A multi-metric approach for block-level video quality assessment

Miltiadis Alexios Papadopoulos; Angeliki Katsenou; Dimitris Agrafiotis; David Bull

doi:10.1016/j.image.2019.06.009

A multi-metric approach for block-level video quality assessment

Miltiadis Alexios Papadopoulos, Angeliki Katsenou^*, Dimitris Agrafiotis, David Bull

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

4 Citations (Scopus)

231 Downloads (Pure)

Abstract

Developing an objective video quality metric that accurately estimates perceived video quality is challenging. Developing a metric that can additionally be embedded in the rate distortion optimisation process of a video codec can be even harder given that decisions have to be made locally. In this paper, we present a method for combining a number of existing state of the art objective video quality metrics at the coding block level by employing a fusion of local content features for deciding how to best utilise the chosen metrics. Our results indicate promising performance in terms of the correlation of the developed locally-acting quality metric with the overall perceived quality of the video.

Original language	English
Pages (from-to)	152-158
Number of pages	7
Journal	Signal Processing: Image Communication
Volume	78
Early online date	28 Jun 2019
DOIs	https://doi.org/10.1016/j.image.2019.06.009
Publication status	Published - 1 Oct 2019

Keywords

Block-level
Content features
Fusion of metrics
RDO
Video quality assessment

Access to Document

10.1016/j.image.2019.06.009

Full-text PDF (final published version)
This is the final published version of the article (version of record). It first appeared online via Elsevier at https://www.sciencedirect.com/science/article/pii/S0923596518307653 . Please refer to any applicable terms of use of the publisher.
Final published version, 662 KBLicence: CC BY-NC-ND

Handle.net

Persistent link

Cite this

@article{bec74e386cc548b486e36d55ad961596,

title = "A multi-metric approach for block-level video quality assessment",

abstract = "Developing an objective video quality metric that accurately estimates perceived video quality is challenging. Developing a metric that can additionally be embedded in the rate distortion optimisation process of a video codec can be even harder given that decisions have to be made locally. In this paper, we present a method for combining a number of existing state of the art objective video quality metrics at the coding block level by employing a fusion of local content features for deciding how to best utilise the chosen metrics. Our results indicate promising performance in terms of the correlation of the developed locally-acting quality metric with the overall perceived quality of the video.",

keywords = "Block-level, Content features, Fusion of metrics, RDO, Video quality assessment",

author = "Papadopoulos, {Miltiadis Alexios} and Angeliki Katsenou and Dimitris Agrafiotis and David Bull",

year = "2019",

month = oct,

day = "1",

doi = "10.1016/j.image.2019.06.009",

language = "English",

volume = "78",

pages = "152--158",

journal = "Signal Processing: Image Communication",

issn = "0923-5965",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A multi-metric approach for block-level video quality assessment

AU - Papadopoulos, Miltiadis Alexios

AU - Katsenou, Angeliki

AU - Agrafiotis, Dimitris

AU - Bull, David

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Developing an objective video quality metric that accurately estimates perceived video quality is challenging. Developing a metric that can additionally be embedded in the rate distortion optimisation process of a video codec can be even harder given that decisions have to be made locally. In this paper, we present a method for combining a number of existing state of the art objective video quality metrics at the coding block level by employing a fusion of local content features for deciding how to best utilise the chosen metrics. Our results indicate promising performance in terms of the correlation of the developed locally-acting quality metric with the overall perceived quality of the video.

AB - Developing an objective video quality metric that accurately estimates perceived video quality is challenging. Developing a metric that can additionally be embedded in the rate distortion optimisation process of a video codec can be even harder given that decisions have to be made locally. In this paper, we present a method for combining a number of existing state of the art objective video quality metrics at the coding block level by employing a fusion of local content features for deciding how to best utilise the chosen metrics. Our results indicate promising performance in terms of the correlation of the developed locally-acting quality metric with the overall perceived quality of the video.

KW - Block-level

KW - Content features

KW - Fusion of metrics

KW - RDO

KW - Video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85068220129&partnerID=8YFLogxK

U2 - 10.1016/j.image.2019.06.009

DO - 10.1016/j.image.2019.06.009

M3 - Article (Academic Journal)

AN - SCOPUS:85068220129

SN - 0923-5965

VL - 78

SP - 152

EP - 158

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

ER -

A multi-metric approach for block-level video quality assessment

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Embargoed Document

Fingerprint

Vision for the Future-Full

Dr Dimitris Agrafiotis

Dr Angeliki Katsenou

Cite this

A multi-metric approach for block-level video quality assessment

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Embargoed Document

Fingerprint

Projects

Vision for the Future-Full

Profiles

Dr Dimitris Agrafiotis

Dr Angeliki Katsenou

Cite this