Anika Begay
“If a more difficult problem comes up in the future, it’s relatively easy for us to work off the installed base, or the technical background that we have in a location, and just add 10, 20, 30, 40 different cameras,” he says. “Maybe we want to focus them on certain parts of the field or distribute them for specific purposes.”
This kind of scalability also brings the concept of the “digital twin” to the table in sports. By capturing streams of video and positioning data as a player moves around the field, that player can be recreated virtually—his movements, his likeness, his hand gestures, all rendered digitally in real time. This is something that has typically only been possible with the kinds of expensive cameras and computer systems used in Hollywood and video game development.
While digital twins can be created in sports, their uses extend beyond refereeing. Broadcasters can use them in digital overlays that show real-time stats, or in virtual reality, so you can watch a game inside your VR headset.
Football is just the first playground for this technology. Nearly every sport can derive value from creating digital twins, and Genius hopes to make inroads into basketball and American football soon.
But as intriguing as a digital twin of football may sound, can Dragon really solve the game’s offside detection problems? After all, the ongoing problems with previous VAR systems have failed to inspire confidence in motion capture technology among football’s key stakeholders and fans alike.
Genius says it has been testing Dragon for several years, both at the EPL and in several other locations, in multiple formats. The company employs several in-house analysts who project tracking data into a video format, then examine it frame by frame alongside the transmitted video to detect any discrepancies. This allows the team to continually retrain its models until those errors are, in theory, eliminated. Genius analysts consider this the foundational testing layer, a baseline upon which others are layered.
Dragon’s inputs were tested side-by-side with VAR and detection systems to validate their basic accuracy. They were also validated manually: engineers spent long hours with various sports stakeholders (coaches, players, officials), reviewing complex actions and confirming that the system’s outputs made sense. Every customer considering using Dragon also has internal teams reviewing the system and validating its outputs.
“We’ve done this with groups like FIFA, where we’ve done extensive testing,” D’Auria says. “The Dragon system is validated by FIFA. They’ll do tests where players wear a Vicon. [motion-capture] system, and we follow them, and they compare data sets and look for errors. We’ve been through five or six of those machinations.”
It should be noted that both Genius and EPL representatives declined to provide specific test information or results to WIRED, stating that despite evaluating the iPhone system side-by-side with VAR, comparisons to previous motion capture systems are complicated by orders of magnitude differences in the amount and quality of data created. Interestingly, once again, both EPL and Genius declined to provide any indication of how much more accurate their smartphone technology is compared to VAR.
Of course, the real judgement will be up to the fans and players, who will have to see Dragon in action to believe it makes a real difference. The last few years of VAR nonsense have understandably left a sour taste in the mouths of many when it comes to optical tracking.
But when the first semi-automated offside call arrives in the UK this season, remember that this isn’t just another setup in a different box. This is the next generation of motion capture, one that stakeholders across the sport and the AI community will be watching closely. Fans won’t have much, if any, tolerance for further issues with motion capture-based systems. Genius and the EPL are confident they’re up to the challenge. We’ll see. Let the games begin.
