CPC G06F 3/013 (2013.01) [G06F 3/012 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 7/73 (2017.01); G06T 2207/10024 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30201 (2013.01)] | 20 Claims |
1. A computer-implemented method for predicting a location of an eye gaze of an operator, the method comprising:
receiving an input image, wherein the input image depicting the operator gazing at a location on a screen of a device;
extracting a plurality of regions from the input image, wherein the plurality of regions include:
one or more eyes, and
a region indicating at least a position and a rotation of a face;
generating, based on the extracted plurality of regions, an image grid, wherein the image grid includes a plurality of image data, the plurality of image data including image data that correspond to distinct regions of the plurality of regions;
determining, based on a previously trained gaze-data prediction model and using the image grid, a location of the eye gaze, wherein the location includes a multi-dimensional location of the eye gaze associated with the screen of the device; and
causing, based on the location, one or more actions associated with an operation of the device.
|