Verizon peels back curtain on edge computing, deep learning for real-time video analytics

Image: Pixabay
Verizon's cameras can use edge computing and deep learning to immediately identify bicyclists. (Pixabay)

Verizon is currently testing a smart city service that applies deep learning and edge computing technology to video feeds in order to allow city officials to remotely keep tabs on residents in real time. The carrier said the monitoring system can discern all kinds of activities, from illegal right turns on red lights to jaywalking pedestrians to how many parking spaces are available.

The details on Verizon’s smart city tests—ongoing in Boston and Sacramento—were disclosed in a post by Verizon partner Nvidia. The silicon vendor supplies the video platform—dubbed Metropolis—as well as its Jetson TX1 processor and its Tesla GPU server and data center accelerators.

Specifically, as the post explains, Verizon’s works with cities to deploy LED street lights that contain a video camera that can connect to Verizon’s network. The cameras record what’s going on and can analyze the video data in near real time through an edge computing setup powered in part by Nvidia’s chips. For example, the video cameras can almost instantly spot things like speeding vehicles and bicyclists—but they can also send that video data to the cloud where it can be further analyzed.

“We’re trending toward being able to spot something happening at intersection A and understanding the near real-time impact on intersections B and C a few blocks away,” using cloud-based predictive analytics technology, said David Tucker, head of product management in the Smart Communities Group at Verizon, in the post.

But that’s just the start, Verizon and Nvidia promised.

“Down the road, these smart lights may be able to communicate with autonomous vehicles and support street light-to-car communication that could help reduce congestion and keep pedestrians and drivers safer,” Nvidia wrote in its post.

Nvidia disclosed its work with Verizon ahead of the company’s own GPU Technology Conference (GTC) that’s focused on artificial intelligence and deep learning. The details help to further highlight Verizon’s work in a number of complex technological areas including edge computing, deep learning and smart cities—as well as the company’s efforts to partner with specific cities like Boston and Sacramento for more advanced wireless technologies tests and deployments.

Moreover, it highlights the revenue opportunities that Verizon likely hopes to eventually uncover: Selling technology to cities that allows officials to more closely track residents’ behavior and, potentially, to provide more safety and security as autonomous cars and others such technologies hit the mainstream.

To be clear, though, Verizon is not alone in its pursuit of this area. AT&T, Cisco and others are also leveraging technologies like edge computing and deep learning to selling various smart city services and related offerings.