No-Reference video quality assessment of H.264 video streams based on semantic saliency maps

H. Boujut; J. Benois-Pineau; T. Ahmed; O. Hadar; P. Bonnet

doi:https://doi.org/10.1117/12.905379

No-Reference video quality assessment of H.264 video streams based on semantic saliency maps

H. Boujut, J. Benois-Pineau, T. Ahmed, O. Hadar, P. Bonnet

Department of Communication Systems Engineering

Ben-Gurion University of the Negev

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	English
Title of host publication	Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX
DOIs	https://doi.org/10.1117/12.905379
State	Published - 13 Feb 2012
Event	Image Quality and System Performance IX - Burlingame, CA, United States Duration: 24 Jan 2012 → 26 Jan 2012

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	8293

Conference

Conference	Image Quality and System Performance IX
Country/Territory	United States
City	Burlingame, CA
Period	24/01/12 → 26/01/12

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

https://doi.org/10.1117/12.905379

Cite this

Boujut, H., Benois-Pineau, J., Ahmed, T., Hadar, O., & Bonnet, P. (2012). No-Reference video quality assessment of H.264 video streams based on semantic saliency maps. In Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX Article 82930T (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8293). https://doi.org/10.1117/12.905379

@inproceedings{ec0ac902005549c280cf7f3a2f9703cf,

title = "No-Reference video quality assessment of H.264 video streams based on semantic saliency maps",

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.",

author = "H. Boujut and J. Benois-Pineau and T. Ahmed and O. Hadar and P. Bonnet",

year = "2012",

month = feb,

day = "13",

doi = "https://doi.org/10.1117/12.905379",

language = "English",

isbn = "9780819489401",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX",

note = "Image Quality and System Performance IX ; Conference date: 24-01-2012 Through 26-01-2012",

}

Boujut, H, Benois-Pineau, J, Ahmed, T, Hadar, O & Bonnet, P 2012, No-Reference video quality assessment of H.264 video streams based on semantic saliency maps. in Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX., 82930T, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8293, Image Quality and System Performance IX, Burlingame, CA, United States, 24/01/12. https://doi.org/10.1117/12.905379

No-Reference video quality assessment of H.264 video streams based on semantic saliency maps. / Boujut, H.; Benois-Pineau, J.; Ahmed, T. et al.
Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX. 2012. 82930T (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8293).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - No-Reference video quality assessment of H.264 video streams based on semantic saliency maps

AU - Boujut, H.

AU - Benois-Pineau, J.

AU - Ahmed, T.

AU - Hadar, O.

AU - Bonnet, P.

PY - 2012/2/13

Y1 - 2012/2/13

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84856702435&partnerID=8YFLogxK

U2 - https://doi.org/10.1117/12.905379

DO - https://doi.org/10.1117/12.905379

M3 - Conference contribution

SN - 9780819489401

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX

T2 - Image Quality and System Performance IX

Y2 - 24 January 2012 through 26 January 2012

ER -

Boujut H, Benois-Pineau J, Ahmed T, Hadar O, Bonnet P. No-Reference video quality assessment of H.264 video streams based on semantic saliency maps. In Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance IX. 2012. 82930T. (Proceedings of SPIE - The International Society for Optical Engineering). doi: https://doi.org/10.1117/12.905379

No-Reference video quality assessment of H.264 video streams based on semantic saliency maps

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this