Tobii Ab

Tobil Ab

David Molin

Oscar Danielsson

Patrik Barkman

Maria Gordon

Tommaso Martini

Alexander Davies

There is disclosed a computer implemented eye tracking system and corresponding method and computer readable storage medium, for detecting three dimensional, 3D, gaze, by obtaining at least one head pose parameter using a head pose prediction algorithm, the head pose parameter(s) comprising one or more of a head position, pitch, yaw, or roll; and to input the at least one head pose parameter along with at least one image of a user's eye, generated from a 2D image captured using an image sensor associated with the eye tracking system, into a neural network configured to generate 3D gaze information based on the at least one head pose parameter and the at least one eye image.

Deep learning for three dimensional (3D) gaze prediction

A method for determining gaze calibration parameters for gaze estimation of a viewer using an eye-tracking system. The method comprises obtaining a set of data points including gaze tracking data of the viewer and position information of at least one target visual; selecting a first subset of the data points and determining gaze calibration parameters using said first subset. A score for the gaze calibration parameters is determined by using the gaze calibration parameters with a second subset of data points, wherein at least one data point of the subset is not included in the first subset. The score is indicative of the capability of the gaze calibration parameters to reflect position information of the at least one target visual based on the gaze tracking data. The score is compared to a candidate score and if it is higher, the calibration parameters are set to the candidate calibration parameters and the score to the candidate score.

Determination of gaze calibration parameters

Growing community of inventors

Danderyd, Sweden

David Molin