Systems and methods for capturing training data for a gaze estimation model

A system for training a gaze estimation model comprising:

• a display for displaying a target image at a known location thereon;
• an eye-tracker positioned on or adjacent to the display;
• a plurality of image sensors configured to capture images of a subject positioned in front of the display, wherein each image sensor has a known location relative to the display;
• a computing device communicatively coupled to the plurality of image sensors, the display, and the eye-tracker, the computing device comprising a processor and a non-transitory computer-readable memory;
• and
• a machine-readable instruction set stored in the non-transitory computer-readable memory that causes the system to perform at least the following when executed by the processor:
• receive images captured from the plurality of image sensors;
• determine a reference gaze vector for one or more eyes of the subject based on the images and the known location of the target image;
• determine, with the gaze estimation model, a gaze direction vector of each of the one or more eyes of the subject from data captured by the eye-tracker;
• determine, with the gaze estimation model, an uncertainty in measurement of the gaze direction vector and an error between the reference gaze vector and the gaze direction vector;
• and
• provide feedback based on at least one of the uncertainty in measurement and the error.