Automated Image Analysis for Fluid Dynamics
Engineering, IT, Mathematics and Statistics
- Due to the sensitivity and security of this project, students must have Australian Citizenship to apply. Any applicants not meeting this requirement will automatically be deemed ineligible for this project.
- The Industry Partner has implemented appropriate preparations to comply with Federal and State Government requirements regarding COVID-19 safety. Due to remote arrangements, this internship is now accepting applications from eligible PhD students nationwide.
DST Group have developed proof of concept code using Matlab and Python, capable of extracting time resolved measurements of wake characteristics from videos of towing tank experiments and CFD simulations of multiphase flow around surface piercing objects. Currently this code is limited in the scope of its capability and requires further development to increase the range of characteristics that can be measured, and reduce the error in the automated measurement process.
RESEARCH TO BE CONDUCTED
- Investigate computer vision techniques readily available through open source libraries (such as OpenCV) and determine the suitability of these techniques to the application.
- Conduct research into novel CV techniques that may be suitable for the applications and implement in code as necessary.
- Develop Python based code to automate extraction of quantitative data from videos/images of experiments and CFD simulations, incorporating existing code as appropriate.
- Determine as appropriate, modifications that can be made to experimental techniques in order to facilitate improvements in ease and accuracy of data analysis.
SKILLS WISH LIST
We are looking for a PhD student with the following:
- Previous experience coding in Matlab or Python (Python preferred).
- Some familiarity with image processing and/or computer vision techniques and libraries is preferred.
- Familiarity with fluid dynamics and computational fluid dynamics is advantageous but not required.
- Delivery of a report outline the capabilities and limitations of various techniques for automatic analysis of experimental data and providing recommendations on the best approaches for the application.
- Delivery of software capable of automating quantitative data extraction from raw experimental data (images and videos).
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
CONNECT WITH APR.INTERN