Unlock instant, AI-driven research and patent intelligence for your innovation.

A content-aware video adaptive transmission method based on deep learning network

A deep learning network and self-adaptive transmission technology, which is applied in selective content distribution, digital video signal modification, image communication, etc., to achieve the effect of reducing network traffic and bandwidth occupation resources, reducing network traffic consumption, and improving user experience

Active Publication Date: 2020-04-10
XI AN JIAOTONG UNIV +1
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the above-mentioned prior art, the object of the present invention is to provide a content-aware video adaptive transmission method based on a deep learning network, which utilizes related applications of the deep learning network to process the server video through a convolutional neural network, Take effective information; re-process the video definition on the client side to improve the user experience of video applications in the mobile network; finally, through different operations on the client side and server side, solve the user viewing experience under the condition of poor bandwidth resources The problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A content-aware video adaptive transmission method based on deep learning network
  • A content-aware video adaptive transmission method based on deep learning network
  • A content-aware video adaptive transmission method based on deep learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to increase the understanding of the present invention, the implementation manner of the present invention will be described in detail below in conjunction with the drawings and examples.

[0028] Such as figure 1 As shown, the present invention performs a series of operations on the video at the server and the client. During the video transmission process, the low-definition video in the non-core area is used for transmission, and the user terminal uses the super-resolution image reconstruction technology based on deep learning to receive the video. After reconstruction, it can finally be played in high-definition, which can effectively reduce bandwidth costs.

[0029] Such as figure 2 Shown, the technical scheme of the present invention is described in detail below:

[0030] Step1: Classify videos according to video features.

[0031] First of all, various videos can be classified into several categories. You can refer to the methods of commercial video p...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a content-aware video adaptive transmission method based on a deep learning network. The method is a new video transmission framework, and the computing power of the client canbe effectively utilized. According to video types, specific content-aware processing is carried out at the server side, core effective information is extracted for coding processing. Definition reconstruction is carried out on the downloaded video in the server at the client, so that a relatively low-quality video can reach relatively good video quality through processing of a deep learning network, and the method can effectively reduce dependence of a video stream on a bandwidth and improve watching experience of a user.

Description

technical field [0001] The invention belongs to the technical field of mobile network transmission, and relates to a server-side video deployment method and processing method in the network transmission process, as well as a super-resolution reconstruction processing process of a requested video, and in particular to a content-aware video auto-sensing based on a deep learning network. Adapt to the transfer method. Background technique [0002] With the continuous development of mobile Internet technology and the popularization of smart terminal devices, video services have gradually played an increasingly important role in Internet services. However, traditional video transmission mechanisms rely heavily on the state of network bandwidth. Therefore, the user's viewing experience will be greatly affected by the state of the network bandwidth. However, the proposal of technologies such as HTTP Adaptive Streaming (HAS, HTTP Adaptive Streaming), which can effectively reduce th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/234H04N21/238H04N21/44H04N19/146H04N19/136
CPCH04N19/136H04N19/146H04N21/23418H04N21/238H04N21/44008
Inventor 王志文何浩郑庆华王迎春李姝洁何智超黄寿钦王轩宇王敬祎冯立楷栾佳锡柳俊全张未展赵敏李国斌高祥玉王雪松周新运
Owner XI AN JIAOTONG UNIV