Imagine a stadium where ultra-high-definition video broadcasts and drones with cameras track how individual players bend their joints while playing, how high they jump or run fast – and use AI to pinpoint the risk of injuring athletes in real time.
Coaches and elite athletes are betting on new technologies that combine artificial intelligence with video to predict injuries before they happen and provide accurate recipes for workouts and exercises to reduce the risk of injury. In the coming years, computer vision technologies similar to those used in face recognition systems at airport checkpoints will take this analysis to the next level. wearable sensors in widespread use by athletes today is unnecessary, sports analysts predict.
This data revolution will mean that some overuse injuries could be significantly reduced in the future, says Stephen Smith, CEO and founder of Kitman Labs, a data processing firm that operates in several professional sports leagues with offices in Silicon Valley and Dublin. “There are athletes who treat their bodies like businesses, and they’ve started using data and information to better manage themselves,” he says. “We will see many more athletes who will play much longer and also play much longer at the highest level.”
Offering prospects for maintaining the health of players, this new frontier of AI and sport also raises difficult questions about who will possess this valuable information – individual athletes or team leaders and coaches who use this data. Concerns about privacy are also growing.
A baseball app called Mustard is one that already uses computer vision. Videos recorded and sent by users are compared to a database of professional pitchers ’moves, giving the app to offer recommended exercises aimed at making throwing more efficient. According to Rocky CEO and co-founder, Mustard, which comes in a free downloadable version, is designed to help ambitious players improve their performance, and avoid repetitive movements that can cause long-term pain and injury. Wheels.
Computer vision is also making inroads into applications for other sports, like golf, and promises to be relevant for both amateurs and professionals in the future. Algorithms using Form AI, known as machine learning, that processes statistics from sensors and can analyze changes in body position or movement that may indicate fatigue, weakness, or potential injury, are now more widely used. Liverpool Football Club in the UK says it has reduced the number of injuries to its players by a third compared to last season after adopting an AI-based data analytics program from Zone7. The information is used to adapt recipes for workouts and suggest the optimal time for rest.
Football has become one of the biggest proponents of artificial intelligence-based data analytics as teams seek any advantage in world sports. But some individual sports are also beginning to use these technologies. At the 2022 Winter Olympics in Beijing, ten American skaters used a system called 4D Motion, developed by New Jersey’s 4D Motion Sports to help track fatigue that could result from too many jumps in practice, says Lindsay Slater. , U.S. Figure Skating Sports Manager and Associate Professor of Physical Therapy at the University of Illinois at Chicago. The skaters tied a small device to their hips and then reviewed the movement data with their coach when the practice was over.
“We’ve actually brought the algorithm to such an extent that we can really determine takeoff and landing when jumping, and we can estimate that the loads on the hips and torso are quite high,” says Dr. Slater. “During the day, we found that athletes have reduced angular velocity, reduced jumping height, they cheat more jumps, and this is where chronic injuries and overuse injuries tend to happen.” She says American figure skating is evaluating the 4D system in a pilot project before expanding its use to more of its athletes.
Algorithms still have to overcome many obstacles in predicting injury risk. First, it is difficult to collect long-term data from athletes who jump from team to team every few years. In addition, data collected by sensors may vary slightly depending on the device manufacturer, while visual data has the advantage of collecting remotely without fear that the sensor may fail, analysts say.
Psychological and emotional factors that affect performance are difficult to measure: stress during contract negotiations, quarrels with husband and wife, bad food the night before. And the only way to really test the algorithms is to see if a player who has been identified as a risk program by AI is actually injured in the game – a test that violates ethical rules, says Devin Player, Toronto’s director of analytics. FC, one of the 28 teams in the Premier League.
“I think there may be a future where these things can be trusted and trusted,” Mr Player says. “But I think there are significant sampling issues and ethical issues that we need to overcome before we can really reach that threshold.”
The problems also present data privacy issues and the question of whether individual athletes should be compensated when teams collect their information to power AI algorithms.
There are currently no rules in the U.S. that prohibit companies from collecting and using player training data, according to Adam Salander, a lawyer in Washington, D.C., who represents several major sports teams and data analytics companies. He notes that the White House is developing guidelines on rules governing artificial intelligence and the use of private data.
Mr Salander says the rules must strike a balance to allow potentially important technologies to help people while respecting human rights to privacy.
Share your thoughts
Do you think artificial intelligence will play a role in training professionals and amateurs in the coming years? Join the conversation below.
At the moment, one sports data processing company that has adopted computer vision is using it not to predict injuries but to predict the next superstar. Paris-based SkillCorner collects TV video from 45 football leagues around the world and launches it using an algorithm that tracks the location and speed of individual players, says Paul Nilsson, the company’s general manager.
The firm’s 65 customers are now using this data to investigate potential recruits, but Mr Nilsson expects that in the near future the company’s gaming video could be used to detect injuries before they occur. However, he doubts that the AI algorithm will ever replace the human trainer on the side.
“During the game you are here and you can smell it, feel it, almost touch it,” he says. “For these decision-makers, I think it’s still less likely that they’re actually listening to an understanding that comes from a source of artificial intelligence.”
Copyright © 2022 Dow Jones & Company, Inc. All rights reserved. 87990cbe856818d5eddac44c7b1cdeb8