Live public street cams are tracking social distancing
Voxel51, a U-M startup led by Prof. Jason Corso, uses custom AI to continuously track vehicle, cyclist, and pedestrian traffic in real time at some of the most visited places in the world.
With advanced computer vision models and live public street cam video, a University of Michigan startup is tracking social distancing behaviors in real time at some of the most visited places in the world.
Voxel51’s new tool shows—quite literally—an uptick in public gathering in Dublin on St. Patrick’s Day, for example, and at New Jersey’s Seaside Heights boardwalk during a recent weekend of unusually good weather.
The tool uses the company’s existing platform and underlying custom AI to continuously track vehicle, cyclist, and pedestrian traffic at seven locations: Times Square; Abbey Road in London; Fremont Street in downtown Las Vegas; Seaside Heights in New Jersey; a beach in Ft. Lauderdale and intersections in Dublin and Prague. Several other locations are in beta, and more will be added soon.
It assigns each place a “physical distancing index,” or PDI score, once every 15 minutes.
“This pandemic is having an unprecedented impact on our daily lives and what we’re trying to do is create a tool to improve public awareness,” said Jason Corso, professor of electrical and computer engineering at U-M and CEO of Voxel51, an Ann Arbor video analytics and data management company. “The PDI score helps people understand and compare how the coronavirus is changing social behaviors over time and enables municipalities to visualize how they’re doing from a public health perspective.
“Even though the virus is spreading, overall, we can see that the public response to the stay-at-home mandates has been rather dramatic and impressive.”
While other projects are also tracking lockdown compliance, what’s different about Voxel51’s approach is that it’s real-time, video-based and protects privacy. Data sources like mobile phones don’t protect privacy and only offer approximate locations.
On this new platform, viewers can click on a specific point in time on an individual city graph to see historic footage as well as additional details about policies such as school closures and stay-at-home orders.
The graphs provide insights into the difficulty in limiting human activity in the face of good weather and special celebrations: Fort Lauderdale is one of the top destinations for students on spring break. As shown on the detailed graph for Florida, despite the governor issuing a public emergency on Feb. 29, crowds were at all-time highs in early March, yet started to fall dramatically after the mayor issued emergency methods on March 17 closing bars and nightclubs. And New York City – hit hardest by the pandemic, has a very tough time keeping its 8 million tightly-packed residents completely shuttered in.
Voxel51 plans to add new locations regularly, as well as blog posts analyzing the data. The company is also accepting requests to add locations or specific installations of the system for local government and taxpayer usage. Views of different parks could help residents locate the least trafficked area to safely walk their dog, for example.
The researchers are also in the process of adding curves to the graphs to plot weather, case rates and death rates.
“We expect to find rich information in the joint analysis of the physical distancing index and these other feeds,” Corso said. “There is even a chance that the PDI can feed into a predictive model for cities not yet greatly affected and the potential for a renewed outbreak next year.”
The research featured in this story is related to some of the issues facing individuals around the world due to COVID-19. See our COVID-19 page for additional resources and news from Electrical & Computer Engineering.
In the Media
Voxel51 lands funds for its platform to manage unstructured dataTechCrunch features Voxel51, a startup founded by Prof. Jason Corso, which closed on $12.5m in Series A funding.
Announcing Our $12.5M Series A Funding to Bring Transparency and Clarity to the World’s DataVoxel51, founded by Prof. Jason Corso, closed on $12.5M Series A funding to accelerate the next phase of their growth in bringing data-centric Machine Learning to the world.
Introducing FiftyOne: A Tool for Rapid Data & Model ExperimentationAlum Brian Moore details Voxel51's new (and open source!) tool for your machine learning toolbox
Ann Arbor-based Voxel51 launches industry’s first open-source experimentation tool
Ann Arbor-based artificial intelligence software company Voxel51 announced the launch of an open-source tool, called FiftyOne, that helps data scientists and machine learning engineers tackle the laborious process of image data management. The company was co-founded by Prof. Jason Corso and alumnus Dr. Brian Moore.