Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Low-code-rate video coding and decoding method based on image reconstruction convolutional neural network

A convolutional neural network and video encoding and decoding technology, which is applied in the field of low-bit-rate video encoding and decoding, can solve problems such as video compression and distortion, achieve the effect of enhancing learning ability, overcoming weak learning ability, and improving the quality of upsampled images

Active Publication Date: 2019-08-02
XIDIAN UNIV
View PDF11 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It solves the problem of serious compression distortion of video after low-bit-rate video codec in the existing technology, and better preserves image details

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
  • Low-code-rate video coding and decoding method based on image reconstruction convolutional neural network
  • Low-code-rate video coding and decoding method based on image reconstruction convolutional neural network
  • Low-code-rate video coding and decoding method based on image reconstruction convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with the accompanying drawings.

[0050] refer to figure 1 , to further describe in detail the specific steps for realizing the present invention.

[0051] Step 1, input video.

[0052] Input a video consisting of multiple images of the same resolution.

[0053]Step 2, extract an unselected image from the input video.

[0054] Step 3, downsampling the selected image.

[0055] Using the bicubic interpolation method, the extracted image is down-sampled by 2 times to obtain a down-sampled low-resolution image.

[0056] The steps of the described double cubic interpolation Bicubic method are as follows:

[0057] The first step is to calculate the weight of each pixel in the surrounding 4x4 pixel block centered on each pixel in each downsampled image in the low-resolution video according to the following formula:

[0058]

[0059] in, Represents the weight of the rth pixel in the xth row, the yth...

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 provides a low-code-rate video coding and decoding method based on an image reconstruction convolutional neural network. The method is used for solving the problem that in the prior art,a video is seriously compressed and distorted after being coded and decoded at a low code rate. The implementation steps are as follows: carrying out down-sampling operation on the input video to obtain a low-resolution video; and performing video encoding and decoding on the low-resolution video by using a standard X265 codec to obtain a decoded low-resolution video, inputting the decoded low-resolution video into the trained image reconstruction convolutional neural network, and then obtaining a reconstructed video with the same resolution as the input video. According to the invention, serious compression distortion caused by video coding and decoding can be effectively inhibited at a low code rate, and the video quality can be well improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a low-bit-rate video encoding and decoding method based on image reconstruction convolutional neural network in the technical field of video image processing. The invention can be used for compression coding and decoding of low bit rate video formed by natural images. Background technique [0002] Coding of video images is an effective means to reduce video redundant data during video transmission. There are many standard algorithms for video image coding and decoding. The latest generation of high-efficiency video coding standards as the latest video compression standards have achieved good results. The AVC standard saves about 50% of the code stream, but it also greatly increases the encoding complexity. This standard framework continues to use the previous international standard hybrid coding framework. The main implementation steps of the coding framework are...

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): H04N19/85H04N19/593H04N19/176H04N19/80G06N3/04G06N3/08
CPCH04N19/85H04N19/593H04N19/176H04N19/80G06N3/08G06N3/045
Inventor 何刚王正蒋昊李云松
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com