>The exact functions of Tobii’s integrated technology aren’t clear, but we do know that the smartphone uses Tobii’s algorithms as well as an infrared camera.
What is the cost of adding the infrared camera?
There might be a better approach that doesn't require a special camera.
A MIT research group is trying to provide eye tracking control for everyone using basic hardware (tablets, smartphones, webcams).
They created a deep learning app that crowdsources eye data:
>Gazecapture
itunes.apple/com/us/app/gazecapture/id1025021075?mt=8
>Eye Tracking for Everyone
>K. Krafka*, A. Khosla*, P. Kellnhofer, H. Kannan, S. Bhandarkar, W. Matusik and A. Torralba
>IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
news.mit/edu/2016/eye-tracking-system-uses-ordinary-cellphone-camera-0616
The app session only takes about a minute to complete.
Look at the dots that randomly appear.
Tap the left side of the screen if you see an L, and the right side of the screen if you see an R.
The current accuracy with 1500 people is about 1 centimeter on a mobile phone, and 1.7 centimeters on a tablet.
If the researchers can get data from 10,000 people, they think that they can reduce the error rate to 0.5 centimeters, which should be good enough for many eye-tracking applications.
Also, there might not have to be use of infrared lights.
>“The field is kind of stuck in this chicken-and-egg loop,” says Aditya Khosla, an MIT graduate student in electrical engineering and computer science and 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.”
csail.mit/edu/eye-tracking_system_uses_ordinary_cellphone_camera