It is not uncommon for certain refereeing decisions at the FIFA World Cup to be debated years later. Artificial intelligence (AI) could therefore help referees make the right decisions.
Referee decisions in football are often the subject of debate, sometimes even for decades. Whether it’s whether the ball crossed the line in the 966 World Cup final, Diego Maradona’s ‘hand of God’ 20 years later or certain decisions made by the referee in the VAR truck during the World Cup in Russia in 2018; football fans will always comment on the slightest mistake of the referee.
So, referees need all the help they can get, and they might be about to get an unexpected helping hand from the AI.
In recent years, the Fifa tested the use of motion tracking technology for offside. This technology uses AI as well as a series of cameras around the stadium to track players’ movements and instantly create a virtual offside line for referees. Used so far in the Club World Cup and Arab Cup Fifathe world football organization hopes to be able to use this technology during the World Cup in Qatar in 2022.
Considering all the issues with VAR, the use of AI in football might raise some concerns. However, Patrick Luciascientific director of the sports data company Perform statisticsbelieves that the approach of Fifa when it comes to motion tracking is the right one.
According to him, rather than a fully automated decision, AI is used to give precise measurements and create the offside lines that previously had to be drawn manually. Human error is thus eliminated, but the human remains in the equation.
The referee or assistant referee can look at the image created by the AI and know immediately if a player is offside. However, the referee may also use his own judgment to decide if that player is interfering with play or if there is some other reason why the goal should be awarded or not.
According to Patrick Lacey, this approach “enables humans to do what they do very well and computers to do what they do very well. “This is the reason why Pierluigi Collinachairman of the FIFA refereeing committee, affirms that it is not a “robotic offside. »
Since the manual work is done by a computer and not by a human, the decision will not be as instantaneous as the goal line technologybut it should be much faster than the current VAR, which should eliminate some of the frustration caused by long VAR decisions, while improving the referees’ overall decision-making.
Patrick Lucey says motion tracking technology isn’t new, it’s been used in basketball for over twenty years. However, camera technology has improved with 4K and 8K cameras which have higher pixel density, and AI can now do things that were impossible before.
Thanks to more powerful AI and improved motion tracking technology, Patrick Lucey estimates that within a year, football data and parameters that were previously collected manually will be able to be captured directly from a live TV football broadcastwithout the need to use other cameras on site.
If TV broadcasts don’t provide the quality needed for live motion tracking technology, which is essential for making accurate refereeing decisions, AI will soon be able to use TV broadcasts to create real-time statistics, including expected goals and estimated position of players who are not on screen. This is done using a fingerprint of player tracking data over the past 20 years, combined with machine learning algorithms to estimate where missing players are.
This technology can then be used on television broadcasts of historic matchesby collecting data from previous World Cups, allowing statisticians to analyze data relating to England’s golden generation or Diego Maradona’s expected goals.
One such advanced stat that the AI is able to create is called “ghosting.” This stat uses AI to determine if players are in the position they are expected to be in particular situations. Clubs can use it to correct errors, for example by showing if a winger is misplaced on a counter-attack, or to find weaknesses in their opponents, by seeing what their players are likely to do in a certain situation.
With AI making it possible to create such stats from a TV broadcast, advanced stats will be accessible at a much broader level of play, which could have even bigger implications than FIFA’s motion-tracking technology. .
Article translated from Forbes US – Author: Steve Price
<< À lire également : STRIVE : Un outil technologique au service des clubs de football pour prévenir les blessures >>>