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

A No-reference Asymmetric Virtual Viewpoint Stereoscopic Video Quality Evaluation Method

A technology of virtual viewpoint and stereoscopic video, applied in stereoscopic systems, televisions, electrical components, etc.

Active Publication Date: 2021-04-09
西安灵境辰星文化科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with FR and RR evaluation methods, the research of NR quality evaluation method is more challenging

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 No-reference Asymmetric Virtual Viewpoint Stereoscopic Video Quality Evaluation Method
  • A No-reference Asymmetric Virtual Viewpoint Stereoscopic Video Quality Evaluation Method
  • A No-reference Asymmetric Virtual Viewpoint Stereoscopic Video Quality Evaluation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0068] Such as figure 1 As shown, a method for evaluating the quality of a stereoscopic video with no reference to asymmetrical virtual viewpoints comprises the following steps:

[0069] Step 1. Input the left and right viewpoints as asymmetrically distorted virtual viewpoint stereoscopic video to be evaluated, and extract the left viewpoint video V of the virtual viewpoint stereoscopic video to be evaluated respectively L and right view video V R , where the left view video V L and right view video V R The width of each is W, the height is H, and the total number of video frames is N; wherein, W, H and N are natural numbers;

[0070] Step 2, extract the left view video V respectively L The luma channel I L and right view video V R The luma channel I R ; Among them, the luminance channel I of the left view video L and the luma channel...

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 method for evaluating the quality of asymmetric virtual viewpoint stereoscopic video without reference, comprising: respectively downsampling each frame image in the luminance channel of the left viewpoint video and the right viewpoint video of the virtual viewpoint stereoscopic video to be evaluated twice, and according to The corresponding images in the three scales obtained by downsampling calculate the spatial local features and spatial global features of the left and right viewpoints, as well as the temporal local features and temporal global features of the left and right viewpoints; and form the left viewpoint feature vector and right viewpoint respectively. Viewpoint feature vector; Simultaneously, calculate the weight of left viewpoint video and the weight of right viewpoint video; Fusion is carried out with left viewpoint feature vector and right viewpoint feature vector and corresponding left viewpoint video weight and right viewpoint video weight, obtains stereoscopic feature vector; Finally, the stereoscopic feature vector is used as an input, and the random forest technique is used to calculate the objective quality evaluation value of the virtual viewpoint stereoscopic video to be evaluated. This evaluation method is more in line with the subjective perception of human eyes.

Description

technical field [0001] The invention relates to the field of video quality evaluation, in particular to a method for evaluating the quality of stereoscopic video with asymmetrical virtual viewpoints without reference. Background technique [0002] Currently, 3D video and Free Viewpoint Video (FVV) are more and more widely used, providing users with a vivid and lifelike visual experience. During the transmission process, due to the limitation of network bandwidth, it is impossible to transmit videos from all viewpoints. The multi-view video plus depth (MVD) expression only needs to encode color video and depth video of multiple viewpoints, and at the decoding end, multiple virtual viewpoints can be generated by using depth map-based rendering (DIBR) technology. However, most existing DIBR-based virtual viewpoint rendering methods are still imperfect, and the synthesized virtual viewpoint videos may have various geometric distortions such as holes, artifacts, and distortions....

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): H04N17/00H04N13/106
CPCH04N17/00H04N2013/0074H04N13/106
Inventor 彭宗举崔帅南邹文辉陈芬郁梅
Owner 西安灵境辰星文化科技有限公司
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