US 11,947,717 B2
Gaze estimation systems and methods using relative points of regard
Gilad Drozdov, Haifa (IL); Oren Haimovitch Yogev, Los Altos, CA (US); and Igor Nor, Haifa (IL)
Assigned to BLINK TECHNOLOGIES INC., Palo Alto, CA (US)
Filed by BLINK TECHNOLOGIES INC., Palo Alto, CA (US)
Filed on Jan. 24, 2022, as Appl. No. 17/582,016.
Claims priority of provisional application 63/140,258, filed on Jan. 22, 2021.
Prior Publication US 2022/0236797 A1, Jul. 28, 2022
Int. Cl. G06F 3/01 (2006.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06T 7/73 (2017.01); G06V 10/25 (2022.01)
CPC G06F 3/013 (2013.01) [G06F 3/012 (2013.01); G06N 3/084 (2013.01); G06T 7/74 (2017.01); G06V 10/25 (2022.01); G06N 3/045 (2023.01)] 19 Claims
OG exemplary drawing
 
1. A method to determine a target point of regard associated with a user of a display, the method comprising:
receiving a target image data associated with the user from a camera coupled with the display, wherein the target image data includes a target eye patch image data associated with the user and target head region image data;
determining, using a convolutional neural network, the target point of regard associated with the target image data based on:
the target eye patch image data,
a plurality of aggregated gaze reference vectors, and
a plurality of reference image data associated with the user, the plurality of reference image data respectively associated with the plurality of aggregated gaze reference vectors, one or more of the plurality of reference image data each including reference head region image data;
determining a target 6D head position associated with the target head region image data;
determining a reference 6D head position associated with the reference head region image data;
determining a target 3D eye position associated with the target eye patch image data;
wherein the target point of regard is determined within a predetermined threshold; and
mapping the target point of regard onto the display.