Honours Project: Can machine learning be used to accurately identify wildlife in remote camera trap images?

This Honours project with Sydney University and the Office of Environment and Heritage NSW will explore how machine learning be used to accurately identify wildlife in remote camera trap images. Apply now

Date published: 2019/05/03

Motion-active or remote camera traps are now commonly used in wildlife studies around the globe. They are a powerful and cost-effective method to survey wildlife due to their ease in deployment and ability to continually monitor populations across time. However, a common limitation of camera traps is that they capture millions of images that need to be processed visually by an observer. Machine learning techniques provide a powerful and exciting opportunity to automate image processing; thereby reducing analysis and reporting time. The time gained by implementing an automated image processing pipeline and increase speed of reporting results can be used for on-ground species conservation management.

This project will work closely with WildCount, a large-scale wildlife monitoring program run by the Office of Environment and Heritage, NSW Government and the School of Life and Environmental Sciences, University of Sydney. It will test the feasibility of using machine learning algorithms for identifying species in camera trap images.

For further information, please contact Dr Aaron Greenville, School of Life and Environmental Sciences, University of Sydney.

Superb lyrebirds. Kindly provided by WildCount, Office of Environment and Heritage, NSW

if you're just starting out in your conservation tech career, you should join our Early Career group! 

Continue the discussion… Early Career