Video quality diagnosis method based on deep learning

A technology of deep learning and video quality, applied in the field of video analysis, to achieve the effect of ensuring normal operation, improving generalization ability, and reducing labor pressure

Inactive Publication Date: 2020-07-03
KUNMING UNIV OF SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for diagnosing video quality based on deep learning, which is used to realize the problem of diagnosing video quality by means of deep learning

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 quality diagnosis method based on deep learning
  • Video quality diagnosis method based on deep learning
  • Video quality diagnosis method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Embodiment 1: as Figure 1-4 Shown, a kind of video quality diagnosis method based on deep learning, described method steps are as follows:

[0019] Step 1: Collect comprehensive abnormal video quality data, then preprocess the abnormal video quality data, label the preprocessed images with abnormal types, and then give quality scores to each preprocessed image that has been tagged. For each pre-processed image, the average value of the quality scores of multiple people is taken as the quality score of the corresponding pre-processed image; the pre-processed image with the quality score and the images in the TID2013 database are used to form video quality diagnosis deep learning data Set, video quality diagnosis deep learning data set is divided into three parts: training set, verification set, test set; data sets are stored in TFRecord files, and then read samples from TFRecord files for analysis; among them, comprehensive video quality abnormalities The data includes...

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 quality diagnosis method based on deep learning, and belongs to the technical field of video analysis. According to the invention, the method includes: analyzing a monitoring video image fault; establishing a corresponding relationship between a front-end acquisition fault and video image quality; a comprehensive video quality data set is collected and made; a monitoring video fault image data set conforming to a deep learning model is sorted out; more features of the abnormal video can be extracted by selecting a specific deep learning model; compared with theprior art, the method is suitable for more complex rules, is more suitable for being combined with practical application, improves the generalization ability of the video diagnosis system in differentscenes, facilitates the timely and effective understanding of the condition of a to-be-diagnosed video, guarantees the normal operation of the video system, and reduces the labor pressure of a personto a certain degree.

Description

technical field [0001] The invention relates to a video quality diagnosis method based on deep learning, and belongs to the technical field of video analysis. Background technique [0002] It is no longer realistic to rely on manual detection and processing for the operation of surveillance video systems. How to quickly and automatically detect and locate problems in the surveillance system has prompted the development of video quality diagnosis technology. Monitoring manufacturers and research institutions have launched a variety of video quality diagnosis systems, which clearly show the problems of faulty equipment to users, which is convenient for users to quickly and accurately fix equipment, ensure the long-term normal operation of the video monitoring system, and reduce the maintenance of monitoring equipment. quantity. [0003] Traditional video quality diagnosis: based on image statistics (peak value and variance); by comparing the relationship between the value of ...

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): G06T7/00H04N17/00G06N3/04G06N3/08
CPCG06T7/0002H04N17/00G06N3/08G06T2207/10016G06T2207/20081G06N3/045
Inventor 赵志鹏李玉惠
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap