Low-latency online per-title encoding
AssigneeBitmovin, Inc.
InventorsVignesh V. Menon, Hadi Amirpour, Christian Timmerer
Life of this patent
Estimating the term…
Abstract
The technology described herein relates to online per-title encoding. A method for online per-title encoding includes receiving a video input, generating segments of the video input, extracting a spatial feature and a temporal feature, predicting bitrate-resolution pairs based on the spatial feature and the temporal feature, using a discrete cosine transform (DCT)-based energy function, and per-title encoding segments of the video input for the predicted bitrate-resolution pairs. A system for online per-title encoding may include memory for storing a set of bitrates, a set of resolutions, and a machine learning module configured to predict bitrate resolution pairs based on low-complexity spatial and temporal features.
Claims15
A method for online per-title encoding, comprising:
- receiving a video input;
- generating a plurality of segments of the video input;
- for at least one segment of the plurality of segments of the video input, extracting a spatial feature and a temporal feature;
- predicting a bitrate-resolution pairs based on the spatial feature and the temporal feature, using a discrete cosine transform (DCT)-based energy function, the bitrate-resolution pairs indicating an optimal resolution for each of a plurality of target bitrates;
- and
- per-title encoding the at least one segment for the predicted bitrate-resolution pairs,
- wherein predicting the bitrate-resolution pair comprises determining a resolution scaling factor for each bitrate in a set of bitrates.
A system for online per-title encoding, comprising:
- a memory comprising non-transitory computer-readable storage medium configured to store a set of bitrates, a set of resolutions, and a machine learning model;
- one or more processors configured to execute instructions stored on the non-transitory computer-readable storage medium to:
- receive a video input;
- generate a plurality of segments of the video input;
- for at least one segment of the plurality of segments of the video input, extract a spatial feature and a temporal feature;
- determine a resolution scaling factor, by the machine learning model, for each bitrate of a set of target bitrates;
- predict a bitrate-resolution pair, by the machine learning model, based on the spatial feature and the temporal feature, using a discrete cosine transform (DCT)-based energy function;
- and
- per-title encode the at least one segment for the predicted bitrate-resolution pair.
Dependencies are inferred from the claim text.