NFL, AWS Develop AI Challenge to Crowdsource Ways to Automate Player Identification Using Game Footage

The National Football League (NFL) and Amazon Web Services (AWS) have launched a new artificial intelligence challenge to create ways for computers to automatically identify players using NFL game footage. New computer vision models created through the challenge will accelerate the NFL’s work with AWS to better understand, and aim to reduce, injuries in the NFL. Prize money totaling $100,000 will be awarded to data scientists with winning models. The contest will be open through November 2, 2021.

This challenge is the next step in the NFL’s work with AWS to develop the Digital Athlete, a virtual representation of an NFL player that can be used to better predict and hopefully prevent player injury. Last season, the NFL hosted its first computer vision competition, providing computer scientists NFL game data and challenging them to create ways to detect on-field helmet impacts. Nearly 7,800 submissions were received from data scientists around the world. Those solutions are now being used by the NFL and AWS in ongoing work on the Digital Athlete.

“This competition is foundational in helping identify each player’s risk to injury-causing events, especially when it comes to head health,” says Jeff Miller, NFL Executive Vice President overseeing the league’s health and safety programs. “We are excited to enlist some of the most talented data scientists from around the world to help develop these solutions and meaningfully advance player safety.”

This challenge builds upon last season’s competition by scoring teams based on how accurately they identify players involved in a helmet impact. The NFL will be providing data scientists with the same set of game data to build upon the current models. This competition will advance an already robust machine learning pipeline built on AWS that is working towards being among the most advanced and sophisticated injury surveillance and mitigation programs in professional sports.

“Using AWS’s broad range of technologies including machine learning (ML) and artificial intelligence (AI), the NFL and AWS will generate more new insights than ever previously possible into player injuries, game rules, equipment, rehabilitation, and recovery,” says Priya Ponnapalli, Senior Manager, Applied Science, Amazon ML Solutions Lab. “This contest will continue that work and the data and insights collected through this project have the potential to shape the future of football.”

The Digital Athlete will ultimately help the NFL and its clubs to leverage sports science and injury biomechanics to develop individualized training and recovery regimens, conduct real-time risk analysis for injury during games, and identify and evaluate additional player safety initiatives, including around equipment, rules changes and coaching techniques.