Supercharge Your Innovation With Domain-Expert AI Agents!

Blind video quality assessment prediction method and system based on comparison self-supervision

A technology of video quality and prediction method, applied in the field of video processing and computer vision, can solve the problems of improving and limiting the prediction performance of the model, and achieve the effect of improving performance

Pending Publication Date: 2022-01-14
CHINA UNIV OF MINING & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To sum up, the problem existing in the existing technology is: in the current video quality assessment method without reference, due to the capacity problem of the database, only some initialization models that are not aimed at the quality assessment task can be used, which limits the further improvement of the model prediction performance

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
  • Blind video quality assessment prediction method and system based on comparison self-supervision
  • Blind video quality assessment prediction method and system based on comparison self-supervision
  • Blind video quality assessment prediction method and system based on comparison self-supervision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0061] A kind of non-reference video quality assessment prediction method based on contrastive self-supervision described in the present invention, refer to figure 1 , including the following steps:

[0062] The first step is to select high-quality video data containing different scenes and different content as sample materials, as follows:

[0063] (1) Collect public video databases and select high-quality video samples as materials;

[0064] (2) roughly divide the collected videos into different categories according to the content, such as people, sports, scenery, architecture, etc.;

[0065] (3) For each category, a c...

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 blind video quality assessment prediction method and system based on comparison self-supervision. According to the invention, videos of different distortion types are constructed by using non-labeled high-quality video data, and training of a model is performed based on taking video samples as positive and negative samples in comparison loss, so that the network model can be effectively enabled to obtain the capability of capturing distortion; and a trained network is used as a pre-trained network to be used in an existing blind quality model, so that the performance better than that of a pre-trained model used by a current mainstream video quality assessment method can be obtained, and a more accurate video quality assessment prediction result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of video processing and computer vision, and in particular relates to a comparison and self-supervision-based non-reference video quality evaluation and prediction method and system. Background technique [0002] To obtain estimates that are highly consistent with human visual perception, video quality assessment (VQA) metrics become an urgent problem to be solved. Subjective VQA methods based on manual ranking are the most reliable methods, but their practical application is limited by time and labor. As another option, the researchers sought objective ways to automatically predict the visual quality of distorted videos. [0003] Based on the availability of reference information in videos, objective VQA methods can be further classified into full-reference (FR), semi-reference (RR), and no-reference (NR) VQA metrics. All or part of the information of the reference video is available in the FR / RR-VQA metr...

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
IPC IPC(8): G06V20/40G06V10/82G06N3/04G06N3/08G06T7/00
CPCG06T7/00G06N3/08G06T2207/20081G06T2207/30168G06T2207/10016G06N3/045
Inventor 刘卫东陈鹏飞李雷达
Owner CHINA UNIV OF MINING & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com