The National Football League (NFL) and Amazon Web Services, Inc. (AWS) have closed out their artificial intelligence competition. The $100,000 AI Challenge tasked data scientists with teaching computers to automatically detect players involved in head impacts. The computers did this by analyzing NFL game footage to understand and reduce head injuries.
Analyzing Game Footage
The NFL already had been reviewing, frame-by-frame, game footage of major injuries while recording 150 different variables. The newly developed models automated this process, making it more comprehensive and accurate. The winning model was 83 times faster than a human when analyzing the footage.
The NFL will use the new insights for injury reduction, equipment design, rule changes, and coaching and training improvements.
Jennifer Langton is SVP at NFL Player Health and Innovation.
“The innovative ideas brought to this competition from data scientists around the world will be transformative, driving a staggering improvement in accuracy of computer vision models over just a three-month competition,” said Langton. “The success of this challenge speaks to the power of the crowdsourcing model that the NFL has deployed over the last decade to drive innovation in player health and safety and we are thrilled to have had some of the brightest minds in data science from around the world working on our challenge.”
The challenge was undertaken by more than 1,000 data analysts from 65 countries. The five winning models were awarded prizes totaling $100,000. First-place went to Kippei Matsuda from Osaka, Japan, followed by Takuya Ito from Tokyo.
Building on Previous Models
The data scientists were granted access to NFL game data and last season's competition data, which had crowdsourced models to detect helmet impacts.
“This was the most exciting competition I've ever experienced,” said Matsuda. “It's a very common task for computer vision to detect objects in 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 since we need to see the data again and again during the competition. I would be honored if my AI can help improve the safety of NFL players.”
The NFL and AWS will also use the new computer vision models to continue developing the “Digital Athlete,” a virtual representation of an NFL player. This virtual athlete can then be used to predict and prevent player injury. Its algorithms can run infinite simulations of in-game scenarios, which provides insight into player health and safety.
Dr. Priya Ponnapalli is Senior Manager at the Amazon Machine Learning (ML) Solutions Lab.
“AWS and the NFL are fostering an understanding of how to treat and rehabilitate injuries in the near term and eventually predict and prevent injuries in the future leveraging data,” said Dr. Ponnapalli. “New computer vision models developed in this challenge, and the hard work put in by all the teams involved, bring us steps closer to our goal and I couldn't be more thrilled to see how this work transforms the sport in the coming years.”
- AI-Generated Drake Song Submitted for Grammys: A Pivotal Moment for Music and AI
- Naré Vardanyan, Co-Founder & CEO of Ntropy – Interview Series
- Navigating the AI Gold Rush: Unveiling the Hidden Costs of Technical Debt in Enterprise Ventures
- Walmart’s Bold Move: Equipping 50,000 Corporate Employees With a Generative AI Assistant
- Employing Generative AI: Unpacking the Cybersecurity Implications of Generative AI Tools