What you'll receive
- a scholarship between $37,000 and $40,000 per year for 3 years (consisting of a base stipend of $27,000 and a top-up between $10,000 and $13,000) with a possible extension of 6 months
- up to $5,000 per year for project costs (to be agreed between CSIRO and QUT on a case by case basis). Additional funding for project costs up to a further $5,000 per year may also be available, if required, from CSIRO on a case by case basis.
International students will also receive a fee sponsorship.
You'll also get the opportunity to work on a cutting-edge project in the area of Deep Machine Learning for Image Classification.
- meet QUT’s PhD admission criteria(PDF file, 235.7 KB)
- Degree in Electrical Engineering and/or Computer Science with 1st Class Honours
- Sound knowledge of Machine Learning, Computer Vision and Image Processing and strong programming skills is desirable.
How to apply
Submit your application to the supervisor of the project you are interested in.
Your application must include:
- a cover letter
- an up-to-date curriculum vitae (CV)
- full academic transcript
- a summary (up to 2 pages) of your scientific career, including:
- a summary of your final project from your most recent degree
- a paragraph on your research interests
- contact details of 3 referees (email, address and phone numbers).
- If your application is successful at this stage, you will be asked to complete an application form.
What happens next?
This scholarship will stay open until a suitable candidate is found.
If your application is not successful, we'll notify you by email.
For more information about the application process please contact Prof Sridha Sridharan via email firstname.lastname@example.org
QUT Supervisors: Prof Sridha Sridharan and Prof Clinton Fookes
CSIRO Supervisor: Dr Peyman Moghadam and Dr Everard Edwards
About the scholarship
Title: Deep learning for Hyperspectral Image Classification.
Hyperspectral imaging is one of the rapidly growing domains in remote sensing primarily due to the breadth of applications on a variety of areas, from plant disease detection to object tracking. For example, hyperspectral imaging provides an opportunity to develop fast and non-invasive methods of detecting plant diseases and potentially discriminating between different disease types (e.g. virus, fungus, bacteria) before the human eye can see them.
The principal aim of this PhD research program is to develop methods to improve the hyperspectral image classification using deep learning techniques. The developed systems will be evaluated on their ability to detect plant diseases and potentially discriminating between different disease types using the hyperspectral imaging dataset which has been already collected by CSIRO.
Other applications of hyperspectral classification based on publicly available data will also be investigated to benchmark the developed techniques with state of the art.