Future Apple Devices Could be Controlled With Ultra-Precise Eye-Tracking

Patent & Trademark Office published Apple’s eye-tracking application which describes a method by which users monitor the interface at a glance.
The application can shed light on one of the rumorous head-mounted display features from Apple for enhanced and virtual reality.

Apple’s application, published Thursday and shared by Patently Apple Monday, notes that “Existing computing systems, sensors and applications do not adequately provide remote eye tracking for electronic devices that move relative to the user.”

It describes one application of eye-tracking as being for “a head mounted display (HMD) [that] moves with [the] user and can provide eye tracking.”

Eye with spherical cornea modelling
A look at how the eye-tracking tech could work.
Photo: Apple

Apple’s system describes a Sensor Fusion approach in which gaze direction is identified by tracking two locations in a 3D coordinate system. It does using a single active illumination source and depth-sensing data. As the patent describes in patent-ese:

“Some implementations of the disclosure involve, at a device having one or more processors, one or more image sensors, and an illumination source, detecting a first attribute of an eye based on pixel differences associated with different wavelengths of light in a first image of the eye. These implementations next determine a first location associated with the first attribute in a three dimensional (3D) coordinate system based on depth information from a depth sensor.

Various implementations detect a second attribute of the eye based on a glint resulting from light of the illumination source reflecting off a cornea of the eye. These implementations next determine a second location associated with the second attribute in the 3D coordinate system based on the depth information from the depth sensor, and determine a gaze direction in the 3D coordinate system based on the first location and the second location.”

As the patent application explains, it could estimate gaze direction by taking multiple pictures of an eye and converting these into 3D locations. Tracking both together would let it accurately estimate gaze direction.

Similar Articles



Please enter your comment!
Please enter your name here


Most Popular