AI COVID Monitoring Tool Modified To Track Congestion

A team of researchers at New York University (NYU) have retrofitted an AI tool originally designed to monitor the effectiveness of stay-at-home and social distancing orders to now assist urban planners and government officials on crisis management response and urban congestion. 

The tool leverages New York City’s publicly available CCTV video feeds, of which there is 700 locations in the city, to calculate pedestrian and traffic densities using a deep-learning object detection method. 

SEE ALSO: 5G is Making On and Offline Retail Fun Again

The team, based in the Connected Cities for Smart Mobility towards Accessible and Resilient Transportation (C2SMART) Center at NYU, built the AI tool to meet the needs of researchers, who were unable to observe in-person due to stay-at-home orders enacted across the state. 

As the need for this Covid tool has dissipated, the team refocused the project to let it have a life after the pandemic. It is now being sold by the researchers as a potential tool to monitor urban congestion and crisis management response. Urban planners can also get a better grasp on the needs of the public by seeing footprint, and potentially identify better access points to public services. 

“We wanted to know if there was a change from pre-COVID when people were going out in the early morning for commuting purposes versus during the lockdown when they might be going out later in the afternoon,” said Jingqin Gao, senior research associate at NYU to IEEE Spectrum. “By exploring these different trends, we were trying to better understand if there are new patterns during and after the lockdown.”

Commercialization of the product appears to be the next step for the group. “Our aim as an engineering school is not just to write papers, but to develop products that can be commercialized, and also to train the next generation of engineers on real projects where they can see how engineering contributes to and can help improve society,” said Kaan Ozbay, Director of C2SMART and Professor at NYU.