A regression method for real-time video quality evaluation

Maria Torres Vega; Decebal Constantin Mocanu; Antonio Liotta

doi:10.1145/3007120.3007125

A regression method for real-time video quality evaluation

Maria Torres Vega, Decebal Constantin Mocanu, Antonio Liotta

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

2 Citations (Scopus)

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 suffer 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
Subtitle of host publication	Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media
Editors	Bessam Abdulrazak, Matthias Steinbauer, Ismail Khalil, Eric Pardede, Gabriele Anderst-Kotsis
Place of Publication	New York, NY
Publisher	Association for Computing Machinery
Pages	217-224
Number of pages	8
ISBN (Electronic)	9781450348065
DOIs	https://doi.org/10.1145/3007120.3007125
Publication status	Published - 28 Nov 2016
Externally published	Yes
Event	14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Grand Copthorne Waterfront Singapore, Singapore, Singapore Duration: 28 Nov 2016 → 30 Nov 2016 Conference number: 14

Conference

Conference	14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016
Abbreviated title	MoMM 2016
Country/Territory	Singapore
City	Singapore
Period	28/11/16 → 30/11/16

Keywords

Cognitive QoE assessment metrics
No-reference video quality
Quality of experience
Regression processes

Access to Document

10.1145/3007120.3007125

Cite this

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

Torres Vega, Maria ; Mocanu, Decebal Constantin ; Liotta, Antonio. / A regression method for real-time video quality evaluation. MoMM '16: Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media. editor / Bessam Abdulrazak ; Matthias Steinbauer ; Ismail Khalil ; Eric Pardede ; Gabriele Anderst-Kotsis. New York, NY : Association for Computing Machinery, 2016. pp. 217-224

@inproceedings{d57f6201fa1d4699b9b810ee2e08181f,

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 suffer 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.",

keywords = "Cognitive QoE assessment metrics, No-reference video quality, Quality of experience, Regression processes",

author = "{Torres Vega}, Maria and Mocanu, {Decebal Constantin} and Antonio Liotta",

year = "2016",

month = nov,

day = "28",

doi = "10.1145/3007120.3007125",

language = "English",

pages = "217--224",

editor = "Bessam Abdulrazak and Matthias Steinbauer and Ismail Khalil and Eric Pardede and Gabriele Anderst-Kotsis",

booktitle = "MoMM '16",

publisher = "Association for Computing Machinery",

address = "United States",

note = "14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016, MoMM 2016 ; Conference date: 28-11-2016 Through 30-11-2016",

}

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

A regression method for real-time video quality evaluation. / Torres Vega, Maria; Mocanu, Decebal Constantin; Liotta, Antonio.
MoMM '16: Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media. ed. / Bessam Abdulrazak; Matthias Steinbauer; Ismail Khalil; Eric Pardede; Gabriele Anderst-Kotsis. New York, NY: Association for Computing Machinery, 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, Maria

AU - Mocanu, Decebal Constantin

AU - Liotta, Antonio

N1 - Conference code: 14

PY - 2016/11/28

Y1 - 2016/11/28

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 suffer 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 suffer 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.

KW - Cognitive QoE assessment metrics

KW - No-reference video quality

KW - Quality of experience

KW - Regression processes

UR - http://www.scopus.com/inward/record.url?scp=85015094073&partnerID=8YFLogxK

U2 - 10.1145/3007120.3007125

DO - 10.1145/3007120.3007125

M3 - Conference contribution

AN - SCOPUS:85015094073

SP - 217

EP - 224

BT - MoMM '16

A2 - Abdulrazak, Bessam

A2 - Steinbauer, Matthias

A2 - Khalil, Ismail

A2 - Pardede, Eric

A2 - Anderst-Kotsis, Gabriele

PB - Association for Computing Machinery

CY - New York, NY

T2 - 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016

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, Steinbauer M, Khalil I, Pardede E, Anderst-Kotsis G, editors, MoMM '16: Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media. New York, NY: Association for Computing Machinery. 2016. p. 217-224 doi: 10.1145/3007120.3007125

A regression method for real-time video quality evaluation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this