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

A Virtual Viewpoint Video Quality Prediction Method

A prediction method and virtual viewpoint technology, applied in the field of virtual viewpoint video quality prediction, can solve the problems of lack of consideration and weak correlation, etc.

Active Publication Date: 2018-12-07
NINGBO UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since this method does not consider the impact of object boundary occlusion on the quality of the virtual viewpoint video, the predicted PSNR value of the virtual viewpoint video has a weak correlation with the original PSNR value.

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
  • A Virtual Viewpoint Video Quality Prediction Method
  • A Virtual Viewpoint Video Quality Prediction Method
  • A Virtual Viewpoint Video Quality Prediction Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0035] A kind of virtual viewpoint video quality prediction method proposed by the present invention, its overall realization block diagram is as follows figure 1 As shown, it includes the following steps:

[0036] ① Denote the original color video as I Co , will be compared with I Co The corresponding original depth video is denoted as I Vo ; Use the HTM platform, and use the set encoding and quantization parameters to I Vo Compress to obtain the distorted depth video under the encoding and quantization parameters set, denoted as I Vd ; will I C The color image of the mth frame in o is denoted as Will I V The m-th frame depth image in o is denoted as Will I Vd The distorted depth image of the mth frame in is denoted as Wherein, the value range of the set encoding quantization parameter is [0, 51], and the encoding quantization pa...

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 virtual viewpoint video quality prediction method. According to the method, a mean value and a variance of each segmentation block in a first color image frame and a first depth image frame, the mean value of each segmentation block in respective gradient images of the first color image frame and the first depth image frame, and the mean value of each segmentation block in depth difference images of the first depth image frame and a first distortion depth image frame are used as training features, the mean value of each segmentation block in a label image corresponding to the first distortion depth image frame is used as a training label, a training sample composed of the training features and the training labels is trained by using SVM, and thus an SVM regression model is acquired; the mean value and the variance corresponding to any rest frame as test features, and the SVM regression model is used for testing; and a quality value of a distorted virtual viewpoint video is acquired by using an output test value. The method has the advantages that each influence factor on drawing quality of a virtual viewpoint is considered, and thus the video quality of the virtual viewpoint can be effectively predicted in the case of compression distortion of the depth video.

Description

technical field [0001] The invention relates to a video quality prediction technology, in particular to a virtual view point video quality prediction method. Background technique [0002] Free Viewpoint Video (FVV, Free Viewpoint Video) system is a further development on the basis of 3D video system, which can enable users to obtain better visual experience and feel a real sense of depth and immersion. It is a new generation of multimedia video system direction of development. Due to the limitation of cost and transmission bandwidth, it is impossible to place a camera on every viewpoint. Multi-view Video plus Depth (MVD, Multi-view Video plus Depth) can overcome the limitation of the camera's ability to obtain real viewpoints and satisfy users' freedom to choose viewing angles. It has become the mainstream representation format of scenes in free-viewpoint video systems. In the free-viewpoint video system, the virtual viewpoint video at any position can be generated by usin...

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): H04N13/111H04N13/128H04N13/15H04N17/02H04N19/124
CPCH04N13/111H04N13/15H04N17/02H04N19/124
Inventor 陈芬焦任直彭宗举蒋刚毅郁梅
Owner NINGBO 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