Empirical evaluation of no-reference VQA methods on a natural video quality database

Men, Hui; Lin, Hanhe; Saupe, Dietmar

Empirical evaluation of no-reference VQA methods on a natural video quality database

Files

Men_2-6ozepo9wxupa0.pdf(95.84 KB)

Date

2017

Publication type

Contribution to a conference collection

Publication status

Published

Published in

2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), May 29 - June 2, 2017, Erfurt, Germany, Proceedings. - Piscataway, NJ : IEEE, 2017. - 17011019. - eISSN 2472-7814. - ISBN 978-1-5386-4024-1

Abstract

No-Reference (NR) Video Quality Assessment (VQA) is a challenging task since it predicts the visual quality of a video sequence without comparison to some original reference video. Several NR-VQA methods have been proposed. However, all of them were designed and tested on databases with artificially distorted videos. Therefore, it remained an open question how well these NR-VQA methods perform for natural videos. We evaluated two popular VQA methods on our newly built natural VQA database KoNViD-1k. In addition, we found that merely combining five simple VQA-related features, i.e., contrast, colorfulness, blurriness, spatial information, and temporal information, already gave a performance about as well as those of the established NR-VQA methods. However, for all methods we found that they are unsatisfying when assessing natural videos (correlation coefficients below 0.6). These findings show that NR-VQA is not yet matured and in need of further substantial improvement.

Subject (DDC)

004 Computer Science

Keywords

empirical evaluation, no-reference, video quality assessment, feature combination

Conference

2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), May 31, 2017 - Jun 2, 2017, Erfurt, Germany

Cite This

ISO 690

MEN, Hui, Hanhe LIN, Dietmar SAUPE, 2017. Empirical evaluation of no-reference VQA methods on a natural video quality database. 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX). Erfurt, Germany, May 31, 2017 - Jun 2, 2017. In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), May 29 - June 2, 2017, Erfurt, Germany, Proceedings. Piscataway, NJ:IEEE, 17011019. eISSN 2472-7814. ISBN 978-1-5386-4024-1. Available under: doi: 10.1109/QoMEX.2017.7965644

BibTex

@inproceedings{Men2017-05Empir-41343,
  year={2017},
  doi={10.1109/QoMEX.2017.7965644},
  title={Empirical evaluation of no-reference VQA methods on a natural video quality database},
  isbn={978-1-5386-4024-1},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), May 29 - June 2, 2017, Erfurt, Germany, Proceedings},
  author={Men, Hui and Lin, Hanhe and Saupe, Dietmar},
  note={Article Number: 17011019}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/41343">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-02-14T10:55:51Z</dc:date>
    <dc:contributor>Men, Hui</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41343/1/Men_2-6ozepo9wxupa0.pdf"/>
    <dc:creator>Men, Hui</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <dcterms:issued>2017-05</dcterms:issued>
    <dcterms:title>Empirical evaluation of no-reference VQA methods on a natural video quality database</dcterms:title>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/41343"/>
    <dcterms:abstract xml:lang="eng">No-Reference (NR) Video Quality Assessment (VQA) is a challenging task since it predicts the visual quality of a video sequence without comparison to some original reference video. Several NR-VQA methods have been proposed. However, all of them were designed and tested on databases with artificially distorted videos. Therefore, it remained an open question how well these NR-VQA methods perform for natural videos. We evaluated two popular VQA methods on our newly built natural VQA database KoNViD-1k. In addition, we found that merely combining five simple VQA-related features, i.e., contrast, colorfulness, blurriness, spatial information, and temporal information, already gave a performance about as well as those of the established NR-VQA methods. However, for all methods we found that they are unsatisfying when assessing natural videos (correlation coefficients below 0.6). These findings show that NR-VQA is not yet matured and in need of further substantial improvement.</dcterms:abstract>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41343/1/Men_2-6ozepo9wxupa0.pdf"/>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-02-14T10:55:51Z</dcterms:available>
    <dc:rights>terms-of-use</dc:rights>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes