In a city of the future, it would be nice to know quickly if there’s a fire burning out of control, a crime in progress at a certain location, or a traffic snarl at a particular corner.

Nvidia hopes to detect such problems in smart cities using Nvidia Metropolis, which the company said could pave the way for the creation of smart artificial intelligence cities. Nvidia announced the tech ahead of its GPU Technology conference this week in San Jose, California.

Metropolis is a video analytics platform that applies deep learning AI to video streams for applications such as public safety, traffic management, and resource optimization.

Nvidia said that Metropolis could make cities safer, and more than 50 partner companies are already providing products and applications for AI city uses based on graphics processing units (GPUs) made by Nvidia.

“Deep learning is enabling powerful intelligent video analytics that turn anonymized video into real-time valuable insights, enhancing safety and improving lives,” said Deepu Talla, vice president and general manager of the Tegra business at Nvidia, in a statement. “The Nvidia Metropolis platform enables customers to put AI behind every video stream to create smarter cities.”

Above: Nvidia Metropolis will apply deep learning to the video surveillance.

Image Credit: Nvidia

Video is the world’s largest generator of data, captured by hundreds of millions of cameras deployed in areas such as government property, public transit, commercial buildings, and roadways. By 2020, the cumulative number of cameras is expected to rise to approximately 1 billion.

But people can only monitor a fraction of that content, which is stored on disks for later review. Initial efforts at real-time video analytics techniques have proved far less reliable than human interpretation, Nvidia said.

Intelligent video analytics solves this challenge by using deep learning in cameras, on-premises video recorders, and servers, and in the cloud to monitor video instantaneously with accuracy and scalability. The deep learning inferencing can happen at the edge, in devices such as security cameras, or in servers in data centers using Nvidia’s Tesla GPU accelerators and Quadro graphics.

“With the fast-paced environment of a city, there are a near infinite number of activities taking place,” said Mahesh Saptharishi, chief technology officer at video surveillance equipment maker Avigilon, in a statement. “We’re excited by the potential of Nvidia’s Metropolis platform, as Avigilon continues to deliver AI-powered surveillance solutions and video analytics that focus users’ attention on what matters most, in order to take action.”