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

Video processing method based on machine learning

A video processing and machine learning technology, applied in the field of video processing based on machine learning, can solve problems such as high complexity and unfavorable practical applications, achieve good image beauty and fidelity, reduce spatial redundancy, and reduce temporal redundancy. Effect

Active Publication Date: 2020-04-21
HANGZHOU ARCVIDEO TECHNOLOGY CO LTD
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If these algorithms are applied at the same time in HDR image processing, the complexity will be very high, which is not conducive to practical application

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
  • Video processing method based on machine learning
  • Video processing method based on machine learning
  • Video processing method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0043] A video processing method based on machine learning, including three parts: screening data and extracting features to form a data set, training and generating a prediction model, and video processing, specifically including the following steps:

[0044](1) When constructing a dataset, first filter the sample points of the video sequence through certain rules, and remove the spatial redundancy and temporal redundancy of the video content as much as possible, so that the obtained dataset can cover as much data as possible while the scale is small Features, not only consider the overall brightness and contrast in the scene, but also consider the brightness and contrast of each image frame and 16x16 macroblock, and finally extract a certain proportion of pixels from each frame of image as samples to form a data set;

[0045] The specific ope...

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 video processing method based on machine learning. The method comprises three parts of screening data and extracting features to form a data set, training to generate a prediction model, and video processing. The method specifically comprises the following steps: (1) when a data set is constructed, firstly, screening sample points for a video sequence through a certain rule, removing video content space redundancy and time redundancy as much as possible, and finally, extracting a certain proportion of pixel points from each frame of image as samples to form the data set; (2) when a prediction model is trained and generated, adopting a simple multi-layer full-connection neural network to ensure that the operation complexity is relatively low while the prediction precision; and (3) during video processing, processing an input image by using the trained prediction model, and then carrying out deblocking effect filtering and sample point adaptive compensation filtering. The method has the beneficial effects that the processing flow is simplified, and the operation complexity is low; the method is suitable for most videos of different styles, and presents goodimage aesthetic feeling and fidelity.

Description

technical field [0001] The present invention relates to the related technical field of video image processing, in particular to a video processing method based on machine learning. Background technique [0002] High Dynamic Range (Hereinafter referred to as HDR) video, compared with Standard Dynamic Range (Hereinafter referred to as SDR) video, the light and dark levels of the image are clearer, the image details are richer, and the real scene can be reproduced more realistically . With the development of HDR technology and the gradual popularization of HDR displays, the demand for HDR video is gradually increasing. True HDR video production requires the use of high dynamic range imaging devices at the acquisition end, and the use of HDR non-editing software during production, which means that HDR video content production has high requirements for shooting equipment and pre-processing technology. Therefore, the HDR content currently on the market is still relatively scarce...

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): G06T5/00G06T5/40G06T7/11G06N3/08H04N5/268H04N19/117H04N19/149H04N19/176H04N19/186H04N19/87
CPCG06T7/11G06T5/40G06N3/08H04N5/268H04N19/117H04N19/149H04N19/176H04N19/186H04N19/87G06T5/90G06T5/70
Inventor 王建伟谢亚光陈勇孙彦龙
Owner HANGZHOU ARCVIDEO TECHNOLOGY CO LTD
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