New research from MIT’s Computer Science and Artificial Intelligence Laboratory and the University of Georgia has developed software that can turn any smartphone into an eye-tracking device.
Eye tracking has been used for more than four decades to determine where people are directing their gaze when looking at things, such as advertisements, social situations, or television or computer screens. Knowing what catches and keeps people’s attention is valuable information. But more importantly, it can also be used to diagnose and monitor certain diseases and disorders. Eyes that shake, or twitch can be indicative of certain neurological disorders, and how a person focuses during social interactions can help diagnose conditions such as autism.
Historically, the devices used to track eye movements have been expensive, cumbersome, and difficult to use. By minimizing the physical footprint and price tag of the technology, the hope is that it can grow, becoming more accessible to people that wouldn’t otherwise be able to use it.
“The field is kind of stuck in this chicken-and- egg loop,” says Aditya Khosla, co-first author on the paper. “Since few people have the external devices, there’s no big incentive to develop applications for them. Since there are no applications, there’s no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera.”
Because millions of people around the world already carry devices with them that have most of the necessary features needed for eye tracking, Khosla’s team considered the hard part to be solved. Small, battery powered computers with high resolution cameras are everywhere, and all they need to be used as eye tracking systems is a bit of code, which can be turned into an app, and then easily distributed to millions.
Once more people start using this new technology, the larger sample sizes will be invaluable to the researchers who focus on mental and behavioral issues. Due to the cost and rarity of eye tracking devices, most current studies only focus on a few dozen people at a time, which makes it hard to gather statistically significant data. With data sets based on millions of users, great advancements in eye- motion research can be achieved.