CPC G06V 20/40 (2022.01) [G06N 3/08 (2013.01)] | 20 Claims |
1. A method, comprising:
receiving first data representative of a first video frame in a video stream;
determining from the first data a first feature identification representative of one or more features captured in the first video frame;
receiving second data representative of a second video frame in the video stream;
generating an intermediate result of analysis of the second data using a first portion of an artificial neural network, the intermediate result identifying a preliminary feature identification of one or more features captured in the second video frame and a confidence level of the preliminary feature identification;
making a determination that the confidence level of the preliminary feature identification for the second video frame is above a threshold based at least in part on the first feature identification for the first video frame; and
terminating, responsive to the determination, computation of a second portion of the artificial neural network.
|