Publication detail

Estimating H.264/AVC Video PSNR Without Reference Using the Artificial Neural Network Approach

SLANINA, M. ŘÍČNÝ, V.

Original Title

Estimating H.264/AVC Video PSNR Without Reference Using the Artificial Neural Network Approach

English Title

Estimating H.264/AVC Video PSNR Without Reference Using the Artificial Neural Network Approach

Type

conference paper

Language

en

Original Abstract

This paper presents a method capable of estimating peak signal-to-noise ratios (PSNR) of digital video sequences compressed using the H.264/AVC algorithm. The idea is in replacing a full reference metric - the PSNR (for whose evaluation we need the original as well as the processed video data) - with a no reference metric, operating on the encoded bit stream only. As we are working just with the encoded bit stream, we can spare a significant amount of computations needed to decode the video pixel values. In this paper, we describe the network inputs and network configurations, suitable to estimate PSNR in intra and inter predicted pictures. Finally, we make a simple evaluation of the proposed algorithm, having the correlation coefficient of the real and estimated PSNRs as the measure of optimality.

English abstract

This paper presents a method capable of estimating peak signal-to-noise ratios (PSNR) of digital video sequences compressed using the H.264/AVC algorithm. The idea is in replacing a full reference metric - the PSNR (for whose evaluation we need the original as well as the processed video data) - with a no reference metric, operating on the encoded bit stream only. As we are working just with the encoded bit stream, we can spare a significant amount of computations needed to decode the video pixel values. In this paper, we describe the network inputs and network configurations, suitable to estimate PSNR in intra and inter predicted pictures. Finally, we make a simple evaluation of the proposed algorithm, having the correlation coefficient of the real and estimated PSNRs as the measure of optimality.

Keywords

H.264/AVC, video quality, no reference assessment, PSNR, artificial neural network.

RIV year

2008

Released

26.07.2008

Publisher

INSTICC

Location

Porto

ISBN

978-989-8111-60-9

Book

Sigmap 2008 International Conference on Signal Processing and Multimedia Applications Proceedings

Pages from

244

Pages to

250

Pages count

7

BibTex


@inproceedings{BUT26704,
  author="Martin {Slanina} and Václav {Říčný}",
  title="Estimating H.264/AVC Video PSNR Without Reference Using the Artificial Neural Network Approach",
  annote="This paper presents a method capable of estimating peak signal-to-noise ratios (PSNR) of digital video sequences compressed using the H.264/AVC algorithm. The idea is in replacing a full reference metric - the PSNR (for whose evaluation we need the original as well as the processed video data) - with a no reference metric, operating on the encoded bit stream only. As we are working just with the encoded bit stream, we can spare a significant amount of computations needed to decode the video pixel values. In this paper, we describe the network inputs and network configurations, suitable to estimate PSNR in intra and inter predicted pictures. Finally, we make a simple evaluation of the proposed algorithm, having the correlation coefficient of the real and estimated PSNRs as the measure of optimality.",
  address="INSTICC",
  booktitle="Sigmap 2008 International Conference on Signal Processing and Multimedia Applications Proceedings",
  chapter="26704",
  howpublished="print",
  institution="INSTICC",
  year="2008",
  month="july",
  pages="244--250",
  publisher="INSTICC",
  type="conference paper"
}