Skip to Content

Deeper Vision

November 1, 2004

Researchers are making big strides toward low-cost systems that mimic human vision to give machines three-dimensional information about their environments. By building hardware that analyzes corresponding chunks of paired live images in parallel – as the human brain is thought to do – Tyzx, a startup in Menlo Park, CA, is making computerized depth perception fast enough that surveillance devices and robotic vehicles can incorporate it.

Creatures with two forward-facing eyes can perceive depth because their left and right eyes see from slightly different perspectives, in which the displacement of nearby objects is greater than that of distant objects. Using this apparent difference, called parallax, the brain swiftly determines the distance to an object. While a machine equipped with a pair of cameras can also use parallax to see in three dimensions, the amount of computation required to find matching pixels had previously made stereo machine vision impractical for most situations.

Tyzx computer vision experts Gaile Gordon and John Woodfill invented an algorithm to speed the process. Rather than trying to find pixels with the same color and brightness, the algorithm seeks out left-right pairs where there is a similar contrast in intensity between one pixel and its surrounding pixels. The researchers then built an integrated circuit that can search many groups of pixels simultaneously. They gave this chip a pair of “eyes,” and now “the image capture and the stereo computation all happen inside one relatively inexpensive, self-contained platform,” says Tyzx CEO Ron Buck.

Among the company’s early customers are federal security agencies – Buck says he can’t reveal which ones – that are using the technology to track suspicious individuals as they move against changing backgrounds such as crowds.

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.