Invited Talks

In team sports, players move in complex but surprisingly predictable ways. With state-of-the-art computer vision and machine learning methods, it is now possible to collect sufficiently large player tracking datasets and learn patterns of how players actually move. In this talk, I will describe how this knowledge has been used at Disney Research to generate new analytics and sports broadcasting tools. As an example, I will detail how a sporting event can be recorded automatically with robotic cameras driven by realtime player tracking data. Peter Carr is a research engineer at Disney Research, Pittsburgh. He received his PhD from the Australian National University in 2010, under the supervision of Richard Hartley. His thesis, Enhancing Surveillance Video Captured in Inclement Weather, explored single-view depth estimation using graph cuts, as well as real-time image processing on graphics hardware. As part of his earlier PhD work in sports analysis, Carr was a research intern at Mitsubishi Electric Research Labs. He received a Master's Degree in physics from the Centre for Vision Research at York University in Toronto, Canada, and a Bachelor's of Applied Science (engineering physics) from Queen's University in Kingston, Canada.