A regression method for real-time video quality evaluation

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)
182 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 languageEnglish
Title of host publicationMoMM '16 : Proceedings of the 14th International Conference on Advances in Mobile Computing and Multimedia, 28-30 November 2016, Singapore, Singapore
EditorsB. Abdulrazak, E. Pardede, M. Steinbauer, I. Khalil, G. Anderst-Kotsis
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages217-224
Number of pages8
ISBN (Print)978-1-4503-4806-5
DOIs
Publication statusPublished - 29 Nov 2016
Event14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)
- Singapore, Singapore
Duration: 28 Nov 201630 Nov 2016
Conference number: 14
http://www.iiwas.org/conferences/momm2016/

Conference

Conference14th International Conference on Advances in Mobile Computing & Multimedia (MoMM2016)
Abbreviated titleMOMM2016
CountrySingapore
CitySingapore
Period28/11/1630/11/16
Internet address

Fingerprint Dive into the research topics of 'A regression method for real-time video quality evaluation'. Together they form a unique fingerprint.

Cite this