A new automated method based on deep-learning techniques will provide coaches and teams with a tool to help assess defensive athletic performance in all game situations, according to researchers at the California Institute of Technology and Disney.
The new method analyzes detailed game data on player and ball positions to create models, or "ghosts," of how a typical player would behave when an opponent is attacking. Users can then visually compare what a team's players actually did during a defensive play compared to what the ghost players would have done.
The method is based on data from 100 games of professional soccer, but the researchers note it also could apply to other sports, such as football and basketball.
The researchers relied on deep learning, which uses brain-inspired recurrent neural networks, to examine the recent history of player actions to make predictions of subsequent actions.
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA