Computer scientists at Loughborough University have engineered artificial intelligence (AI) algorithms that can analyze football (that's soccer for you fellow Americans) players' abilities on the field. Dr. Baihua Li, the project lead, says the novel technology could revolutionize the sport by effectively enabling teams to properly identify the right talent to recruit.
Currently, player performance analysis is a long and labor-intensive process that sees an individual watch many video recordings of a player's performances. This process is time-consuming and could be faulty as it relies on human judgment which is often influenced by bias.
Although some automated technologies exist today, they are only able to track players on the pitch. To resolve this issue, Li and her team developed a hybrid system where human data entry can be supplemented by camera-based automated methods.
The team has made use of the latest advances in computer vision, deep learning, and AI to achieve three outcomes:
1. Detecting body pose and limbs to identify actions
2. Tracking players to get individual performance data
3. Camera stitching (using two low-cost consumer-grade normal cameras (such as GoPros), with each recording half of the football field to get a full picture)
Li believes her new system will aid in getting the data needed for accurate player performance analysis and talent identification. There is also the potential to adapt the technology to be used in other sports.
“Performance data and match analysis in football is an essential part of the sport and can have a huge impact on the player and team performance.
“The developed technology will allow a much greater objective interpretation of the game as it highlights the skills of players and team cooperation.
“This innovation will have a positive impact on the football industry and further advance sports technology while providing value to the players, coaches, and recruiters that use the data," Li concluded.