GoHeels

UNC Installs Kiosks to Detect Masks and Distancing

The University of North Carolina at Chapel Hill (UNC) is using AI to ensure that students and visitors keep their distance and keep their masks on at football games.

The Health Greeter Kiosks, developed by the Reese Innovation Lab at UNC, use computer vision and machine learning to process real-time data and detect when people are not following best practices to prevent COVID-19. The kiosks, developed in 10 weeks, alert those who are flagged through large displays at the entrance gates of Kenan Stadium.

“The kiosks accurately detected masks and distance, and I was happy to see people pass by and engage directly with the displays. Some took photos of themselves with the screen confirming their masks, and many stopped to read about the devices and better understand the underlying technology,” said Steven King, chief innovation officer at the Reese Innovation Lab.

To ensure privacy concerns are addressed, the kiosks do not store video data, and must meet Family Educational Rights and Privacy Act (FERPA) data security requirements.

Football games aren’t where the solution will stop – UNC is currently holding most classes remotely, but plans to have a larger return to in-person classes in the spring semester.

“From campus hallways to outdoor events, these kiosks will help us better understand human behavior and encourage safe behavior, and I’m excited to see how we evolve and adapt this AI-powered solution,” King said.

The solution was developed by students and staff in partnership with Lenovo’s AI Innovation Center, which provided technical support for the effort.

“This is an exciting and important application of smarter technology and smarter IT infrastructure out of our AI Innovation Center,” said Matthew Zielinski, president of Lenovo North America.