Video compression using multiple computing agents

摘要

A system and method of using multiple processors to perform video compression is provided. A video sequence is partitioned into subsequences and processing assignments for the subsequences are distributed among a plurality of processors. A picture type is then determined for each picture in each subsequence and the encoding complexity of each picture is modeled, based on the picture type. Based on the modeling, a number of bits is allocated to each picture. Each picture is then compressed in accordance with the bits allocated. Another aspect provides for encoding of pictures in a video sequence using dynamic modeling of the encoding complexity of future pictures in the video sequence. Bits are allocated to the encoding of a current picture in the video sequence based on the dynamic model. The current picture is then encoded based on the bits allocated.