Imma Perfetto
Imma Perfetto is a science journalist at Cosmos. She has a Bachelor of Science with Honours in Science Communication from the University of Adelaide.
Australia is proudly home to some of the world’s most diverse and unique wildlife, but with that richness comes a market for illegal wildlife trafficking.
Existing techniques to detect illegally trafficked wildlife have involved X-ray scans, physical detections via border security, and use of biosecurity dogs.
Now, Australian scientists have found that 3D X-ray technology and artificial intelligence (AI) algorithms can be used together to detect trafficked wildlife hidden in luggage or other cargo.
The team created a 3D scanned ‘reference library’ for three classes of wildlife – lizards, birds, and fish – which they used to ‘teach’ artificial intelligence (AI) algorithms to detect the animals.
The AI achieved a detection rate of 82% with a false hit rate of just 1.6%.
The recently published study, in the journal Frontiers in Conservation Science Human-Wildlife Interactions, is the first to document the use of 3D x-ray CT scanning technology for wildlife protection.
Read more: Reptiles threatened by online trade.
“Taking animals from the wild poses risks to the species’ conservation, local populations, habitats and ecosystems, and stopping wildlife from being trafficked into Australia protects our unique natural environment from exotic pests and diseases,” says Sam Hush, acting Assistant Secretary for Environment Compliance at the Department of Climate Change, Energy, the Environment and Water (DCCEEW).
“It is also extremely cruel. Smuggled animals often suffer stress, dehydration or starvation and many die during transit. We have been working with the Department of Agriculture Fisheries and Forestry (DAFF) to test and validate the wildlife 3D x-ray and algorithms which have both proven to be very effective.”
There is also a biosecurity element. “Illegal wildlife trafficking poses a significant biosecurity risk to Australia as it could introduce pests and diseases that could impact on the environment, as well as human and animal health,” says Dr Chris Locke, Deputy Secretary of the Biosecurity and Compliance group at DAFF.
The research team used 3D X-ray CT technology using Real Time Tomography (RTT) in the study. This is a technique which uses X-rays to produce a series of image cross sections through an item, in this case an animal, which can be manipulated to provide a 360-degree view of it.
The already deceased specimens were scanned using a system used for explosive detection screening currently in use at international borders and around the world in airports and mail cargo facilities.
Read more: Should we keep native Australian animals as pets?
The library included 294 scans from 13 different species in different scenarios – from an animal on its own to more complicated and realistic trafficking scenarios – which was then used to teach AI algorithms to detect the animals.
“This paper demonstrates the boundless potential the 3D x-ray algorithm has in helping to stop exotic wildlife from being trafficked, protecting Australia’s agricultural industries and unique natural environment from exotic pests and diseases.
“This innovative technology is an invaluable complementary platform to our existing biosecurity and wildlife detection tools at Australian international borders, with potential worldwide applications in the future,” Locke says.