Building a reduced reference video quality metric with very low overhead using multivariate data analysis

Tobias Oelbaum, Klaus Diepold

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In this contribution a reduced reference video quality metric for AVC/H.264 is proposed that needs only a very low overhead (not more than two bytes per sequence). This reduced reference metric uses well established algorithms to measure objective features of the video such as 'blur' or 'blocking'. Those measurements are then combined into a single measurement for the overall video quality. The weights of the single features and the combination of those are determined using methods provided by multivariate data analysis. The proposed metric is verified using a data set of AVC/H.264 encoded videos and the corresponding results of a carefully designed and conducted subjective evaluation. Results show that the proposed reduced reference metric not only outperforms standard PSNR but also two well known full reference metrics.

Original languageEnglish
Title of host publicationCITSA 2007 - Int. Conference on Cybernetics and Information Technologies, Systems and Applications and CCCT 2007 - Int. Conference on Computing, Communications and Control Technologies, Proceedings
Pages94-99
Number of pages6
StatePublished - 2007
Event4th International Conference on Cybernetics and Information Technologies, Systems and Applications, CITSA 2007, Jointly with the 5th International Conference on Computing, Communications and Control Technologies, CCCT 2007 - Orlando, FL, United States
Duration: 12 Jul 200715 Jul 2007

Publication series

NameCITSA 2007 - Int. Conference on Cybernetics and Information Technologies, Systems and Applications and CCCT 2007 - Int. Conference on Computing, Communications and Control Technologies, Proceedings
Volume1

Conference

Conference4th International Conference on Cybernetics and Information Technologies, Systems and Applications, CITSA 2007, Jointly with the 5th International Conference on Computing, Communications and Control Technologies, CCCT 2007
Country/TerritoryUnited States
CityOrlando, FL
Period12/07/0715/07/07

Keywords

  • AVC/H.264
  • Multivariate data analysis
  • Reduced reference
  • Video quality metric

Fingerprint

Dive into the research topics of 'Building a reduced reference video quality metric with very low overhead using multivariate data analysis'. Together they form a unique fingerprint.

Cite this