near its source.
Combined with real-time video analysis, the technology can identify koalas as they approach or cross a road.
Researchers say the detection provides a foundation for future systems that could activate roadside warning signs and improve driver awareness.
Zoom out
Wildlife vehicle collisions remain a major threat to koalas across Australia.
Technology that detects wildlife movement and alerts drivers could become an important tool in reducing road deaths and improving road safety.
What to look for next
Further development could allow the system to trigger roadside warning signs when koalas are detected.
Researchers are continuing to assess the trial as a potential model for wider deployment across high-risk wildlife corridors.
