In a corner of a crowded Barcelona conference center, I probably looked a little odd. While other smartly dressed MWC 2024 attendees shuffled past me, chatting amiably, burying themselves in their phones, gawking at the latest technology, I… I got some strange looks at least a few times. That’s because even though I was wearing jeans and flat-soled Vans, I was sprinting in place, trying to pull my knees higher each time.
In front of me was a camera connected to a mirror-length smart display that guided me through some quick training drills. I had to run in place, jump from side to side, and perform one squat jump. There was also a “pop the bubble as fast as you can” Xbox Kinect-style cognitive response game played on the smart display’s touch screen.
Behind the scenes, artificial intelligence was analyzing my performance, and once the trial was over, it provided the kind of information you’d expect from the best Garmin watches. In other words, it measures my explosiveness, speed, coordination, agility, etc. All metrics are simple scores out of 100.
This was one of the most entertaining interactive displays I was involved with at MWC, but behind the sprints, jumps, and bubble-popping movements, there’s a lot of sophistication that could have a big impact on the fitness technology scene. Technology was hidden. ai.io he developed 3D Athlete Tracking (3DAT). This is a “human tracking” using artificial intelligence and his YOLO (“look once”) object detection to identify key points on the body and provide biometrics based on movement.
Currently used by soccer players. The UK-based app called aiScout allows young amateur athletes to record their drills and connect with coaches. The coach can then use these AI-generated metrics to identify promising young candidates.
But soccer is not the only use case. In conversations with ai.io representatives and engineers, they revealed that discussions with organizations such as the NFL are underway, and areas such as running are “on the roadmap.” This is great news for me. As an avid runner, I can only imagine the possibilities. Instead of making an appointment at a running store to choose the best running shoes for your running style, why not try gait analysis to improve your running at home or at your local gym with a treadmill? Please register.
My only question is how reliable are these indicators? No two objects are the same, and it may take the human mind to discern certain features. But the same can be said about smartwatches. I battle to increase my Garmin Endurance Score several times a week. It uses your VO2 Max data and Garmin’s algorithms to give you a single number that tells you how you’re doing. This is an evolution of that methodology, using a single camera and some software rather than expensive hardware.
This is just one example of using AI to track athletic performance, but I’m excited to see where 3DAT goes in the future. As this technology evolves further, there is no doubt that AI will do what it does best: destroy. I think in the not-too-distant future, more personal trainers, professional coaches, and fitness enthusiasts alike will be using cameras instead of relying on power meters, heart rate monitors, or even the best smartwatches. I’m predicting.