US 11,657,263 B2
Neural network based determination of gaze direction using spatial models
Nuri Murat Arar, Zurich (CH); Hairong Jiang, Campbell, CA (US); Nishant Puri, San Francisco, CA (US); Rajath Shetty, Santa Clara, CA (US); and Niranjan Avadhanam, Saratoga, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Aug. 28, 2020, as Appl. No. 17/5,914.
Claims priority of provisional application 62/948,796, filed on Dec. 16, 2019.
Prior Publication US 2021/0182609 A1, Jun. 17, 2021
Int. Cl. G06K 9/62 (2022.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06V 10/94 (2022.01); G06V 20/59 (2022.01); G06V 20/64 (2022.01); G06V 40/16 (2022.01); G06V 40/18 (2022.01); G06F 18/21 (2023.01)
CPC G06F 18/214 (2023.01) [G06F 18/2193 (2023.01); G06N 20/00 (2019.01); G06V 10/95 (2022.01); G06V 20/597 (2022.01); G06V 20/647 (2022.01); G06V 40/171 (2022.01); G06V 40/193 (2022.01)] 26 Claims
OG exemplary drawing
 
1. A method comprising:
determining a gaze direction of a subject, the gaze direction determined according to output of a machine learning model having as input one or more features determined from image data representing an image of the subject;
retrieving one or more spatial regions corresponding to one or more fields of view from a position of the subject, a spatial region of the one or more spatial regions representing a three-dimensional (3D) surface corresponding to an object;
determining, based at least on the gaze direction, that a gaze of the subject intersects with at least the spatial region of the one or more spatial regions; and
initiating an operation based at least on the gaze of the subject intersecting with the spatial region.