Nvidia Metropolis Platform Brings AI Smarts To Smart City Video Feeds

Nvidia has taken the lid off Metropolis, an intelligent video analytics platform which applies deep learning technology to video steams to aid traffic management, pubic safety and other smart city tasks.

Effectively a combination of Nvidia’s artificial intelligence (AI) systems – notably the Jetson AI embedded computing platform – its graphics processing units, and server technology, Metropolis is a collection of the company’s advanced technology.

Injecting AI into smart cities

The idea behind Metropolis is to add a layer of smart AI capabilities to all the video feeds found in modern cities, such as CCTV, public transit video cameras, roadway and commercial building cameras.

Nvidia explained that the only a small fraction of captured video is properly analysed by humans, and that existing analytics systems are not smart enough to make sense of the nuances and complexity of video feeds from busy cities.

Through the combination of on-premise, edge and cloud based systems, Metropolis is aimed at solving this issue and conduct video analytics in real-time, which in the context of a smart city means better management of people and traffic flows, more proactive deployment of resources, and more effective public safety activity.

“Deep learning is enabling powerful intelligent video analytics that turn anonymised 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. “The Nvidia Metropolis platform enables customers to put AI behind every video stream to create smarter cities.”

Nvidia highlighted that Metropolis is already being put into action by 50 AI partner companies, which are using the platform for smart city priducts and applications.

For a company best known for making graphics cards and software for gaming, Nvidia is certainly pushing its AI technology harder and further into a variety of tech platforms and industries, notably packing its GPUs into the Google Cloud Platform to power deep learning algorithms.

What do you know about tech in transport? Take our quiz!