A distributed processing method and device for streaming audio and video data

Abstract

The invention discloses a distributed processing method oriented to streaming audio-video data and a device thereof. The method comprises the following steps: S1, dividing multiple physical machines into different types with specific functions as follows: a distributed resource management function, a distributed data memorization function, a distributed encapsulation slicing function, a distributed decoding function, and other audio-video distributed processing function, and establishing a mapping relation among the physical machines of different types; S2, extracting the audio-video code streams from all transmission channels to save in the memory; S3, directly encapsulating the fragments of the audio-video code streams stored in the memory as an audio-video short fragment capable of independently performing coding and decoding; S4, coding and decoding the audio-video short fragment under the situation of not needing to maintain the coding and decoding context of each path; and S5, performing further audio-video processing on the decoded YUV data or independently coded and decoded audio-video short fragment .

Description

technical field [0001] The present invention relates to the field of audio and video processing, in particular to a distributed processing method and device for streaming audio and video data. Background technique [0002] With the development of mobile Internet, big data, and artificial intelligence, the demand for audio and video processing in live broadcast, entertainment, communication, security and other fields is increasing. How to achieve high performance, high throughput, high efficiency, easy maintenance, easy expansion, and easy optimization of audio and video processing systems is a new challenge in this field. [0003] Traditional audio and video processing methods generally only support the input of one or several types of audio and video data (for example, local files, RTP, RSTP, HLS), and then directly perform distributed codec processing on these forms of audio and video data. Therefore, the traditional processing method has the following disadvantages: 1. I...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the above problems encountered in the processing of massive audio and video streaming data, such as difficult expansion of input forms, low encoding and decoding efficiency, small number of channels supported, high power consumption, and the number of physical machines cannot change with the change of user traffic. Problems such as load imbalance

Images