Carter intends to experiment with Stanford University's Frankencamera platform for Nokia's N900 smart phone. This platform gives developers more freedom to develop software to control a phone's photographic hardware than they'd get from production cameras or even app SDKs like Android's.

Developers are testing NudgeCam as part of research studies that ask participants to record video diaries or interviews. Helping people compose better video can increase the amount of useful material a study produces, says Carter.

Automated guidance on capturing video has particular potential in developing regions, Carter says. In such places, people are often unfamiliar with how to make videos. He has been discussing with Berkeley researchers how NudgeCam might aid a project that helps rural health workers in India use cell phones to capture interviews with community leaders to encourage people to visit clinics.

"Videos really helped them," says John Canny, a human computer interaction researcher who leads the Berkeley project, "but in order to scale the idea, we need most of the videos to be taken by health workers, most of whom are poorly educated, and roughly a quarter of whom are illiterate. This kind of technology could help them with that."

But Canny says the app has potential for consumers, too. "Everybody could use some help," he says, pointing out that some cameras can already warn of a shaky grip or provide simple guides to composition. "This seems like a qualitative improvement on that."

Carter is also working with robot-building firm Willow Garage, which could use NudgeCam's techniques to guide users of a camera on a telepresence robot.