- Project Title: Profiling athlete’s throwing mechanics from video using high precision computer vision.
- Partner Organisation: Queensland Academy of Sport (QAS)
- PhD Candidate at QUT
- Supervisors: Associate Professor Simon Denman, Dr Maryam Haghighat
Ryan grew up in Brisbane, Queensland, and completed a double degree in Engineering (Mechatronics) and Information Technology (Computer Science) at QUT in 2024. During his time at university, he developed a strong interest in deep learning and computer vision. Outside of his academic pursuits, Ryan enjoys self-studying Japanese, 3D modelling, and 3D printing.
What made you interested in this program?
After completing my dual degree, I was eager to apply machine learning and computer vision to real-world challenges. The NGGP program stood out to me for its strong industry connections and its focus on delivering practical, impactful solutions. I was also drawn to the program’s inclusion of biomechanics, a field I find fascinating. The opportunity to work on projects that combine biomechanics with machine learning was what really sparked my interests.
What research question are you looking forward to exploring?
I’m excited to explore how video-based machine learning can be used to provide near real-time pose estimation and biomechanical analysis for athletes in throwing sports. Specifically, I want to investigate how accurately and reliably a markerless system can capture human poses compared to traditional marker-based methods. From this, develop a state-of-the arts pipeline that delivers immediate, actionable feedback to athletes and coaches to help improve athlete technique and track long-term development for throwing sports.
Fun fact about yourself?
I am pretty good at ice skating/roller skating!