Preparing to go pro in any sport is challenging enough under the watchful eye of trainers and coaches. Thanks to the COVID-19 pandemic, many athletes find themselves in a tough spot with fewer opportunities to analyze their performance. For 130 NFL hopefuls training for the upcoming draft, there is a creative new solution helping bridge the gap.
Intel announced on Thursday that its artificial intelligence (AI) technology is taking athletes to the next level. It is partnering with EXOS, a company dedicated to improving human performance, to test a system called 3D Athlete Tracking (3DAT). The tech analyzes regular video footage to create insights about things like velocity, acceleration, and other biomechanics.
Anyone that’s a fan of track and field recognizes the name Ashton Eaton. The two-time Olympic gold medalist enjoyed success at the highest level during the 2012 London and 2016 Rio de Janeiro games and captured the hearts of millions in the process. After retiring from track, Eaton went on to become a product development engineer at Intel. Unsurprisingly, he is now involved with the 3DAT project.
In a company press release, Eaton said, “There’s a massive gap in the sports and movement field, between what people feel when they move and what they actually know that they’re doing… 3DAT allows athletes to understand precisely what their body is doing while in motion, so they can precisely target where to make tweaks to get faster or better.”
Perhaps the biggest advantage for athletes is that the system works without any leads or wires getting in the way. Instead, they are simply filmed while performing drills or training. 3DAT captures video at 60 frames per second and sends it to a cloud-based server powered by Intel’s Xeon hardware and Deep Learning Boost AI acceleration.
The system then generates an actionable report that coaches can use to help their athletes understand what needs to happen to improve their performance.
Craig Friedman, senior vice president of EXOS’ Performance Innovation Team, says, “3DAT is giving us information, and insight, not just into the technique of how people are running and how they can improve, but also what might be holding them back. This data enables us to make adjustments in the weight room to help unlock more potential on the field.”
Interestingly, Intel first planned to use its 3DAT technology during the 2020 Tokyo Olympics to enhance TV broadcasts. Viewers would be able to get a brand-new perspective on what it takes to compete in events like the 100-meter dash.
Obviously, the 2020 Olympics weren’t held as planned. However, they are scheduled to occur this summer in Tokyo. It’s unclear if 3DAT will still be used, but it would certainly make an interesting addition to typical camera angles.
In the meantime, 3DAT will continue to help athletes elevate their game—whether they’re training for the NFL Draft or the Olympics. The partnership between Intel and EXOS will also lead to further innovations as athletes and coaches use the tool and offer feedback.
Ultimately, this is a great example of how things like AI and video analysis can be used to address real-world problems.