Researchers at an Australian university are set to trial the use of artificial intelligence facial recognition technology to monitor koala crossings to aid in the conservation of this iconic species.
In a statement on Tuesday, Griffith University said Associate Professor Jun Zhou will lead a team of artificial intelligence researchers in the two-year pilot study, which aims to set up an AI-based monitoring facility that will use a network of cameras to analyze how koalas are crossing busy roads.
Car accidents are one of the primary causes of death for koalas, making manmade "koala-crossings" that provide safe pathways across roads a regular feature in key koala habitats across Australia.
According to the Queensland government where the university is based, about 300 koalas are killed on the state's roads each year.
"Previously, cameras have been set up to monitor the koala crossings but each of the captured video(s) then had to be manually checked to see whether the animals filmed using the crossings were koalas or other species," said Zhou.
"Now, with artificial intelligence developing very quickly over the past 10 years, the technology is powerful enough to help recognize not only koalas generally, but which individual koalas are using the crossings using videos that have been trained by our AI."
The cameras will be rolled out at key koala crossing locations on roads near the state capital of Brisbane, with 20 cameras to be set up by the end of July.