Quality Eye Tracking...With Your Smartphone

Quality Eye Tracking...With Your Smartphone



Eye-tracking technology — which determines where in a visual scene people are directing their gaze — has so far required pricey hardware that has kept it from finding everyday applications. But now researchers at MIT’s Computer Science and Artificial Intelligence Laboratory and the University of Georgia have created intelligent software that can turn any smartphone into an eye-tracking device.

In addition to making existing applications of eye-tracking technology more accessible, the system could enable new computer interfaces or even help detect signs of incipient neurological disease or mental illness. The system was built using machine learning — a technique in which computers learn to perform tasks by looking for patterns in large sets of training examples. The research team were able to work with data from the crowdsourced gaze patterns of 1,500 mobile-device users, which is the largest available database to date. This has reduced the margin of error right down to around a centimetre.

In future, they hope to expand the dataset to 10,000 training examples, which they expect will reduce the error margin even further, to around half a centimetre.

The researchers’ machine-learning system was a neural network, which has been enabled to run much more efficiently on a smartphone. With the reduced network, the eye tracker can operate at about 15 frames per second, which is fast enough to record even brief glances.



Join The Discussion