Only AI can understand Premier League offside rules

Image credit: Pixabay (Image credit: Pixabay)

The Premier League kicks off this week, and a new AI referee tool to spot when players are offside will be coming on board before it ends, as first reported by Wired. The league has turned to sports tech company Genius Sports and its Semi-Assisted Offside Technology (SAOT).

Unlike the usual video assistant referee (VAR) systems, SAOT doesn’t need expensive 4K cameras, just a network of between 24 and 28 iPhones around the pitch. The built-in GeniusIQ AI then analyzes the images collected by the iPhones to work out precisely where every bit of a player was at any moment and whether they were offside.

Sports rules can be complicated, and few are as notorious as offside violations for being contentious and difficult to call. VAR has helped but is often criticized for slowing the game or leading to wrong calls. SAOT can look at the field and gather between 7,000 and 10,000 data points per match, creating detailed 3D virtual meshes of each player. By comparison, current systems often rely on 30 to 40 tracking points to create rudimentary stick figures for the players,

The GeniusIQ system’s 3D meshes offer a much more detailed and accurate model. That data then creates a picture of where each player is compared to the ball and the offside line. iPhones with their 100 fps recording speed are plenty fast enough when combined with the GeniusIQ system. The AI, trained on several seasons’ worth of matches, can identify not just player positions but even individual body parts as small as their fingers and extrapolate even if they are partially obscured from view.

AI Refs

The Premier League's adoption of this technology could streamline the decision-making process, reducing the delays that have plagued VAR use in the past. Although the exact rollout date has not been announced, the technology is anticipated to be in full use across all Premier League matches soon.

Still, though the SAOT system has shown promise in testing, its effectiveness in live matches remains to be seen. It will need to demonstrate that it can consistently outperform existing VAR systems in terms of accuracy and efficiency. Plus, it will have to overcome a reliance on extensive data processing, which means any technical issues with the servers or software could cause it to fail.

As the SAOT system is implemented in live matches, the global football community will closely watch it. If successful, it could set a new standard for the use of technology in sports, not just in soccer but across a range of athletics, where precise location can decide the fate of a match. In the end, the human referees make the final call and will be celebrated or cursed regardless of what the AI suggests about who is offside.

You might also like...

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.