A regression method for real-time video quality evaluation

M. Torres Vega; D.C. Mocanu; A. Liotta

doi:10.1145/3007120.3007125

A regression method for real-time video quality evaluation

M. Torres Vega, D.C. Mocanu, A. Liotta

Electro-Optical Communication

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

2 Citations (Scopus)

351 Downloads (Pure)

Abstract

No-Reference (NR) metrics provide a mechanism to assess video quality in an ever-growing wireless network. Their low computational complexity and functional characteristics make them the primary choice when it comes to realtime content management and mobile streaming control. Unfortunately, common NR metrics suer from poor accuracy, particularly in network-impaired video streams. In this work, we introduce a regression-based video quality metric that is simple enough for real-time computation on thin clients, and comparably as accurate as state-of-the-art Full-Reference (FR) metrics, which are functionally and computationally inviable in real-time streaming. We benchmark our metric against the FR metric VQM (Video Quality Metric), finding a very strong correlation factor.

Original language	English
Title of host publication	MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore
Editors	B. Abdulrazak, E. Pardede, M. Steinbauer, I. Khalil, G. Anderst-Kotsis
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	217-224
Number of pages	8
ISBN (Print)	978-1-4503-4806-5
DOIs	https://doi.org/10.1145/3007120.3007125
Publication status	Published - 29 Nov 2016
Event	14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016) - Singapore, Singapore Duration: 28 Nov 2016 → 30 Nov 2016 Conference number: 14 http://www.iiwas.org/conferences/momm2016/

Conference

Conference	14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)
Abbreviated title	MOMM2016
Country/Territory	Singapore
City	Singapore
Period	28/11/16 → 30/11/16
Internet address	http://www.iiwas.org/conferences/momm2016/

Access to Document

10.1145/3007120.3007125

author versionGalley Proof, 12.4 MB

Cite this

Torres Vega, M., Mocanu, D. C., & Liotta, A. (2016). A regression method for real-time video quality evaluation. In B. Abdulrazak, E. Pardede, M. Steinbauer, I. Khalil, & G. Anderst-Kotsis (Eds.), MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore (pp. 217-224). Association for Computing Machinery, Inc. https://doi.org/10.1145/3007120.3007125

Torres Vega, M. ; Mocanu, D.C. ; Liotta, A. / A regression method for real-time video quality evaluation. MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore. editor / B. Abdulrazak ; E. Pardede ; M. Steinbauer ; I. Khalil ; G. Anderst-Kotsis. New York : Association for Computing Machinery, Inc, 2016. pp. 217-224

@inproceedings{0c2291d67d394125a9ec7c15b4298aef,

title = "A regression method for real-time video quality evaluation",

abstract = "No-Reference (NR) metrics provide a mechanism to assess video quality in an ever-growing wireless network. Their low computational complexity and functional characteristics make them the primary choice when it comes to realtime content management and mobile streaming control. Unfortunately, common NR metrics suer from poor accuracy, particularly in network-impaired video streams. In this work, we introduce a regression-based video quality metric that is simple enough for real-time computation on thin clients, and comparably as accurate as state-of-the-art Full-Reference (FR) metrics, which are functionally and computationally inviable in real-time streaming. We benchmark our metric against the FR metric VQM (Video Quality Metric), finding a very strong correlation factor.",

author = "{Torres Vega}, M. and D.C. Mocanu and A. Liotta",

year = "2016",

month = nov,

day = "29",

doi = "10.1145/3007120.3007125",

language = "English",

isbn = "978-1-4503-4806-5",

pages = "217--224",

editor = "B. Abdulrazak and E. Pardede and Steinbauer, {M. } and I. Khalil and G. Anderst-Kotsis",

booktitle = "MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

note = "14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)<br/>, MOMM2016 ; Conference date: 28-11-2016 Through 30-11-2016",

url = "http://www.iiwas.org/conferences/momm2016/",

}

Torres Vega, M, Mocanu, DC & Liotta, A 2016, A regression method for real-time video quality evaluation. in B Abdulrazak, E Pardede, M Steinbauer, I Khalil & G Anderst-Kotsis (eds), MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore. Association for Computing Machinery, Inc, New York, pp. 217-224, 14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)
, Singapore, Singapore, 28/11/16. https://doi.org/10.1145/3007120.3007125

A regression method for real-time video quality evaluation. / Torres Vega, M.; Mocanu, D.C.; Liotta, A.
MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore. ed. / B. Abdulrazak; E. Pardede; M. Steinbauer; I. Khalil; G. Anderst-Kotsis. New York: Association for Computing Machinery, Inc, 2016. p. 217-224.

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

TY - GEN

T1 - A regression method for real-time video quality evaluation

AU - Torres Vega, M.

AU - Mocanu, D.C.

AU - Liotta, A.

N1 - Conference code: 14

PY - 2016/11/29

Y1 - 2016/11/29

N2 - No-Reference (NR) metrics provide a mechanism to assess video quality in an ever-growing wireless network. Their low computational complexity and functional characteristics make them the primary choice when it comes to realtime content management and mobile streaming control. Unfortunately, common NR metrics suer from poor accuracy, particularly in network-impaired video streams. In this work, we introduce a regression-based video quality metric that is simple enough for real-time computation on thin clients, and comparably as accurate as state-of-the-art Full-Reference (FR) metrics, which are functionally and computationally inviable in real-time streaming. We benchmark our metric against the FR metric VQM (Video Quality Metric), finding a very strong correlation factor.

AB - No-Reference (NR) metrics provide a mechanism to assess video quality in an ever-growing wireless network. Their low computational complexity and functional characteristics make them the primary choice when it comes to realtime content management and mobile streaming control. Unfortunately, common NR metrics suer from poor accuracy, particularly in network-impaired video streams. In this work, we introduce a regression-based video quality metric that is simple enough for real-time computation on thin clients, and comparably as accurate as state-of-the-art Full-Reference (FR) metrics, which are functionally and computationally inviable in real-time streaming. We benchmark our metric against the FR metric VQM (Video Quality Metric), finding a very strong correlation factor.

U2 - 10.1145/3007120.3007125

DO - 10.1145/3007120.3007125

M3 - Conference contribution

SN - 978-1-4503-4806-5

SP - 217

EP - 224

BT - MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore

A2 - Abdulrazak, B.

A2 - Pardede, E.

A2 - Steinbauer, M.

A2 - Khalil, I.

A2 - Anderst-Kotsis, G.

PB - Association for Computing Machinery, Inc

CY - New York

T2 - 14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)<br/>

Y2 - 28 November 2016 through 30 November 2016

ER -

Torres Vega M, Mocanu DC, Liotta A. A regression method for real-time video quality evaluation. In Abdulrazak B, Pardede E, Steinbauer M, Khalil I, Anderst-Kotsis G, editors, MoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore. New York: Association for Computing Machinery, Inc. 2016. p. 217-224 doi: 10.1145/3007120.3007125

A regression method for real-time video quality evaluation

Abstract

Conference

Access to Document

Fingerprint

Cite this