Share Email Print
cover

Proceedings Paper

No-reference video quality assessment of H.264 video streams based on semantic saliency maps
Author(s): H. Boujut; J. Benois-Pineau; T. Ahmed; O. Hadar; P. Bonnet
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The paper contributes to No-Reference video quality assessment of broadcasted HD video over IP networks and DVB. In this work we have enhanced our bottom-up spatio-temporal saliency map model by considering semantics of the visual scene. Thus we propose a new saliency map model based on face detection that we called semantic saliency map. A new fusion method has been proposed to merge the bottom-up saliency maps with the semantic saliency map. We show that our NR metric WMBER weighted by the spatio-temporal-semantic saliency map provides higher results then the WMBER weighted by the bottom-up spatio-temporal saliency map. Tests are performed on two H.264/AVC video databases for video quality assessment over lossy networks.

Paper Details

Date Published: 25 January 2012
PDF: 9 pages
Proc. SPIE 8293, Image Quality and System Performance IX, 82930T (25 January 2012); doi: 10.1117/12.905379
Show Author Affiliations
H. Boujut, Lab. Bordelais de Recherche en Informatique, CNRS, Univ. Bordeaux (France)
J. Benois-Pineau, Lab. Bordelais de Recherche en Informatique, CNRS, Univ. Bordeaux (France)
T. Ahmed, Lab. Bordelais de Recherche en Informatique, CNRS, Univ. Bordeaux (France)
O. Hadar, Ben Gurion Univ. of the Negev (Israel)
P. Bonnet, Audemat Worldcast Systems (France)


Published in SPIE Proceedings Vol. 8293:
Image Quality and System Performance IX
Frans Gaykema; Peter D. Burns, Editor(s)

© SPIE. Terms of Use
Back to Top