A team of Griffith University AI researchers will train cameras to use ‘facial recognition’ technology at koala crossing locations acrossSouth EastQueenslandtodeterminehow koalas are using them and ultimately provideresearch-basedplanningto help protect the declining population.
Associate Professor Jun Zhou, from Griffith’s School of Information and Communication Technology, will lead the two-year pilot study which is funded by a Community Sustainability Action Grant awarded to the team by the Queensland Government’s Department of Environment and Science in March 2021.
The $90,000grant program, Koala Applied ResearchSouth EastQueensland (SEQ), allocatesfunding to eligible recipients to undertake practical and appliedresearch projects into koala habitat protection and restoration, threat mitigation andcommunity partnerships to support the long-term conservation of koalas in SEQ.
Associate Professor Zhou’s pilot study,‘Predicting Koala Road Crossing Behaviours using AI-Powered Observation Network’, willbe rolled out atkoala crossing locationsin the Redland City Council areawith20camerasby the end of July 2021.
“The goal of this project is to set up an AI-based monitoring facility to monitor the koalas’ road crossing behaviours, so that we can analyse how many koalas are using the facilities to cross the road using underground pathways or the above-road crossings,” he said.
“Previously, cameras have been set up to monitor the koala crossings buteach of the captured videothen had tobemanually checkedto seewhether the animals filmed using the crossings were koalas or other species.
“Now, with artificial intelligence developing very quickly over the past 10 years, the technology is powerful enough to help recognise not only koalas generally, but which individual koalas are using the crossingsusing videos that have been trained by our AI.
“Thislastgoalis quite challenging, butwe hope the researchand collaboration with wildlife organisationswillmake it possible.”
As the AI needs to recognise individual koalas using the crossing at monitoring sites, the research team plans to work closely with conservation groups such as Koala Action Group, Daisy Hill Koala Centre, Moggill Koala Rehabilitation Centre and Currumbin Wildlife Sanctuary to train the technology to distinguish one koala to another based on their appearance and movements.
From 1997-2018, an average of 356 koalas entered care facilities due to vehicle collisions each year. Mitigating koala fatalities and injuries caused by vehicleswas one of the most important tasks for koala conservation.
This requireda deeper understanding and a better prediction of koala road crossing behaviour, which reliedonenhancedkoala monitoring and tracking technology, according to Associate Professor Zhou.
“In this study, networks of interconnected deviceswill be deployed, with each deviceintegrating a camera, a motion sensor, a wireless/mobilenetwork module, and a solar panel, in the vicinity of roadcrossing structures,” he said.
“Animal movement will trigger imagecapture, with images transferred to a server at GriffithUniversity. Computer vision and machine learning systemswill be used to process images, allowing for automaticdetection and recognition of individual koalas.”
Thisdatawouldthen be analysedby the teamto provideagreater understanding ofkoalas’use of crossing structures and help to design andoptimise the location of fauna mitigation measures onroads, while working with governments, local councils and transport departments.