Software tracks athletes for ‘robot sportscasters’

Researchers at the Ecole Polytechnique Federale de Lausanne have come up with an algorithm that can track all the players in a sports match, and say it could soon appear at international competitions.

It works, says the team, even when players are buried under a pile of bodies in a rugby match or crouched behind another player, and there’s no need for the players to wear extra gear or RFID chips.

The athletes appear on a screen with a superimposed image bearing their jersey color and number, so that spectators, referees, and coaches can easily follow individuals without mixing them up.

The system‘s made up of eight standard cameras – two on each side of the field or court, two that film from above and two that zoom – and three algorithms. After a tackle, goal, basket, or pileup, the system reattributes the jersey number to each player automatically.

The first algorithm detects individuals at a specific moment in time, independently of where they were immediatelybefore or after. To do this, it slices the playing area into 25 cm2 squares, removes the background in all the images simultaneously, and from this deduces the probability of the presence of a player in each of the small squares.

The other two algorithms connect the results obtained for each moment in order to establish individual trajectories.

The team’s now making final adjustments to the system that will let television cameras provide direct input. It’ll allow sports coaches to get a much clearer idea of what’s going on on the pitch, and could even lead to robot commentators.

“Other applications, like tracking pedestrians to monitor traffic in an area, or following the movement of clients in a store for marketing purposes, are being planned,” says researcher Horesh Ben Shitrit.