Post date: Mar 18, 2012 1:0:18 PM
REUTERS/EPFL HANDOUT - Before long basketball fans watching the game on a tv or computer screen will be able to get even closer to the action with software that uses complex algorithms to monitor individual players.
It's not being used in this year's "March Madness" US college basketball tournament or the upcoming Olympic Games, but a new tracking software designed to radically improve the analysis of individual performances in basketball games, is close to being ready. The software has been developed by computer scientists in Lausanne who say it will revolutionise sports for both coaches and spectators. Jim Drury reports.
The system's being devised at Switzerland's science university EPFL by a team including PhD student Horesh Ben Shitrit.
HORESH BEN SHITRIT, PHD STUDENT AT EPFL, SAYING:
"Our system is able to track multiple people from multiple cameras. We can estimate the position of each player at each time on the floor and from that we can have the trajectory of each player during the match. We use the trajectory in order to do analysis of the behaviour of the players and the behaviour of the teams and we can improve the performance of the teams and the players."
Matches are recorded by eight cameras and analysed with three separate algorithms.
The first divides the playing area into grids of 25 square centimetres, deducing the probability of a player's presence in each square.
The second estimates a player's location and movement, based on the first algorithm's work.
A third monitors their appearance - the colour of their shirt, team number, and other visual cues.
Here Professor Pascal Fua and his team demonstrate the technology, which he says could also help outside the world of sports, with surveillance, crowd control, and even architectura.
PROFESSOR PASCAL FUA, HEAD OF EPFL TRACKING TECHNOLOGY TEAM, SAYING:
"You could watch how a building's being used. Typically, when an architect builds a building he has a particular pattern of usage in mind, but who knows, maybe it's being used differently and a kind of a system like this could be used to do this, and it could be used to do this without intruding on the privacy of people because we don't have to record their identity in the end. All what you have is trajectories, it doesn't say who they are."
Fua says the technology could be used in other sports and help broadcast commentators analyse play more accurately and with greater speed. He says it could even lead to the replacement of human commentators entirely, allowing the computer to do the work.
The technology is aimed not just at viewers but also professional coaches.
PROFESSOR PASCAL FUA, HEAD OF EPFL TRACKING TECHNOLOGY TEAM, SAYING:
"You could analyse the tactics of your team and, even more interestingly, the opposing team and maybe try to watch them play in various games and try to understand what their strategy is, what their play book is and that sort of things, and that's things that I think coaches for all team sports will be interested in."
The Lausanne-based team devised the system with colleagues from the Idiap Research Institute.
They hope it will be ready in months, though probably not in time for this summer's Olympics.
But Ben Shirit believes the 12 countries competing for medals could benefit from EPFL's work before the games begin.
HORESH BEN SHITRIT, PHD STUDENT AT EPFL, SAYING:
"If you could start analysing your behaviour before the Games, the Olympic Games, then while the Olympic Games are running you could understand what the other teams are doing."
EPFL's research is itself being monitored with interest.
And if the professional game decides it's a winner, then the EPFL could be celebrating its very own, commercially-successful slam-dunk.
Jim Drury, Reuters