“In volleyball, we now use cameras with computer vision technology to track not only athletes, but also the ball,” says Alain Zobrist, head of Omega Timing. “So it’s a combination where we use camera technology and artificial intelligence.”
Omega Timing’s R&D department has 180 engineers, and the development process began with its own positioning systems and motion sensor systems, according to Zobrist, 2012. The goal was to get to the point where for more sports in sports of 500 plus At events at which it operates each year, Omega could provide detailed information on live athlete performance. This data should also take less than a tenth of a second to be measured, processed and transmitted during the event to match the information to what viewers see on the screen.
In beach volleyball, this meant taking this positioning and movement technology and training AI to recognize countless types of shots – from kicks to blocks to spikes and their variations – and passes as well as ball trajectories, then combine this data with information picked up from sensors gyroscope in the player’s clothing. These motion sensors allow the system to know the direction of the athlete’s movement, as well as the height of the jumps, speed, etc. Once processed, it is all broadcast live to broadcasters for use in on-screen comments or graphics.
According to Zobrist, one of the hardest lessons AI learned was to accurately track the ball in the game when the cameras could no longer see it. “Sometimes he is covered with a part of the athlete’s body. Sometimes it’s outside the TV frame, ”he says. “So the challenge was to follow the ball when you lost it. For the software to predict where the ball is going, then, when it reappears, recalculate the gap from the moment it lost the item and returned it, and fill in the field [missing] data, then proceed automatically. That was one of the biggest problems. “
It is the tracking of the ball that is crucial for AI to determine what happens during the game. “When you can follow the ball, you will know where it was and when it changed direction. And with the combination of sensors on athletes, the algorithm will then recognize the shot “, says Zobrist. “Whether it’s a block or a breakup. You will know which team it was and which player it was. So, it is this combination of both technologies that allows us to be precise in measuring data. “
Omega Timing claims that its beach volleyball system is 99 percent accurate, thanks to sensors and multiple cameras that work at 250 frames per second. Toby Breckon, a professor of computer vision and image processing at Durham University, however, wonders if this is the case during the Games – and, most importantly, if the system is deceived by differences between race and gender.
“What has been done is quite impressive. And you will need a large set of data to train AI in all the different moves, ”says Breckon. “But one of the things is accuracy. How often is it misunderstood in terms of these different moves? How often does he lose track of the ball? And also if it acts uniformly on all races and poles. Is that an accuracy of 99 percent, say, of the American women’s team i 99 percent accuracy in Ghana’s women’s team? “
Zobrist is confident and explains that while it may have been easier to call Google or IBM to provide the necessary AI expertise, it was not an option for Omega. “What’s extremely important, whether it’s a point-scoring sport or a time sport, is that we can’t have disagreements between explaining performance and the end result,” he says. “So to protect the integrity of the results, we can’t “We have to have the expertise to be able to explain the result and how the athletes got there.”
As for future time upgrades and monitoring, Zobrist is tight-lipped, but says the 2024 Paris Games will be crucial. “You will see a whole new set of innovations. Of course, it will stay around timekeeping, scoring, and certainly around motion sensors and positioning systems. And certainly Los Angeles 2028. For that we have really interesting projects that we have actually just started. “
More great WIRE stories