Shifting video code rate regulation method based on experience qualitative forecast

Abstract

The invention relates to a shifting video code rate regulation method based on experience qualitative forecast. According to the invention, a sending end divides an encoding video speed rate into four grades, when a mobile terminal user requires a video business, the scale of the initial code rate of a video is middle, and thus, a QoE prediction model is periodically utilized to calculate a user taste value; the predicted QoE value and the presupposed QoE threshold value are compared, if the user experience quality is lower than the threshold value, and the corresponding adjustment is performed according to the network congestion indication and encoding video speed rate fedback by a receiving end in two periods; and the code rate grade of the next period is output until the request is finished, wherein the QoE prediction model is positioned on a video server side, and the decision tree structure is improved through training a plurality of gradients. The shifting video code rate regulation method provided by the invention can be used for solving a problem that in the current code rate regulation method, the video quality subjective feeling of users can not be considered, a network resource is fully utilized, meanwhile, the generation of network congestion is avoided or slacked, and the taste quality of the users is effectively improved.

Description

technical field [0001] The invention relates to the technical field of mobile communication, in particular to a mobile video code rate adjustment method based on quality of experience prediction. Background technique [0002] With the continuous development of mobile communication technology, compression technology, and video codec technology, mobile video services have been rapidly developed and applied. The real-time transmission of mobile video streams requires high network bandwidth, and due to the large amount of video data, it is necessary to perform appropriate compression coding at the sending end, and then use relevant information to restore video data at the receiving end. Different degrees of distortion will be produced in the process of processing, transmission and restoration. [0003] In order to improve the quality of video transmission, the existing technology usually performs adaptive bit rate control on the video server side, and adjusts the sending bit ra...

AI Technical Summary

Problems solved by technology

However, this method not only increases the burden on the network, but also requires high terminal processing performance. At the same time, it is difficult for each smartphone to customize the QoE prediction module.

[0006] To sum up, how to effectively predict the user's QoE value and adjust the video bit rate according to the prediction result, there is no good solution yet

Images