US 12,230,040 B2
Robust state estimation
Yuzhuo Ren, Sunnyvale, 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 Nov. 21, 2023, as Appl. No. 18/516,531.
Application 18/516,531 is a continuation of application No. 17/410,564, filed on Aug. 24, 2021, granted, now 11,830,259.
Prior Publication US 2024/0087341 A1, Mar. 14, 2024
Int. Cl. G06V 20/59 (2022.01); B60W 40/08 (2012.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01); G06V 40/16 (2022.01); G06V 40/18 (2022.01)
CPC G06V 20/597 (2022.01) [B60W 40/08 (2013.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01); G06V 40/161 (2022.01); G06V 40/171 (2022.01); G06V 40/172 (2022.01); G06V 40/18 (2022.01); B60W 2540/229 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining, based at least on eye state information of a person depicted in an image, a set of blink parameters for the person over a period of time;
determining context data for a time at which the image data was generated, the context data relating to one or more environmental conditions of a vehicle operated by the person;
determining, using the eye state information, blink frequency information for the period of time;
providing the set of blink parameters as input to a first neural network, and the blink frequency information as input to a second neural network;
generating a first drowsiness prediction for the person using the first neural network, and a second drowsiness prediction for the person using the second neural network;
generating an overall drowsiness determination for the person based at least in part on the first drowsiness prediction and the second drowsiness prediction;
determining the overall drowsiness determination exceeds a threshold; and
activating one or more alerts for the person, based at least on the context data.