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

Low-complexity video coding method based on random training set adaptive learning

An adaptive learning and video coding technology, applied in the field of low-complexity video coding, can solve the complex and advanced problems of HEVC video coding, and achieve the effects of reducing computational complexity, saving time, and improving efficiency

Active Publication Date: 2017-07-07
河北雄华科技有限公司
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to address the shortcomings of the existing HEVC video coding complexity, and propose a low-complexity video coding method based on random training set adaptive learning, by simplifying the determination method of CU and PU partition mode and its rate-distortion cost The amount of calculation can reduce the complexity of encoding while ensuring the encoding quality, especially suitable for fast real-time video encoding

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-complexity video coding method based on random training set adaptive learning
  • Low-complexity video coding method based on random training set adaptive learning
  • Low-complexity video coding method based on random training set adaptive learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with drawings and embodiments.

[0024] Such as Figure 1-6 As shown, the low-complexity video coding method based on random training set adaptive learning adopts the HM model of HEVC video coding, and the test conditions use the HEVC video coding general test Full Intra encoding configuration file for High Efficiency Video Coding with encoder_intra_main.cfg.

[0025] Figure 4 Shown is the general encoding flow chart of the present invention, before each video sequence is encoded, the video sequences are grouped according to the frame rate, the first two frames of each group of video are learning encoding frames, and the standard HEVC encoding method is run to traverse all The 2N×2N (N=32, 16, 8) CU division mode and the 2N×2N (N=4) minimum size CU corresponding to the PU division mode obtain video encoding parameters and apply them to subsequent fast encoding frames to Implement low-complexity enc...

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 low-complexity video coding method based on random training set adaptive learning. The low-complexity video coding method includes a learning coding method and a rapid coding method. The low-complexity video coding method comprises the following steps: firstly, grouping video sequences according to frame rates, wherein first two frames in each group of video frames are learning coding frames for parameter learning, and subsequent frames are rapid coding frames; optimizing a CU (Coding Unit) partition method and a PU (Prediction Unit) partition method of video coding according to video coding parameters obtained according to the learning coding frames; during CU partition, ending partition of non-minimum-size CUs in advance or skipping rate distortion calculation of a current CU for direct partition; and during intra-frame prediction, judging a partition mode of a PU corresponding to a minimum-size 8x8 CU in advance or skipping rate distortion calculation of a current PU and directly judging the partition mode of the current PU. Through adoption of the low-complexity video coding method, the complexity in CU partition judgment and PU partition judgment in HEVC (High Efficiency Video Coding) is lowered greatly. The HEVC efficiency is increased effectively on the premise of keeping the coding quality.

Description

technical field [0001] The invention belongs to the technical field of high-efficiency video coding (HEVC), in particular to a low-complexity video coding method based on random training set adaptive learning. Background technique [0002] In recent years, with the application of high-definition and ultra-high-definition video (resolution up to 4K×2K, 8K×4K) into people’s field of vision, video compression technology has been greatly challenged. In addition, various video applications are emerging with the development of network and storage technologies. The diversification of video applications and the trend of high-definition put forward higher requirements for video compression performance. To this end, in April 2010, the Video Coding Experts Group (VCEG) of ITU-T and the Moving Picture Experts Group (MPEG) of ISO / IEC established the Joint Video Coding Team (JCT-VC) to jointly formulate a new generation of video coding standards. In 2013, the HEVC (High Efficiency Video...

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 Applications(China)
IPC IPC(8): H04N19/147H04N19/61H04N19/567H04N19/176H04N19/122
Inventor 陆宇林雅梦刘华平沈礼权姚英彪
Owner 河北雄华科技有限公司
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