| 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 |

|
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.
|