Eye gaze tracking

A method for eye gaze tracking comprising:

• generating a three-dimensional (3D) point cloud of a person's face from infrared (IR) data captured from an IR camera;
• generating a two-dimensional image of the person's face from visible wavelength data captured from a visible wavelength camera;
• detecting a symmetry plane of the person's face based on the 3D point cloud and the two-dimensional image, the symmetry plane divides the 3D point cloud into two portions, including minimizing a cost function to detect the symmetry plane, the cost function comprising a first parameter that provides a first weight for a first symmetrical half of the person's face and a second parameter that provides a second weight for a second symmetrical half of the person's face;
• reconstructing the 3D point cloud based on the symmetry plane;
• and
• tracking eye gaze of the person's face based on the reconstructed 3D point cloud.

An electronic device for detecting eye gaze, comprising:

• at least one camera;
• and
• one or more processors configured to:
• generate an image of a person's face from data captured from the at least one camera;
• and
• input the data into a long short-term memory (LSTM) cell to determine a direction of the person's gaze, wherein the LSTM cell comprises:
• a registration component configured to look for corresponding points in a first three dimensional point cloud of the person's face and a second three dimensional point cloud of the person's face;
• and
• a transformation component configured to measure differences between the corresponding points.