Intelligent decoded picture buffering

摘要

A system and method for intelligent decoded picture buffering is described. In one embodiment, a video bitstream buffer receives and temporarily holds an encoded compressed bitstream containing portions of a video. Then, a look ahead parser scans ahead in the video to analyze portions of the encoded video bitstream in the video bitstream buffer to predict the value of the video. Based on this prediction, an intelligent memory manager prioritizes the video portions, and then sends the high valued video portions to a first buffer and sends the low valued video portions to a second buffer.

主权项

1. A video data buffering system comprising:
a memory including a first memory and a second memory; and a hardware processor configured to:
predict a value for a portion of video data to be decoded by looking ahead at a first encoded portion of a video data bitstream corresponding to the portion of the video data to be decoded, wherein the value is predicted based on a frequency of reference to the first encoded portion by a plurality of portions subsequent to the first encoded portion in the video data bitstream;assign a first value as the predicted value when the frequency of reference is equal to or above a threshold value and assign a second value as the predicted value when the frequency of reference is below the threshold value;decode the first encoded portion of the video data bitstream;store the decoded portion in a first buffer in the first memory when the assigned value is the first value or in a second buffer in the second memory when the assigned value is the second value, wherein the first buffer has a faster access time than the second buffer;subsequent to storing the decoded portion in the first buffer or the second buffer, update the predicted value based on a frequency of reference to the decoded portion by a second encoded portion of the video data bitstream; andmove the decoded portion between the first buffer and the second buffer based on the updated predicted value, wherein the predicted value for the portion of the video data to be decoded is a predicted bandwidth of the portion of the video data to be decoded, a predicted lifespan of the portion of the video data to be decoded, or a predicted bandwidth variation of the portion of the video data to be decoded over the lifespan.