A Software that can identify the significant events in live TV sports coverage should soon be able to compile programmes of highlights without any human intervention. When this technology becomes commercially available, it will save I millions in editing costs.
В Picking out the key moments from a game – whether it be snooker, rugby, baseball, football or basketball – is extremely labour-intensive at present. As the footage streams into a TV station or outside-broadcast truck, someone has to watch the action and keep notes on what happens and when. Only after that are the clips retrieved and put together to form a highlights package, which will probably amount to less than five minutes’ viewing per game when it is finally broadcast.
С However, as sports follow fixed rules, and take place in i predictable locations, computers ought to be able to pick out the key pieces of play and string them together. Anil Kokaram and colleagues at Trinity College in
Dublin, Ireland, are among the research teams trying to turn the idea into reality. They have decided to analyse table-based ball games like – snooker and pool. These are the sports that a computer should find relatively easy to handle as the action is slow the lighting is fairly consistent and cameras mostly shoot from fixed positions.
D The Trinity team uses the edges of the table and the position of the pockets to work out where the balls are on the table. The software has the rules of the game programmed in so it can track the moving balls and work out has happened. For example, if a ball approaches a posket and then disappears from view, the program assume it has been potted. By working out how to detect foul shorts when a player hits the wrong ball – the team hopes : to find a way to create a compelling highlights package for the sport.
E Until recently, the chances of getting similar software for football were not high. Involving a far greater number of moving objects (22 players and a ball) on a playing field whose appearance can vary with the weather and lighting, football had been proving an impossible challenge to developers, but then Carlo Colombo and his colleagues at the University of Florence in Italy started to approach the task in another way. They have found that they can compile highlights from footage without tracking either the ball or the moving players. Instead, they have looked at the position of the players in set pieces. Their software detects the position of the pitch markings in a shot to work out which area is in the frame (see graphic). Then, by checking the positions the players adopt in relation to the markings, the software can decide whether a player is about to take a penalty, free kick or corner, and whether a goal is scored as a result.
F The Florence team has not yet worked out how to enable the computer to determine when a goal is scored in open Play. However, Ahmat Ekin, a computer scientist from the university of Rochester in New York, may be close to solving that problem. He has designed software that looks for specific sequence of camera shots to work out whether a goal has been scored. For example, player close-ups often indicate a gap in play when something important has happened, and slow-motion footage is another useful cue. Ekin also includes sound analysis so it is conceivable that the software could hunt for the № commentator’s extravagant shouts of ‘Gooooaaal!’