Objective No-Reference Video Quality Assessment Method Based on Spatio-Temporal Pixel Analysis

Wyllian B. da SILVA; Keiko V. O. FONSECA; Alexandre de A. P. POHL

doi:10.1587/transinf.2014EDP7155

Objective No-Reference Video Quality Assessment Method Based on Spatio-Temporal Pixel Analysis

Wyllian B. da SILVA, Keiko V. O. FONSECA, Alexandre de A. P. POHL

Full Text Views

0

Share
Cite this

Summary :

Digital video signals are subject to several distortions due to compression processes, transmission over noisy channels or video processing. Therefore, the video quality evaluation has become a necessity for broadcasters and content providers interested in offering a high video quality to the customers. Thus, an objective no-reference video quality assessment metric is proposed based on the sigmoid model using spatial-temporal features weighted by parameters obtained through the solution of a nonlinear least squares problem using the Levenberg-Marquardt algorithm. Experimental results show that when it is applied to MPEG-2 streams our method presents better linearity than full-reference metrics, and its performance is close to that achieved with full-reference metrics for H.264 streams.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.7 pp.1325-1332

Publication Date: 2015/07/01

Publicized: 2015/04/03

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDP7155

Type of Manuscript: PAPER

Category: Image Processing and Video Processing

Authors

Wyllian B. da SILVA
  Federal University of Santa Catarina (UFSC)
Keiko V. O. FONSECA
  Federal University of Technology-Paraná (UTFPR)
Alexandre de A. P. POHL
  Federal University of Technology-Paraná (UTFPR)

Keyword

H.264, MPEG-2, no-reference metric, objective video quality assessment

Cite this

Copy

Wyllian B. da SILVA, Keiko V. O. FONSECA, Alexandre de A. P. POHL, "Objective No-Reference Video Quality Assessment Method Based on Spatio-Temporal Pixel Analysis" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 7, pp. 1325-1332, July 2015, doi: 10.1587/transinf.2014EDP7155.
Abstract: Digital video signals are subject to several distortions due to compression processes, transmission over noisy channels or video processing. Therefore, the video quality evaluation has become a necessity for broadcasters and content providers interested in offering a high video quality to the customers. Thus, an objective no-reference video quality assessment metric is proposed based on the sigmoid model using spatial-temporal features weighted by parameters obtained through the solution of a nonlinear least squares problem using the Levenberg-Marquardt algorithm. Experimental results show that when it is applied to MPEG-2 streams our method presents better linearity than full-reference metrics, and its performance is close to that achieved with full-reference metrics for H.264 streams.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7155/_p

Copy

@ARTICLE{e98-d_7_1325,
author={Wyllian B. da SILVA, Keiko V. O. FONSECA, Alexandre de A. P. POHL, },
journal={IEICE TRANSACTIONS on Information},
title={Objective No-Reference Video Quality Assessment Method Based on Spatio-Temporal Pixel Analysis},
year={2015},
volume={E98-D},
number={7},
pages={1325-1332},
abstract={Digital video signals are subject to several distortions due to compression processes, transmission over noisy channels or video processing. Therefore, the video quality evaluation has become a necessity for broadcasters and content providers interested in offering a high video quality to the customers. Thus, an objective no-reference video quality assessment metric is proposed based on the sigmoid model using spatial-temporal features weighted by parameters obtained through the solution of a nonlinear least squares problem using the Levenberg-Marquardt algorithm. Experimental results show that when it is applied to MPEG-2 streams our method presents better linearity than full-reference metrics, and its performance is close to that achieved with full-reference metrics for H.264 streams.},
keywords={},
doi={10.1587/transinf.2014EDP7155},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Objective No-Reference Video Quality Assessment Method Based on Spatio-Temporal Pixel Analysis
T2 - IEICE TRANSACTIONS on Information
SP - 1325
EP - 1332
AU - Wyllian B. da SILVA
AU - Keiko V. O. FONSECA
AU - Alexandre de A. P. POHL
PY - 2015
DO - 10.1587/transinf.2014EDP7155
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2015
AB - Digital video signals are subject to several distortions due to compression processes, transmission over noisy channels or video processing. Therefore, the video quality evaluation has become a necessity for broadcasters and content providers interested in offering a high video quality to the customers. Thus, an objective no-reference video quality assessment metric is proposed based on the sigmoid model using spatial-temporal features weighted by parameters obtained through the solution of a nonlinear least squares problem using the Levenberg-Marquardt algorithm. Experimental results show that when it is applied to MPEG-2 streams our method presents better linearity than full-reference metrics, and its performance is close to that achieved with full-reference metrics for H.264 streams.
ER -