NFL calls on data science community to help track head impacts
The NFL continues to crowdsource new ways to track head and helmet impacts during games from data scientists and for the second year in a row, the winner of its artificial intelligence competition comes from outside the United States .
The NFL and Amazon Web Services have awarded $100,000 in prize money for this year’s competition, with the top prize of $50,000 going to Kippei Matsuda of Osaka, Japan, the league announced Friday.
The task for Matsuda and the rest of the data scientists who participated was to use artificial intelligence to create models that would detect helmet impacts from NFL game footage and identify the specific players involved in those impacts.
NFL executive vice president Jeff Miller, who oversees health and safety, said the league started manually tracking helmet impacts for a small number of games a few years ago.
The tedious task of tracking every helmet collision, especially along the line of scrimmage, made it difficult to do more than a small sample of games as the league attempted to collect more head impact data.
By sharing gameplay footage and information with the data science community, the league hopes to continue to develop better systems that can track these impacts more effectively. The league estimates that Matsuda’s winning system could detect and track helmet impacts with greater accuracy and 83 times faster than a person working manually.
“There were certainly a number of national participants as well, but the data science community is large and finding solutions in places or with communities you wouldn’t normally speak with can be quite a fruitful exercise,” Miller said. “So I think we’ve proven that this model of working with the global data science community is useful to us and will continue to be and we’ll continue to be committed to it.”
The competition’s first year in 2020 focused on models that detected all helmet impacts from NFL game footage. This competition was won by Dmytro Poplavskiy from Brisbane, Australia, which included nearly 7,800 submissions from 55 countries.
This year’s competition focused more on specific player impacts and featured 825 teams and 1,028 competitors from 65 countries, and a total of 12,600 submissions.
“It was the most exciting competition I have ever experienced,” Matsuda said in a statement. “It is a very common task for computer vision to detect 2D images, but this challenge required us to consider higher dimensional data such as the 3D location of players on the field. NFL videos are also fun to watch, which is very important because we need to review data again and again during competition. I would be honored if my AI could help improve NFL player safety. »
Miller said the league’s goal is to create a “digital athlete” who can become a virtual representation of the actions, movements and impacts an NFL player experiences on the field during a game and can be used to help predict and hopefully prevent injury in the future.
“It’s new to us and obviously has a big impact on how we think about making the game safer for athletes,” Miller said. “It will definitely have an effect on training and training. It will definitely have an effect on the rules. It will definitely have an impact in terms of equipment and the benefits we can see from equipment because now, for the first time, we’ll have a pretty good appreciation for every time someone bumps their head during an NFL game, and so we’ll be looking for ways to avoid many of them.
Priya Ponnapalli, senior director of Amazon’s Machine Learning Solutions Lab, said the potential of machine learning to analyze past data but also to make forward-looking projections will be useful in the future to help create a digital version of players at all positions and analyze the types of shots they take.
“Machine learning is a very intuitive process and you hit a certain level of performance, and in this case we have quite accurate and comprehensive models,” Ponnapalli said. “And as we collect more data, these models are going to get better and better.”
More AP NFL: https://apnews.com/hub/nfl and https://apnews.com/hub/pro-32 and https://twitter.com/AP_NFL
Comments are closed.