The South Australian government has partnered with Flinders University and conservation group Koala Life to use drones and facial recognition technology to count, identify and re-identify koalas.
The non-invasive koala monitoring technique is used as part of a study of koalas on Kangaroo Island and the Adelaide Mount Lofty Ranges to understand their numbers, movements, behavior, and physiology, and to assess whether koalas are showing signs of stress.
âThe use of drones in animal research is widely used to monitor koalas across Australia, especially Queensland. Until now, potential behavior and physiological effects have not been fully researched so we are one of the few groups studying this, âsays Dr Diane Colombelli-NÃ©grel said.
âThrough this research, we can determine whether this method has really little effect on koalas and whether it is suitable for the future in the long term.
âKoalas are declining in parts of Australia. And while the numbers in South Australia are pretty good, the recent fires have reduced the numbers dramatically.
“We need to make sure we are aware of the new numbers and how they will recover from fires so that we can then work to reduce the impact that is affecting their survival.”
According to Minister for Environment and Water David Speirs, this approach will be very different from traditional methods in which each koala is caught and individually tagged.
“It is very important for us to develop non-invasive techniques to monitor animals in a safe manner, and facial recognition through drone monitoring uses the latest technology to achieve this,” he said.
“The ability to recognize individual members of a species in the wild will help develop an understanding of individual movements as well as population estimates, and this understanding will enable the development of meaningful management strategies.”
In the middle of last year, researchers in Queensland began using AI-enabled infrared drones to provide more accurate estimates of the number of surviving koalas in the areas affected by bushfires.
Research showed that the use of drones and infrared imaging was more reliable and less invasive than traditional livestock surveillance techniques, such as people looking up at trees or dogs coming in to sniff out koalas.
The same group from Queensland University of Technology (QUT) set up an AI hub last month to expand their conversational work.
Research lead Grant Hamilton said setting up the AI ââhub would now allow the team to expand the system and work with local talkgroups and organizations like Landcare who can help with using the drones and thermal imaging to find bushfire-hit areas on koalas before sending the raw data back to the QUT hub for analysis.
The system is initially being tested with Noosa and District Landcare and Watergum, who will be conducting drone surveys to produce a census of koalas and other endangered species in the area.
Their plans are to eventually expand the system to other community groups across the country, QUT said.
Meanwhile, the New South Wales government has been using AI software to detect intruders on the Sydney rail tunnel network.
The AI ââsystem was integrated into the existing CCTV infrastructure in the city’s subway stations, said NSW Transport Minister Andrew Constance.
âDo not enter our tunnels under any circumstances. When you do, you will be captured by artificial intelligence software trained to identify people entering tunnel areas on CCTV and immediately notify the Sydney Trains security team, âhe said.
“This technology is already working, seven intruders were caught trying to get into tunnels from the platforms. The security staff was always able to react quickly without anyone being injured.”