- Head of Computer Vision and Machine Learning at the Australian Institute of Sport
- Associate Professor in Computer Science at La Trobe University
- Adjunct Associate Professor in Computer Science at Queensland University of Technology
- 18 years’ experience in computer sciences and sports analytics in high performance sport, including work with numerous high profile international teams at World Championships and Olympic Games.
Our research team consists of full time staff appointed at the Australian Institute of Sport and La Trobe University, as well as three PhD students, two postdoctoral fellows, and several research assistants. Our team currently focuses on gaining competition insight from pose analysis, action recognition and player tracking data using deep learning and other machine learning techniques. We have developed fully-autonomous convolutional neural networks capable of understanding key performance metrics in swimming races, such as instantaneous velocity, stroke rate, stroke length and other pacing features. Additionally, our work includes a semi-autonomous player tracking system capable of detecting and tracking sports players in complex environments. Other work has focussed on autonomously detecting, tracking and classifying diving performance in training and competition, meta-learners capable of recognising multi-agent actions in sport, and 3D pose analysis.
- Wei, X; Lucey, P; Morgan, S; Sridharan, S. (2013) “Sweet-Spot”: Using Spatiotemporal Data to Discover and Predict Shots in Tennis”, MIT Sloan Sports Analytics Conference, Boston.
- Lucey, P; Bialkowski, A; Carr, P; Morgan, S; Matthews, I; Sheikh, Y. (2013) “Representing and discovering adversarial team behaviours using player roles” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
- Wei, X; Lucey, P; Morgan, S; Reid, M; Sridharan, S. (2016) “The Thin Edge of the Wedge: Accurately Predicting Shot Outcomes in Tennis using Style and Context Priors”, MIT Sloan Sports Analytics Conference, Boston.