Semantic video encoding
AssigneeAT&T Intellectual Property I, L.P.
InventorsEric Zavesky, Lee Begeja
Life of this patent
Estimating the term…
Abstract
Devices, computer-readable media, and methods for encoding a scene in a video program using an encoding strategy that is selected in accordance with a theme that is identified in the scene are disclosed. For example, a method may include a processing system receiving a video program, identifying boundaries of a scene in the video program, identifying a theme in the scene, and selecting an encoding strategy for the scene based upon the theme, where the encoding strategy is associated with the theme. The processing system may further encode the scene using the encoding strategy that is selected.
Claims20
A method comprising:
- receiving, by a processing system, a video program;
- identifying, by the processing system, boundaries of a scene in the video program;
- identifying, by the processing system, a theme in the scene, wherein the theme comprises a concept selected from a lexical database, wherein the lexical database defines themes comprising:
- different types of objects, different sites, different types of people, different events, and different activities;
- selecting, by the processing system, an encoding strategy for the scene based upon the theme and a target bitrate, wherein the encoding strategy is associated with the theme, wherein for each of a plurality of themes, the processing system maintains a plurality of encoding strategies associated with different target bitrates, wherein the plurality of themes includes the theme;
- encoding, by the processing system, the scene using the encoding strategy that is selected;
- receiving, by the processing system, a video quality indicator of the scene that is encoded;
- and
- adjusting, by the processing system based upon the video quality indicator, the encoding strategy that is associated with the theme as maintained by the processing system, wherein the encoding strategy is adjusted when the video quality indicator falls below a video quality indicator threshold, wherein for each of the plurality of themes, the processing system maintains a plurality of video quality indicator thresholds, wherein each of the plurality of video quality indicator thresholds is for adjusting a different one of the plurality of encoding strategies.
A non-transitory computer-readable medium storing instructions which, when executed by a processing system, cause the processing system to perform operations, the operations comprising:
- receiving a video program;
- identifying boundaries of a scene in the video program;
- identifying a theme in the scene, wherein the theme comprises a concept selected from a lexical database, wherein the lexical database defines themes comprising:
- different types of objects, different sites, different types of people, different events, and different activities;
- selecting an encoding strategy for the scene based upon the theme and a target bitrate, wherein the encoding strategy is associated with the theme, wherein for each of a plurality of themes, the processing system maintains a plurality of encoding strategies associated with different target bitrates, wherein the plurality of themes includes the theme;
- encoding the scene using the encoding strategy that is selected;
- receiving a video quality indicator of the scene that is encoded;
- and
- adjusting, based upon the video quality indicator, the encoding strategy that is associated with the theme as maintained by the processing system, wherein the encoding strategy is adjusted when the video quality indicator falls below a video quality indicator threshold, wherein for each of the plurality of themes, the processing system maintains a plurality of video quality indicator thresholds, wherein each of the plurality of video quality indicator thresholds is for adjusting a different one of the plurality of encoding strategies.
A device comprising:
- a processing system;
- and
- a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
- receiving a video program;
- identifying boundaries of a scene in the video program;
- identifying a theme in the scene, wherein the theme comprises a concept selected from a lexical database, wherein the lexical database defines themes comprising:
- different types of objects, different sites, different types of people, different events, and different activities;
- selecting an encoding strategy for the scene based upon the theme and a target bitrate, wherein the encoding strategy is associated with the theme, wherein for each of a plurality of themes, the processing system maintains a plurality of encoding strategies associated with different target bitrates, wherein the plurality of themes includes the theme;
- encoding the scene using the encoding strategy that is selected;
- receiving a video quality indicator of the scene that is encoded;
- and
- adjusting, based upon the video quality indicator, the encoding strategy that is associated with the theme as maintained by the processing system, wherein the encoding strategy is adjusted when the video quality indicator falls below a video quality indicator threshold, wherein for each of the plurality of themes, the processing system maintains a plurality of video quality indicator thresholds, wherein each of the plurality of video quality indicator thresholds is for adjusting a different one of the plurality of encoding strategies.
Dependencies are inferred from the claim text.