A method for quality assessment of multi-camera video

A quality assessment and multi-camera technology, applied in television, image communication, electrical components, etc., can solve the problems of high cost and low scoring efficiency, and achieve the effects of saving cost and time, improving scoring accuracy, and enhancing optimization capabilities

Active Publication Date: 2022-02-01
南京理工大学紫金学院
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the subjective quality evaluation of the video requires a lot of manpower, and in order to ensure that the uncertainty due to human factors has as little impact on the final video score as possible, it is necessary to formulate detailed and unified standards, and the scoring efficiency is relatively low and the cost is high.

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 method for quality assessment of multi-camera video
  • A method for quality assessment of multi-camera video
  • A method for quality assessment of multi-camera video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] refer to figure 1 , which is the first embodiment of the present invention, this embodiment provides a method for evaluating the quality of video captured by multiple cameras, including:

[0046] S1: Collect the shooting data of four adjustable cameras through the virtual simulation module of short track speed skating, and make a data set.

[0047] It should be noted that the short track speed skating virtual simulation module is an intelligent short track speed skating broadcast platform for the Winter Olympics. The virtual simulation teaching experiment project aimed at helping students master the broadcasting skills of short track speed skating events in the Winter Olympics, through the virtual simulation of short track speed skating intelligent broadcasting, enables students to master the use of short track speed skating intelligent Basic steps and skills; this project has been shared on the experimental teaching public service platform, and can be widely used in t...

Embodiment 2

[0104] In order to verify and explain the technical effects adopted in this method, this embodiment selects the traditional BP neural network, the traditional video quality scoring method and this method for comparative testing, and compares the test results by means of scientific demonstration to verify the results of this method. have real effects.

[0105] The accuracy of the traditional BP neural network is not high, and the training takes a long time; the traditional video quality scoring method needs to rely on a lot of manpower, and in order to ensure that the final video score is affected by the uncertainty due to human factors as little as possible, it is necessary to To formulate detailed and unified standards, the scoring efficiency is relatively low and the cost is high.

[0106] In order to verify that this method has higher scoring accuracy and efficiency relative to the traditional BP neural network and the traditional video quality scoring method, in this embod...

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 method for evaluating the quality of video shot by multiple cameras, comprising: collecting shooting data of four adjustable cameras through a short-track speed skating virtual simulation module, and making a data set; and constructing a video shooting quality scoring network based on the data set ; calculate the error of the output layer of the video shooting quality scoring network, and train the video shooting quality scoring network in combination with the error and the bat optimization strategy. The video is input into the trained video shooting quality scoring network for video quality scoring; the present invention enhances the optimization ability by optimizing the bat algorithm, and uses it as an optimizer to optimize the video shooting quality scoring network to improve the video shooting quality The scoring accuracy rate of the scoring network saves the cost and time of manual evaluation of video shooting.

Description

technical field [0001] The invention relates to the technical field of video quality assessment, in particular to a method for evaluating the quality of videos captured by multiple cameras. Background technique [0002] Video quality evaluation includes video fidelity and intelligibility. Fidelity refers to the degree of deviation between the evaluated image and the standard image, and intelligibility refers to the ability of the image to provide information to humans or computers. There are two types of evaluation methods: subjective evaluation method and objective evaluation method. The former judges the image quality by normalizing the observer's rating, and the latter judges the image quality by normalizing the difference between the observer's evaluation score of the undistorted image and the distorted image. [0003] At present, most of the work on video quality assessment is based on factors such as video distortion rate and frame loss rate, and few evaluate from the...

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): H04N17/00
CPCH04N17/004
Inventor 朱惠娟卢锋张皓名李庆明丛玉华黄萍唐美燕
Owner 南京理工大学紫金学院
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