Scaling video processing complexity based on power savings factor
A method of scaling complexity of a video processing system including determining a power saving factor based on an operating parameter and adjusting processing of video information based on the power saving factor to reduce computation complexity. The operating parameter may include available power and/or available processing capacity. A method of complexity scalability for a video processing system using prioritized layered coding including determining a power saving factor based on one or more metrics, such as power capacity and/or available processing capacity, and reducing processing complexity of multiple prioritized coding functions in a predetermined order of priority based on the level of the power saving factor. A video processing system including a power management circuit which determines the power saving factor and a video encoder system which correspondingly adjusts computation complexity.
1. A method of scaling complexity of a video processing system, comprising:
determining a frame size, a frame rate and a frame type suitable for a given power level;
determining a power saving factor based on at least one operating parameter of the video processing system, the at least one operating parameter including available power, wherein the power saving factor is at a first level corresponding to said given power level and is adjusted in response to decreases of available power; and
adjusting processing of video information by the video processing system when the power saving factor indicates less available power than the given power level to reduce computation complexity while maintaining the frame size, the frame rate and the frame type equal to that determined for the given power level, wherein said adjusting processing of video information comprises:
performing prediction error adjustment to adjust an amount of sub-pixel interpolation when the power saving factor is at least a second level which indicates less available power than when at the first level; and
performing fast mode decision to reduce processing performed for selecting between an intracoding mode and an intercoding mode for each video block of a frame when the power saving factor is at least a third level which indicates less available power than when at the second level.
2. The method of claim 1 , wherein said determining a power saving factor based on at least one operating parameter of the video processing system comprises determining the power saving factor based on available power and available processing capacity.
3. The method of claim 1 , wherein said adjusting processing of video information based on the power saving factor comprises successively reducing processing complexity of a plurality of prioritized coding methods from a lowest priority to a highest priority in response to changes of the power saving factor indicating successively decreasing level of available power.
4. The method of claim 3 , further comprising prioritizing the coding methods based on coding efficiency and computation cost.
5. The method of claim 1 , wherein said performing prediction error adjustment comprises reducing an amount of sub-pixel interpolation in response to a change of the power saving factor indicating less available power than the given power level.
6. The method of claim 1 , wherein said adjusting processing of video information comprises forcing the intracoding mode when the power saving factor indicates that available power is less than a predetermined level and when a motion error metric is at least a predetermined threshold.
7. The method of claim 1 , wherein said adjusting processing of video information comprises successively reducing processing of intra prediction for intracoding mode in response to changes of the power saving factor indicating successively decreasing level of available power.
8. The method of claim 1 , wherein said adjusting processing of video information comprises successively reducing motion search processing in response to changes of the power saving factor indicating successively decreasing available power.
9. The method of claim 8 , wherein said successively reducing motion search comprises sequentially reducing a motion search window in response to changes of the power saving factor indicating sequentially decreasing levels of available power.
10. The method of claim 1 , wherein said adjusting processing of video information further comprises:
reducing motion search processing when the power saving factor is at least a fourth level which indicates less available power than when at the third level.
11. The method of claim 10 , further comprising reducing intra prediction processing when the power saving factor is at least the third level.
12. The method of claim 11 , wherein said reducing intra prediction processing comprises successively reducing intra prediction processing with successive changes of the power saving factor indicating less available power than when at the third level.
13. The method of claim 10 , wherein said reducing motion search processing comprises successively reducing motion processing with successive increases of the power saving factor indicating less available power than when at the fourth level.
14. The method of claim 10 , further comprising forcing intracoding mode when the power saving factor is at least a fifth level indicating less available power than when at the fourth level and when a motion error metric is at least a predetermined threshold.
15. The method of claim 10 , further comprising disabling deblock filtering when the power saving factor is at least a fifth level which indicates less available power than when at the fourth level.
16. A method of scaling complexity of a video processing system, comprising:
determining a frame size, a frame rate and a frame type for a power saving factor that indicates a given power level;
determining a level of the power saving factor based on at least one operating parameter of the video processing system, the at least one operating parameter including available power, wherein the power saving factor is at a first level corresponding to said given power level and increases with decreasing available power level; and
adjusting processing complexity of at least one coding method by the video processing system for a given video sequence in response to increases of the power saving factor while maintaining frame size, frame rate and frame type equal to that determined for the given power level, wherein said adjusting processing complexity comprises:
performing prediction error adjustment to adjust an amount of sub-pixel interpolation when the power saving factor is at least a second level which is greater than the first level; and
performing fast mode decision to reduce processing performed for selecting between an intracoding mode and an intercoding mode for each video block of a frame when the power saving factor is at least a third level which is greater than the second level.
17. The method of claim 16 , wherein said adjusting processing complexity further comprises limiting processing of intra prediction for an intracoding mode when the power saving factor is at least the third level.
18. The method of claim 16 , wherein said adjusting processing complexity further comprises adjusting motion search processing when the power saving factor is at least a fourth level which is greater than the third level.
19. The method of claim 16 , wherein said adjusting processing complexity further comprises forcing intracoding mode for at least one video block when the power saving factor is at least a fourth level which is greater than the third level.