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

Quality evaluation method for immersive virtual reality based on human visual perception process

A technology of virtual reality and perception process, which is applied in the direction of television, electrical components, image communication, etc., to achieve the effect of small error, easy implementation, and simple and effective implementation method.

Inactive Publication Date: 2020-08-18
TIANJIN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, the three-dimensional features in the virtual reality experience will have certain requirements for comfort, but previous studies have mostly ignored this content

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
  • Quality evaluation method for immersive virtual reality based on human visual perception process
  • Quality evaluation method for immersive virtual reality based on human visual perception process
  • Quality evaluation method for immersive virtual reality based on human visual perception process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention proposes an immersive virtual reality quality evaluation method based on the human visual perception process, which is based on feature extraction and uses machine learning methods for final quality determination. The overall framework is as follows figure 1 Shown. The specific evaluation method includes the following steps:

[0032] Step 1: For the physical distortion analysis of virtual reality data, the present invention uses natural statistics as a quantification method. First, the distorted virtual reality video is framed, and the extracted left frame V l And right frame V r Calculate natural statistical characteristics according to formula (1):

[0033]

[0034] After calculation, the result can be defined as the equalization coefficient (MSCN). On this basis, the method of equalized Gaussian distribution (GGD) fitting can be used in the above result graph. The GGD fitting process follows formula (2).

[0035]

[0036] Thus, two-dimensional featu...

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 relates to an immersive virtual reality quality evaluation method based on human visual perception process. The method comprisesrandomly extracting the distorted virtual reality data, calculating the natural statistical characteristics of the left frame Vl and the right frame Vr of the extracted distorted VR map respectively, and extracting the feature vector by adopting an equalizedGaussian distribution fitting method; performing comfort analysis oriented to virtual reality and computingreference VR disparity map and distorted VR disparity map, computingglobal correlation coefficient and mean square error MSE to generate comfort oriented eigenvectors. For the immersive analysis of the virtual reality scene, the depth map fusion calculation is performed on the left and rightviewpoint data of the random frame, and the structural similarity map SC-SSIM in the multi-scale background is obtained, and the gradient map is obtained on the basis of the structure; the physical distortion and comfort are used to evaluate the quality of visual acceptance experience in virtual reality; the physical distortion and immersion are used to evaluate the perceptual experience qualityof visual information in virtual reality, and the final evaluation results are obtained.

Description

Technical field [0001] The invention belongs to the field of video multimedia processing and relates to an immersive virtual reality quality evaluation method. Background technique [0002] Virtual reality is an emerging technology. Through the playback of panoramic video, the experiencer can get a strong sense of immersion in it. However, many virtual reality applications have high requirements for data quality. In the process of data collection and transmission, distortion is an inevitable problem. Therefore, how to construct a high-quality virtual reality data scene will be a challenging subject. Based on this consideration, the evaluation method of virtual reality quality also needs to be established to establish new technical standards and promote the development of the virtual reality industry. [0003] Like traditional image and video quality evaluation, immersive virtual reality quality evaluation can also be divided into two types: subjective evaluation methods and obj...

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): H04N17/00H04N13/10
CPCH04N17/00
Inventor 姜斌杨嘉琛刘天麟
Owner TIANJIN 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