Skip to Content
Uncategorized

Demo: Seamless Surveillance

Sarnoff shows how to turn the feeds from many surveillance cameras into a unified 3-D scene.
February 1, 2004

Video cameras are proliferating; they’re everywhere at airports, urban centers, and government buildings. But how do you tackle the tedious job of actually watching all these boring, narrowly focused video feeds? Sarnoff, the former RCA Labs now owned by SRI International, is building a solution-a system that combines video from many cameras into a 3-D model of an area. “Instead of watching the world through a soda straw, this is essentially taking video and putting it into context,” says Rakesh Kumar, a computer scientist who developed the technology as director of Sarnoff’s 14-member media vision lab. The result is called Video Flashlight: it’s like playing a video game, except the scene is of real events in real time; grab a joystick and you can swoop down hallways and fly around buildings, immersing yourself in a scene. The technology has a rich legacy: RCA was a pioneer in television technology, and its laboratory was a key source of World War IIera electronics innovations. Today, Video Flashlight is getting tested as a security tool at government buildings. At Sarnoff’s labs in Princeton, NJ, Kumar showed TR senior editor David Talbot the latest in surveillance.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.