A reduced-reference parametric model for audiovisual quality of IPTV services

Toni Mäki; D. Kukolj; D. Dordevic; Martin Varela

doi:10.1109/QoMEX.2013.6603193

A reduced-reference parametric model for audiovisual quality of IPTV services

Toni Mäki, D. Kukolj, D. Dordevic, Martin Varela

VTT Technical Research Centre of Finland

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

14 Citations (Scopus)

Abstract

In this paper we present a parametric model for audiovisual quality estimation in IPTV and similar services. The proposed model takes advantage of signal characteristics calculated at the sender (in particular related to levels of motion in the content), but is purely parametric on the estimation (i.e. it does not require peeking into the bitstream), which makes it suitable for large-scale real-time monitoring applications. In order to obtain the model, we followed the Pseudo-Subjective Quality Assessment (PSQA) methodology, and compared different kinds of statistical estimators, namely Multilayer Perceptrons (MLP) and Random Neural Networks (RNN).

Original language	English
Title of host publication	Proceedings
Subtitle of host publication	Fifth International Workshop on Quality of Multimedia Experience, QoMEX 2013
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	6-11
ISBN (Electronic)	978-1-4799-0738-0
DOIs	https://doi.org/10.1109/QoMEX.2013.6603193
Publication status	Published - 2013
MoE publication type	Not Eligible
Event	5th International Workshop on Quality of Multimedia Experience, QoMEX 2013 - Klagenfurt am Wörthersee, Austria Duration: 5 Jul 2013 → 7 Jul 2013 Conference number: 5

Conference

Conference	5th International Workshop on Quality of Multimedia Experience, QoMEX 2013
Abbreviated title	QoMEX 2013
Country	Austria
City	Klagenfurt am Wörthersee
Period	5/07/13 → 7/07/13

Keywords

audiovisual quality assessment
feature clustering
neural network
video quality assessment

Access to Document

10.1109/QoMEX.2013.6603193

Fingerprint Dive into the research topics of 'A reduced-reference parametric model for audiovisual quality of IPTV services'. Together they form a unique fingerprint.

Cite this

Mäki, T., Kukolj, D., Dordevic, D., & Varela, M. (2013). A reduced-reference parametric model for audiovisual quality of IPTV services. In Proceedings: Fifth International Workshop on Quality of Multimedia Experience, QoMEX 2013 (pp. 6-11). IEEE Institute of Electrical and Electronic Engineers. https://doi.org/10.1109/QoMEX.2013.6603193

@inproceedings{a79cb17f771b47fcb9ae242b03ae8f80,

title = "A reduced-reference parametric model for audiovisual quality of IPTV services",

abstract = "In this paper we present a parametric model for audiovisual quality estimation in IPTV and similar services. The proposed model takes advantage of signal characteristics calculated at the sender (in particular related to levels of motion in the content), but is purely parametric on the estimation (i.e. it does not require peeking into the bitstream), which makes it suitable for large-scale real-time monitoring applications. In order to obtain the model, we followed the Pseudo-Subjective Quality Assessment (PSQA) methodology, and compared different kinds of statistical estimators, namely Multilayer Perceptrons (MLP) and Random Neural Networks (RNN).",

keywords = "audiovisual quality assessment, feature clustering, neural network, video quality assessment",

author = "Toni M{\"a}ki and D. Kukolj and D. Dordevic and Martin Varela",

year = "2013",

doi = "10.1109/QoMEX.2013.6603193",

language = "English",

pages = "6--11",

booktitle = "Proceedings",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

note = "5th International Workshop on Quality of Multimedia Experience, QoMEX 2013, QoMEX 2013 ; Conference date: 05-07-2013 Through 07-07-2013",

}

Mäki, T, Kukolj, D, Dordevic, D & Varela, M 2013, A reduced-reference parametric model for audiovisual quality of IPTV services. in Proceedings: Fifth International Workshop on Quality of Multimedia Experience, QoMEX 2013. IEEE Institute of Electrical and Electronic Engineers, pp. 6-11, 5th International Workshop on Quality of Multimedia Experience, QoMEX 2013, Klagenfurt am Wörthersee, Austria, 5/07/13. https://doi.org/10.1109/QoMEX.2013.6603193

A reduced-reference parametric model for audiovisual quality of IPTV services. / Mäki, Toni; Kukolj, D.; Dordevic, D.; Varela, Martin.

Proceedings: Fifth International Workshop on Quality of Multimedia Experience, QoMEX 2013. IEEE Institute of Electrical and Electronic Engineers, 2013. p. 6-11.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - A reduced-reference parametric model for audiovisual quality of IPTV services

AU - Mäki, Toni

AU - Kukolj, D.

AU - Dordevic, D.

AU - Varela, Martin

N1 - Conference code: 5

PY - 2013

Y1 - 2013

N2 - In this paper we present a parametric model for audiovisual quality estimation in IPTV and similar services. The proposed model takes advantage of signal characteristics calculated at the sender (in particular related to levels of motion in the content), but is purely parametric on the estimation (i.e. it does not require peeking into the bitstream), which makes it suitable for large-scale real-time monitoring applications. In order to obtain the model, we followed the Pseudo-Subjective Quality Assessment (PSQA) methodology, and compared different kinds of statistical estimators, namely Multilayer Perceptrons (MLP) and Random Neural Networks (RNN).

AB - In this paper we present a parametric model for audiovisual quality estimation in IPTV and similar services. The proposed model takes advantage of signal characteristics calculated at the sender (in particular related to levels of motion in the content), but is purely parametric on the estimation (i.e. it does not require peeking into the bitstream), which makes it suitable for large-scale real-time monitoring applications. In order to obtain the model, we followed the Pseudo-Subjective Quality Assessment (PSQA) methodology, and compared different kinds of statistical estimators, namely Multilayer Perceptrons (MLP) and Random Neural Networks (RNN).

KW - audiovisual quality assessment

KW - feature clustering

KW - neural network

KW - video quality assessment

U2 - 10.1109/QoMEX.2013.6603193

DO - 10.1109/QoMEX.2013.6603193

M3 - Conference article in proceedings

SP - 6

EP - 11

BT - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 5th International Workshop on Quality of Multimedia Experience, QoMEX 2013

Y2 - 5 July 2013 through 7 July 2013

ER -