Authors:
Martin Slanina
and
Václav Říčný
Affiliation:
Brno University of Technology, Czech Republic
Keyword(s):
H.264/AVC, video quality, no reference assessment, PSNR, artificial neural network.
Related
Ontology
Subjects/Areas/Topics:
Audio and Video Quality Assessment
;
Mpeg/H.26X Standards and Related Issues
;
Multimedia
;
Multimedia and Communications
;
Multimedia Systems and Applications
;
Telecommunications
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.