“Hey CSIRO, what bug is this?” It’s a question we often hear. And, in a country home to 170 species of snakes and 2000 kinds of spider, it’s easier asked than answered.
So where do you go when you want the details on what’s creeping and crawling near you?
A collaboration with Data61 is seeing the construction of a tool that uses machine learning and citizen science to take the guesswork out of animal spotting.
A bug’s life
Nic and Murray Scarce know the benefit of being able to identify Australia’s wildlife.
“During one of her trips to Australia, my mother-in-law acted as a magnet for all of the country’s big-name insects,” jokes Mr Scarce. “The questions relating to their identification and danger levels were relentless. And, the fact that we didn’t have all the answers simply exacerbated the situation.”
They found that an online search failed to provide all of the facts in one place. Thus, the idea to create an instant identification app was born.
The tool allows users to take photos of a snake or spider from their smart device. A system trained with an algorithm then classifies it, providing information on the family, genus or species.
The artificially intelligent (AI) platform considers not only these images, but also additional information, like GPS location.
To teach the platform, hundreds of thousands of images of snakes and spiders were fed into the system. It was a sizeable task uniquely perfect for an AI solution.
“The visual differences between the two species can be quite subtle. We need a great deal of training data to adequately identify critters,” explains project lead and Data61 researcher Dr Matt Adcock.
The application aims to provide education and awareness for all Australians. And, as a wildlife safety tool, could ultimately save human and animal lives.
For the full version of this article head on over to our Algorithm blog.
10th August 2020 at 1:05 pm
Great initiative team! This will be very handy.