No-reference video quality measurement

Added value of machine learning

Decebal Constantin Mocanu, Jeevan Pokhrel, Juan Pablo Garella, Janne Seppänen, Eirini Liotou, Manish Narwaria

Research output: Contribution to journalArticleScientificpeer-review

15 Citations (Scopus)

Abstract

Video quality measurement is an important component in the end-to-end video delivery chain. Video quality is, however, subjective, and thus, there will always be interobserver differences in the subjective opinion about the visual quality of the same video. Despite this, most existing works on objective quality measurement typically focus only on predicting a single score and evaluate their prediction accuracies based on how close it is to the mean opinion scores (or similar average based ratings). Clearly, such an approach ignores the underlying diversities in the subjective scoring process and, as a result, does not allow further analysis on how reliable the objective prediction is in terms of subjective variability. Consequently, the aim of this paper is to analyze this issue and present a machine-learning based solution to address it. We demonstrate the utility of our ideas by considering the practical scenario of video broadcast transmissions with focus on digital terrestrial television (DTT) and proposing a no-reference objective video quality estimator for such application. We conducted meaningful verification studies on different video content (including video clips recorded from real DTT broadcast transmissions) in order to verify the performance of the proposed solution.
Original languageEnglish
Article number061208
JournalJournal of Electronic Imaging
Volume24
Issue number6
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

machine learning
Learning systems
Television transmission
Television
clips
scoring
ratings
predictions
estimators
delivery

Keywords

  • deep learning
  • no-reference video quality assessment
  • objective studies
  • quality of experience
  • subjective studies

Cite this

Mocanu, D. C., Pokhrel, J., Garella, J. P., Seppänen, J., Liotou, E., & Narwaria, M. (2015). No-reference video quality measurement: Added value of machine learning. Journal of Electronic Imaging, 24(6), [061208]. https://doi.org/10.1117/1.JEI.24.6.061208
Mocanu, Decebal Constantin ; Pokhrel, Jeevan ; Garella, Juan Pablo ; Seppänen, Janne ; Liotou, Eirini ; Narwaria, Manish. / No-reference video quality measurement : Added value of machine learning. In: Journal of Electronic Imaging. 2015 ; Vol. 24, No. 6.
@article{4f758bb1092b4c54bce23e98e63221d7,
title = "No-reference video quality measurement: Added value of machine learning",
abstract = "Video quality measurement is an important component in the end-to-end video delivery chain. Video quality is, however, subjective, and thus, there will always be interobserver differences in the subjective opinion about the visual quality of the same video. Despite this, most existing works on objective quality measurement typically focus only on predicting a single score and evaluate their prediction accuracies based on how close it is to the mean opinion scores (or similar average based ratings). Clearly, such an approach ignores the underlying diversities in the subjective scoring process and, as a result, does not allow further analysis on how reliable the objective prediction is in terms of subjective variability. Consequently, the aim of this paper is to analyze this issue and present a machine-learning based solution to address it. We demonstrate the utility of our ideas by considering the practical scenario of video broadcast transmissions with focus on digital terrestrial television (DTT) and proposing a no-reference objective video quality estimator for such application. We conducted meaningful verification studies on different video content (including video clips recorded from real DTT broadcast transmissions) in order to verify the performance of the proposed solution.",
keywords = "deep learning, no-reference video quality assessment, objective studies, quality of experience, subjective studies",
author = "Mocanu, {Decebal Constantin} and Jeevan Pokhrel and Garella, {Juan Pablo} and Janne Sepp{\"a}nen and Eirini Liotou and Manish Narwaria",
year = "2015",
doi = "10.1117/1.JEI.24.6.061208",
language = "English",
volume = "24",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "International Society for Optics and Photonics SPIE",
number = "6",

}

Mocanu, DC, Pokhrel, J, Garella, JP, Seppänen, J, Liotou, E & Narwaria, M 2015, 'No-reference video quality measurement: Added value of machine learning', Journal of Electronic Imaging, vol. 24, no. 6, 061208. https://doi.org/10.1117/1.JEI.24.6.061208

No-reference video quality measurement : Added value of machine learning. / Mocanu, Decebal Constantin; Pokhrel, Jeevan; Garella, Juan Pablo; Seppänen, Janne; Liotou, Eirini; Narwaria, Manish.

In: Journal of Electronic Imaging, Vol. 24, No. 6, 061208, 2015.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - No-reference video quality measurement

T2 - Added value of machine learning

AU - Mocanu, Decebal Constantin

AU - Pokhrel, Jeevan

AU - Garella, Juan Pablo

AU - Seppänen, Janne

AU - Liotou, Eirini

AU - Narwaria, Manish

PY - 2015

Y1 - 2015

N2 - Video quality measurement is an important component in the end-to-end video delivery chain. Video quality is, however, subjective, and thus, there will always be interobserver differences in the subjective opinion about the visual quality of the same video. Despite this, most existing works on objective quality measurement typically focus only on predicting a single score and evaluate their prediction accuracies based on how close it is to the mean opinion scores (or similar average based ratings). Clearly, such an approach ignores the underlying diversities in the subjective scoring process and, as a result, does not allow further analysis on how reliable the objective prediction is in terms of subjective variability. Consequently, the aim of this paper is to analyze this issue and present a machine-learning based solution to address it. We demonstrate the utility of our ideas by considering the practical scenario of video broadcast transmissions with focus on digital terrestrial television (DTT) and proposing a no-reference objective video quality estimator for such application. We conducted meaningful verification studies on different video content (including video clips recorded from real DTT broadcast transmissions) in order to verify the performance of the proposed solution.

AB - Video quality measurement is an important component in the end-to-end video delivery chain. Video quality is, however, subjective, and thus, there will always be interobserver differences in the subjective opinion about the visual quality of the same video. Despite this, most existing works on objective quality measurement typically focus only on predicting a single score and evaluate their prediction accuracies based on how close it is to the mean opinion scores (or similar average based ratings). Clearly, such an approach ignores the underlying diversities in the subjective scoring process and, as a result, does not allow further analysis on how reliable the objective prediction is in terms of subjective variability. Consequently, the aim of this paper is to analyze this issue and present a machine-learning based solution to address it. We demonstrate the utility of our ideas by considering the practical scenario of video broadcast transmissions with focus on digital terrestrial television (DTT) and proposing a no-reference objective video quality estimator for such application. We conducted meaningful verification studies on different video content (including video clips recorded from real DTT broadcast transmissions) in order to verify the performance of the proposed solution.

KW - deep learning

KW - no-reference video quality assessment

KW - objective studies

KW - quality of experience

KW - subjective studies

U2 - 10.1117/1.JEI.24.6.061208

DO - 10.1117/1.JEI.24.6.061208

M3 - Article

VL - 24

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 6

M1 - 061208

ER -