The all-seeing eyes of Artificial Intelligence are watching over the UEFA Euro 2024 football tournament with greater scrutiny than even the most passionate fans. Thanks to the latest VAR technology, which incorporates AI, no slight movement of the ball or players will go undetected.
Since its introduction in 2016, the Video Assistant Referee (VAR) system has been a hot topic among football fans. Inconsistencies in how referees apply the technology and the time taken to make decisions have fueled dissatisfaction. The Premier League even held a vote on whether to completely eliminate VAR: the clubs ultimately voted 19 to 1 in favor of keeping it, but the opposition highlighted the need for improvements. Consequently, a semi-automated, enhanced version of the technology that incorporates more advanced AI and a real-time location tracking chip within the ball was used for the first time in a major global tournament at the FIFA 2022 World Cup in Qatar.
AI's Role in Observation and Data Processing
Euro 2024 showcases the latest version of the AI-assisted referee. How does AI observe a football match? "When people hear about AI, they might think it's a sentient being working alongside humans, but these are algorithms and machines capable of rapidly processing large amounts of data that a referee otherwise wouldn't have access to," says John Eric Goff, a sports physicist at the University of Lynchburg, Virginia.
Above the football field, 10 overhead cameras positioned throughout the stadium can observe 29 body zones on each player. Thus, with 22 players on the field, there are over 600 moving points. Fifty times per second, this data is fed into a computer. All these different cameras can real-time track the players' positions on the field, the ball’s location, and how fast the ball and players' body parts are moving.
Ball Technology and Referee Assistance
What information can the ball itself provide? If you were to cut open the ball, you’d see a small sensor at the center connected by wires to the outer shell. This tiny inertial measurement unit logs the ball’s location and movements. It transmits data at 500 Hz, which is ten times faster than the stadium cameras. These data can be combined with camera rendering to track the ball's location relative to a player's body. The chip inside can determine the precise time and point of contact whenever the ball receives an impulse from a kick or a player’s hand. This will be crucial for making tough calls on goals or handballs.
How are all these data useful for referees? A major application is detecting offside rule violations. AI can render the 29 data points it collects for each player in three dimensions. Using this, it can extrapolate the player’s form beyond these 29 points based on algorithms, and then determine where a particular body part representing an off-side is located. AI can make these decisions quickly, so referees will know whether a player is off-side or not, or whether it's a goal or not. The old technology took an average of about 70 seconds to return a computer-generated offside determination. Now it is estimated to take less than half a minute, so referees will be able to make these calls faster.
AI Expo Europe and Future of Refereeing
At AI Expo Europe, taking place on October 6-7 in Bucharest at Radisson Blu, we will decode the impact of Artificial Intelligence on all fields of activity. The largest interactive conference in Eastern and Central Europe will involve professionals, leaders, and innovation enthusiasts, "dreamers, thinkers & doers", mentors, and business people, in a unique event of this world-changing industry. For more information, to purchase tickets, or promotional packages, click here: www.aiexpoeurope.com
What are the margins of error for this technology? There will always be a coverage issue: are there enough cameras? Is the camera field wide enough to record every action? Even the algorithms used for rendering will have certain types of errors; 29 points do not represent every point on the body, so there will be an error associated with forming a 3D rendering of the body. But we are talking about very small errors, less than half a centimeter.
Impacts on Aerodynamics and Game Dynamics
Does the chip affect the ball's aerodynamic behavior? It shouldn't. It is well placed in the center of the ball and there should be no asymmetry. Regarding the weight, the rules of the game specify about 410–450 grams of ball weight at the start of the match; the chip itself weighs around 14 grams, which is negligible. The ball has been thoroughly tested for the types of kicks and pressures it is subjected to at speeds over 90 km/h before being brought onto the field for play.
How has VAR changed the role of the referee? The important part of the "semi-automated" technology is the "semi", so there is still an element of human determination. The one thing AI will not be able to decide is the player's intention. If a player's hand touches the ball, it will tell the referee that the ball has been touched. It might not precisely identify that it was the hand. So, there are also times when the referee can review a replay and determine that there was malicious intent on a particular player which helps in determining a yellow or red card. And, of course, that will still be subjective, and fans will always argue about it.
What does the future hold for refereeing, will it ever be fully automated? We are not yet close to having robotic referees. Things like fouls and yellow or red cards still require human decision-making. As for the future, it is possible that virtual reality contact lenses could be involved, which referees could use to show the type of data provided by AI in real time. As computing power becomes faster, massive data sets will very quickly render information.