Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams

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

doi:10.1117/12.876471

Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams

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

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

Abstract

Human vision system is very complex and has been studied for many years specifically for purposes of efficient encoding of visual, e.g. video content from digital TV. There have been physiological and psychological evidences which indicate that viewers do not pay equal attention to all exposed visual information, but only focus on certain areas known as focus of attention (FOA) or saliency regions. In this work, we propose a novel based objective quality assessment metric, for assessing the perceptual quality of decoded video sequences affected by transmission errors and packed loses. The proposed method weights the Mean Square Error (MSE), Weighted-MSE (WMSE), according to the calculated saliency map at each pixel. Our method was validated trough subjective quality experiments.

Original language	American English
Title of host publication	Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance VIII
DOIs	https://doi.org/10.1117/12.876471
State	Published - 25 Feb 2011
Event	Image Quality and System Performance VIII - San Francisco, CA, United States Duration: 24 Jan 2011 → 26 Jan 2011

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7867

Conference

Conference	Image Quality and System Performance VIII
Country/Territory	United States
City	San Francisco, CA
Period	24/01/11 → 26/01/11

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

10.1117/12.876471

Cite this

Boujut, H., Benois-Pineau, J., Hadar, O., Ahmed, T., & Bonnet, P. (2011). Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams. In Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance VIII Article 78670X (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7867). https://doi.org/10.1117/12.876471

@inproceedings{3a0b3fd0b6a048b6af157fb2c2146cbd,

title = "Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams",

abstract = "Human vision system is very complex and has been studied for many years specifically for purposes of efficient encoding of visual, e.g. video content from digital TV. There have been physiological and psychological evidences which indicate that viewers do not pay equal attention to all exposed visual information, but only focus on certain areas known as focus of attention (FOA) or saliency regions. In this work, we propose a novel based objective quality assessment metric, for assessing the perceptual quality of decoded video sequences affected by transmission errors and packed loses. The proposed method weights the Mean Square Error (MSE), Weighted-MSE (WMSE), according to the calculated saliency map at each pixel. Our method was validated trough subjective quality experiments.",

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

year = "2011",

month = feb,

day = "25",

doi = "10.1117/12.876471",

language = "American English",

isbn = "9780819484048",

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

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

note = "Image Quality and System Performance VIII ; Conference date: 24-01-2011 Through 26-01-2011",

}

Boujut, H, Benois-Pineau, J, Hadar, O, Ahmed, T & Bonnet, P 2011, Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams. in Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance VIII., 78670X, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7867, Image Quality and System Performance VIII, San Francisco, CA, United States, 24/01/11. https://doi.org/10.1117/12.876471

Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams. / Boujut, H.; Benois-Pineau, J.; Hadar, O. et al.
Proceedings of SPIE-IS and T Electronic Imaging - Image Quality and System Performance VIII. 2011. 78670X (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7867).

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

TY - GEN

T1 - Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams

AU - Boujut, H.

AU - Benois-Pineau, J.

AU - Hadar, O.

AU - Ahmed, T.

AU - Bonnet, P.

PY - 2011/2/25

Y1 - 2011/2/25

N2 - Human vision system is very complex and has been studied for many years specifically for purposes of efficient encoding of visual, e.g. video content from digital TV. There have been physiological and psychological evidences which indicate that viewers do not pay equal attention to all exposed visual information, but only focus on certain areas known as focus of attention (FOA) or saliency regions. In this work, we propose a novel based objective quality assessment metric, for assessing the perceptual quality of decoded video sequences affected by transmission errors and packed loses. The proposed method weights the Mean Square Error (MSE), Weighted-MSE (WMSE), according to the calculated saliency map at each pixel. Our method was validated trough subjective quality experiments.

AB - Human vision system is very complex and has been studied for many years specifically for purposes of efficient encoding of visual, e.g. video content from digital TV. There have been physiological and psychological evidences which indicate that viewers do not pay equal attention to all exposed visual information, but only focus on certain areas known as focus of attention (FOA) or saliency regions. In this work, we propose a novel based objective quality assessment metric, for assessing the perceptual quality of decoded video sequences affected by transmission errors and packed loses. The proposed method weights the Mean Square Error (MSE), Weighted-MSE (WMSE), according to the calculated saliency map at each pixel. Our method was validated trough subjective quality experiments.

UR - http://www.scopus.com/inward/record.url?scp=79951825688&partnerID=8YFLogxK

U2 - 10.1117/12.876471

DO - 10.1117/12.876471

M3 - Conference contribution

SN - 9780819484048

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

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

T2 - Image Quality and System Performance VIII

Y2 - 24 January 2011 through 26 January 2011

ER -

Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this