Study to train AI for koala ‘face recognition’ at crossings


Image Recognition

ARTICLE SOURCE

PublishedA team of Griffith University AI researchers will train cameras to use ‘facial recognition’ technology at koala crossing locations across South East Queensland to determine how koalas are using them and ultimately provide research-based planning to help protect the declining population. Associate Professor Zhou’s pilot study, ‘Predicting Koala Road Crossing Behaviours using AI-Powered Observation Network’, will be rolled out at koala crossing locations in the Redland City Council area with 20 cameras by the end of July 2021. “Previously, cameras have been set up to monitor the koala crossings but each of the captured video then had to be manually checked to see whether the animals filmed using the crossings were koalas or other species. Mitigating koala fatalities and injuries caused by vehicles was one of the most important tasks for koala conservation. This required a deeper understanding and a better prediction of koala road crossing behaviour, which relied on enhanced koala monitoring and tracking technology, according to Associate Professor Zhou.