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

Fast vvc intra prediction method based on ensemble learning and probabilistic model

An integrated learning and probability model technology, applied in the field of video coding, can solve the problem of increasing coding time and achieve the effect of saving video coding time

Active Publication Date: 2021-09-28
FUZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the introduction of new technology increases the encoding time while improving the compression ratio.

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
  • Fast vvc intra prediction method based on ensemble learning and probabilistic model
  • Fast vvc intra prediction method based on ensemble learning and probabilistic model
  • Fast vvc intra prediction method based on ensemble learning and probabilistic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0051] Please refer to figure 1 , the present invention provides a kind of fast VVC intra prediction method based on integrated learning and probability model, comprising the following steps:

[0052] Step S1: Based on integrated learning and using the temporal and spatial domain correlation of video sequences, the depth information of different coding units is predicted and obtained, which is used to determine the final division depth of CU;

[0053] Step S2: Predict the partition mode of the uncoded CU by using the partition mode of the adjacent coded CU in the space-time domain, and sort according to the probability to obtain the partition mode sorting table;

[0054] Step S3: According to the obtained depth information of different coding units and the sorting table of partition modes, terminate the partitioning of the CU in advance.

[0055] In t...

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 present invention relates to a fast VVC intra-frame prediction method based on integrated learning and probability model, comprising the following steps: Step S1: Based on integrated learning and using the temporal and spatial domain correlation of video sequences, the depth information of different coding units is obtained by prediction; Step S2 : Predict the partition mode of the uncoded CU using the partition mode of the adjacent coded CU in the space-time domain, and sort by the probability to obtain the partition mode sorting table; step S3: according to the obtained depth information and partition mode sorting table of different coding units , prematurely terminate the partitioning of the CU. On the premise of ensuring the video quality, the present invention effectively saves video coding time, and has more obvious advantages when it is used for current mainstream high-definition and ultra-high-definition video coding.

Description

technical field [0001] The invention relates to the technical field of video coding, in particular to a fast VVC intra-frame prediction method based on integrated learning and probability models. Background technique [0002] The purpose of video coding is to remove a large amount of redundant information in the video (such as temporal redundancy, spatial redundancy, statistical redundancy, entropy redundancy, etc.), to compress the occupied space of video files, and improve video storage and transmission. time efficiency. [0003] VVC is a new generation of video coding standard. It achieves higher compression efficiency by updating the algorithm and improving the technology of each module in the original coding framework. Prediction technology, position-based intra-frame prediction merging technology and more angle prediction modes; in inter-frame prediction, affine motion prediction technology, advanced temporal motion vector prediction technology, adaptive motion vector...

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): H04N19/124H04N19/593G06N3/04G06N20/20
CPCH04N19/124H04N19/593G06N20/20G06N3/045
Inventor 赵铁松黄雨航吴陆狄徐艺文王楷
Owner FUZHOU UNIV