Check patentability & draft patents in minutes with Patsnap Eureka AI!

End-to-end video compression coding method

A technology of video compression and coding method, applied in the field of end-to-end video compression and coding, can solve problems such as the inability to achieve compression performance, and achieve the effect of compressing the overall size, improving compression efficiency, and reducing memory footprint

Pending Publication Date: 2022-02-11
NORTHWEST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The downside of this approach is that these modules are optimized individually and may not achieve the best compression performance

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
  • End-to-end video compression coding method
  • End-to-end video compression coding method
  • End-to-end video compression coding method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific content of the present invention will be further explained in detail below in conjunction with the examples.

[0039] refer to Figure 1-4 , the present embodiment provides an end-to-end video compression coding method, comprising the following steps:

[0040] Step 1, input video A to be compressed;

[0041] Step 2, performing frame extraction on video A;

[0042] Step 3, normalize the video frames extracted in step 2, and set the pixel value of each video frame to 832×448;

[0043] Step 4, performing motion estimation and compression processing on the video frames normalized in step 3;

[0044] First use CNN to estimate the current frame x t with the previous reconstructed frame The optical flow, get its motion information as v t , and then use the motion encoding and decoding network to process the motion information v t Compress and encode through the motion coding network to obtain quantized motion information The motion information decoded ...

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 an end-to-end video compression coding method, which comprises the steps of firstly, carrying out frame extraction on an input video to be compressed, and then resetting the size of a video frame; secondly, acquiring motion information by using learning-based optical flow estimation and reconstructing a current video frame; then compressing corresponding behavior and residual information by using a neural network of two auto-encoder styles so as to remarkably compress the size of the current video frame; and synthesizing the compressed video frames into a new video, wherein the overall size of the current video is effectively compressed on the premise that the watching effect is not affected, and the occupied memory space is reduced. The method can be used as a video coding method on the cloud, and is superior to an H.264 video coding mode.

Description

technical field [0001] The invention relates to computer graphics processing technology, in particular to an end-to-end video compression encoding method. Background technique [0002] Today, video content contributes more than 80% of Internet traffic, and this proportion is expected to increase further. Therefore, it is crucial to build an efficient video coding system and generate higher quality frames within a given bandwidth budget. Additionally, most video-related computer vision tasks are sensitive to the quality of compressed video, and efficient video coding may bring benefits to other computer vision tasks. [0003] In the past period of time, people have proposed many image compression algorithms. These methods rely heavily on manual techniques. For example, the JPEG standard linearly maps pixels to another spatial representation by using DCT and quantizes the corresponding coefficients before entropy encoding. The downside of this approach is that these module...

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
IPC IPC(8): H04N19/50H04N19/124
CPCH04N19/50H04N19/124H04N19/537H04N19/61H04N19/577H04N19/567H04N19/19
Inventor 耿国华冯龙白涛张琦许阳李康周蓬勃周明全刘阳洋
Owner NORTHWEST UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com