Researchers at Disney, California Institute of Technology and STATS, a supplier of sports data developed a deep learning-based technique that provides coaches and teams with a quicker tool to help assess defensive athletic performance in any game situation.
The method analyzes game data on player and ball positions to create models, or “ghosts,” of how a typical player in a league or on another team would behave when an opponent is on the attack. It is then possible to visually compare what a team’s players actually did during a defensive play versus what the ghost players would have done.
“With the innovation of data-driven ghosting, we can now, for the first time, scalably quantify, analyze and compare detailed defensive behavior,” said Peter Carr, research scientist at Disney Research.
“Our approach avoids the need for manual input,” Carr said. “Our ghosting model can be trained in several hours (using Tesla K80s GPUs and cuDNN), after which it can ghost every play in real-time. Because it is fully automated, we can easily learn models for different subsets of data, such as all the games of a particular team.”
The researchers leveraged techniques from deep imitation learning, a tool that is able to learn from demonstrations and has proven useful in robotic applications, said Yisong Yue, assistant professor of computing and mathematical sciences at Caltech, to address the issue of the deep learning predictions tended to veer from truth.