A video call method and device based on deep imitation learning

Abstract

The embodiment of the invention provides a video call method and device based on deep imitation learning. The method comprises the following steps: obtaining the transmission information of a previoustransmission time slot for the current transmission time slot of a video call; wherein the transmission information comprises transmission layer information and application layer information; inputting the transmission information into a code rate optimization network model to obtain a transmission code rate of the current transmission time slot; wherein the code rate optimization network model is a model obtained by training according to a training set, and the training set comprises real transmission information and a real transmission code rate of each transmission time slot in the samplevideo call; and sending the video call data to the receiving end based on the transmission code rate of the current transmission time slot. Therefore, the proper transmission code rate in the video call is determined in real time, and the video call quality is improved.

Description

technical field [0001] Embodiments of the present invention relate to the field of communication technologies, and in particular, to a video call method and device based on deep imitation learning. Background technique [0002] With the development of communication technology, real-time video calls have become an indispensable part of people's lives. And mobile wireless network applications, such as crowdsourcing live broadcast, cloud video games, robotics, vehicle remote operation, etc., continue to promote the growth of video call traffic. [0003] However, the quality of existing video calls is still not satisfactory. For example, during a video call, problems such as blurred images, loss of image frames, and freezing may occur. [0004] The main reason for the low quality of existing video calls is that the incoordination between the application layer and the transport layer makes it impossible to determine the appropriate bit rate for data transmission. Specifically, ...

AI Technical Summary

Problems solved by technology

[0003] However, the quality of existing video calls is still not satisfactory. For example, during a video call, problems such as image blurring, image frame loss, and freezing may occur

[0004] The main reason for the low quality of existing video calls is: the inconsistency between the application layer and the transport layer, resulting in the inability to determine the appropriate bit rate for data transmission

Specifically, the transport layer usually updates the network capacity estimation with millisecond-level granularity to respond to network changes as dynamically as possible, while the video codec at the application layer can only change the video bit rate at large time intervals, resulting in the video encoder cannot Follow the data transmission rate of the transport layer in real time to adjust the transmission code rate

[0005] It can be seen that due to the incoordination between the application layer and the transport layer in the existing video call technology, it is impossible to determine the appropriate transmission rate, resulting in low video call quality

Images