| CPC H04N 19/137 (2014.11) [H04N 19/103 (2014.11); H04N 19/172 (2014.11); H04N 19/85 (2014.11)] | 19 Claims |
|
1. A method comprising:
at a device including a processor and a non-transitory memory:
receiving one or more frames in a media stream and a performance target of an encoder;
performing cycles of pre-analysis of the one or more frames to generate content features within the performance target;
assigning a content class to the one or more frames based on the content features, a previous classification, and the performance target; and
setting configurations of the encoder for encoding the one or more frames corresponding to the content class and the performance target, including identifying a degree of content discontinuities between the previous classification and the content class, and allowing changing from previous configurations of the encoder to the configurations based on the degree of content discontinuities greater than a threshold.
|