AI in Sports - When the Video Assistant Referee Can Save the Game

AI


As a fan of the England national football team, I have gotten used to regular disappointment. Most recently there was the heartbreak of the 2018 FIFA World Cup semi-final loss to Croatia, and prior to that the embarrassment of not even making it out of the group stages in 2014. However, going back further there is one moment that stands head and shoulders above the rest for me, THAT Frank Lampard goal in the 2010 FIFA World Cup quarter-final between England and Germany.

England were on the verge of making an incredible comeback when having just scored a goal, they were on the attack again. With a thunderous shot from midfielder, Frank Lampard, the ball stuck the crossbar bounced down into the goal to be followed by massive celebrations around the country. However, the one person who didn’t see the ball cross the line was the one who mattered the most: the referee. The players all saw it. The whole stadium saw it. The entire world saw the ball cross that line. And yet, the referee did not allow the goal and following that critical disappointment, England went on to crash out of the game with a 4-1 defeat to the Germans.

This event set off a wave of calls for the Video Assistant Referee, or VAR as it is commonly known today. With its introduction into many leagues and competitions, the problem of referees missing key events or goals seemed to have been removed from the game. However VAR’s own set of problems were highlighted in this summer’s FIFA Women’s World Cup in France, and we’re seeing issues already after week one of the English Premier League.

At the FIFA Women’s World Cup, VAR was used extensively, checking almost every call the referee made with lengthy review sessions. With many of these VAR incidents, questions were raised to whether VAR was helping or hurting the beautiful game. One such example was England striker, Ellen White, having an incredibly marginal goal disallowed due to VAR which contributed to England’s failure to reach the Final (sound familiar anyone?).

With many questions still surrounding VAR, what could a solution possibly be? More technology could be the answer as a recent study showed that one in four football fans want more AI technology used in sports. Machine learning is a form of AI that could be used to teach the computer which camera angles from 40+ cameras to show the referee. This would allow the referee able to make his decision quicker and more accurately. Subject matter experts (in this case experienced referees) would go through historic footage and tag the angles that are useful and which are not. The computer would start to learn the key factors that determine whether an angle is relevant and apply these to new footage in real time.

More and more leagues across Europe are introducing VAR into their stadiums such as the top division's in Italy and Germany. For example in Spain, La Liga (the Spanish premier division) is introducing VAR with artificial intelligence to help with the decision making process of their referees. La Liga is implementing the machine learning aspect of artificial intelligence by allowing for the insertion of graphic overlays to help with decision making. While the use of this technology has yet to be implemented into the game, it does open up the options to improve and correct officiating in the modern game.

Hopefully, more leagues and football federations will adopt artificial intelligence into their VAR systems so that decisions like those seen at the Women’s World Cup or Frank Lampard’s goal are removed from the game we all love.






Written by Christian Wady

See Christian Wady's blog

Related blogs

Qubits North America - Rumours from the Trade Show Floor

It's lunchtime here in the beautiful city of Amsterdam where I am enjoying my time at the excellent World Summit AI, at which Verne Global are exhibiting, and earlier today our CTO Tate Cantrell moderated an engaging panel on today's hottest AI disruptors. As I take a breather from the networking, I thought I would write some thoughts about another excellent event which I went to a couple of weeks ago - Qubits North America.

Read more


Deep Learning at Scale

Deep learning is a current hot topic in HPC and I am sure it will be one of the key themes at SC18. In many cases, we have been hearing about artificial intelligence, machine learning, and deep learning discussed together, though in reality, machine learning is a type of AI, and deep learning is a subset of machine learning. In this article, we will try to best define deep learning and its industrial applications and, more specifically, the benefits of scale - from big data to high-performance computing - to the successful implementation of deep learning.

Read more


How AI can keep your executives out of jail

Only artificial intelligence (AI) can prevent social media firms from shutting their doors. Costs, fines and executive jail terms are threatened as the government tackles online harm.

Stricter regulation of social media companies is now high up on the agenda of many national governments. In the UK plans are in place to create a statutory duty of care toward social media users, and a new independent regulator with powerful sanctions is to be established.

Read more

We use cookies to ensure we give you the best experience on our website, to analyse our website traffic, and to understand where our visitors are coming from. By browsing our website, you consent to our use of cookies and other tracking technologies. Read our Privacy Policy for more information.