This project will investigate methods to monitor wildlife using machine learning applied to aerial imagery.
While it's highly desirable to use drones and aerial footage to monitor wildlife, there are substantial challenges created by the nature of the data and target wildlife.
This, combined with the vast nature of any collected aerial data, makes manual analysis difficult. This challenge motivates the development of machine learning methods to automatically process data and perform tasks, such as:
- detecting target animals
- counting herd animals
- classifying land use
- assessing environment health.
As part of the research project, you will:
- investigate and deploy machine learning algorithms for tasks including object detection, object counting and scene segmentation
- investigate improvements to the deployed algorithms to enhance performance
- benchmark developed algorithms and assess accuracy/performance.
The outcomes of this work will include:
- one or more algorithms that are trained and deployed on aerial wildlife data
- performance benchmarks for the deployed algorithm(s).
Skills and experience
Strong programming experience, especially with Python, is ideal.
Some prior machine learning or computer vision experience is desirable, but not mandatory.
Contact the supervisor Dr Simon Denman for more information.