Skip to Content

SXSW: Allowing Ordinary Webcams to Track your Gaze

That small camera over your screen knows where you’re looking.
March 15, 2011

I reported earlier this month on a prototype laptop that has an infrared camera to track your eye movements, cutting mouse use and creating a more intuitive experience. Here at SXSW a startup just presented technology that could allow such techniques using a regular webcam, rather than the kind of specialized cameras built into that prototype.

GazeHawk has combined a suite of image recognition software that recognizes faces, estimates head motion and position in 3D, and follows eye movements. Those capabilities are combined with data from a brief calibration step where users look at specific points on their screen to identify where a person’s gaze is directed to about 70 pixels, co-founder Brian Krausz told me, after pitching in a contest for new web technology firms.

As a startup, revenue is crucial for GazeHawk who right now are targeting web designers and advertisers interested in knowing know where people look on a page, and if their ads are being noticed. The startup pays people to have their gaze tracked on the site of interest (sign up here) and does it by using their browser to tap into their webcam. The photo above shows example results: a heat map showing where a person’s eyes lingered.

Krausz said that he believed GazeHawk’s technology could be used for gaming or other consumer applications, allowing eye tracking on existing hardware. However, that would require a certain amount of rearchitecting the service, which currently doesn’t decode gazes from video in real time. “It could be done in real time,” he says, “but we don’t need to for our current application and that saves us a lot of resources.”

The 9 month old company will soon get its technology working on the iPad, said Krausz. That could give designers of apps new insight into what works for users, and in the long term perhaps even a new control method to accompany the touchscreen.

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.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

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.