Towards efficient context-specific video coding based on gaze-tracking analysis

D Agrafiotis; SJC Davies; CN Canagarajah; DR Bull

doi:10.1145/1314303.1314307

Towards efficient context-specific video coding based on gaze-tracking analysis

D Agrafiotis, SJC Davies, CN Canagarajah, DR Bull

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

12 Citations (Scopus)

Abstract

This article discusses a framework for model-based, context-dependent video coding based on exploitation of characteristics of the human visual system. The system utilizes variable-quality coding based on priority maps which are created using mostly context-dependent rules. The technique is demonstrated through two case studies of specific video context, namely open signed content and football sequences. Eye-tracking analysis is employed for identifying the characteristics of each context, which are subsequently exploited for coding purposes, either directly or through a gaze prediction model. The framework is shown to achieve a considerable improvement in coding efficiency

Translated title of the contribution	Towards efficient context-specific video coding based on gaze-tracking analysis
Original language	English
Pages (from-to)	22:1 - 22:15
Number of pages	15
Journal	ACM Transactions on Multimedia Computing, Communications and Applications
Volume	3 (4)
DOIs	https://doi.org/10.1145/1314303.1314307
Publication status	Published - Dec 2007

Bibliographical note

Publisher: Association for Computing Machinery

Access to Document

10.1145/1314303.1314307

Handle.net

Persistent link

ACADEMIC FELLOWSHIP RCUK
Piccini, A. A.
1/02/05 → 1/02/10
Project: Research

Cite this

@article{f26091edb7e64c5791ccc82f36e31bc2,

title = "Towards efficient context-specific video coding based on gaze-tracking analysis",

abstract = "This article discusses a framework for model-based, context-dependent video coding based on exploitation of characteristics of the human visual system. The system utilizes variable-quality coding based on priority maps which are created using mostly context-dependent rules. The technique is demonstrated through two case studies of specific video context, namely open signed content and football sequences. Eye-tracking analysis is employed for identifying the characteristics of each context, which are subsequently exploited for coding purposes, either directly or through a gaze prediction model. The framework is shown to achieve a considerable improvement in coding efficiency",

author = "D Agrafiotis and SJC Davies and CN Canagarajah and DR Bull",

note = "Publisher: Association for Computing Machinery",

year = "2007",

month = dec,

doi = "10.1145/1314303.1314307",

language = "English",

volume = "3 (4)",

pages = "22:1 -- 22:15",

journal = "ACM Transactions on Multimedia Computing, Communications and Applications",

issn = "1551-6857",

publisher = "Association for Computing Machinery (ACM)",

}

TY - JOUR

T1 - Towards efficient context-specific video coding based on gaze-tracking analysis

AU - Agrafiotis, D

AU - Davies, SJC

AU - Canagarajah, CN

AU - Bull, DR

N1 - Publisher: Association for Computing Machinery

PY - 2007/12

Y1 - 2007/12

N2 - This article discusses a framework for model-based, context-dependent video coding based on exploitation of characteristics of the human visual system. The system utilizes variable-quality coding based on priority maps which are created using mostly context-dependent rules. The technique is demonstrated through two case studies of specific video context, namely open signed content and football sequences. Eye-tracking analysis is employed for identifying the characteristics of each context, which are subsequently exploited for coding purposes, either directly or through a gaze prediction model. The framework is shown to achieve a considerable improvement in coding efficiency

AB - This article discusses a framework for model-based, context-dependent video coding based on exploitation of characteristics of the human visual system. The system utilizes variable-quality coding based on priority maps which are created using mostly context-dependent rules. The technique is demonstrated through two case studies of specific video context, namely open signed content and football sequences. Eye-tracking analysis is employed for identifying the characteristics of each context, which are subsequently exploited for coding purposes, either directly or through a gaze prediction model. The framework is shown to achieve a considerable improvement in coding efficiency

U2 - 10.1145/1314303.1314307

DO - 10.1145/1314303.1314307

M3 - Article (Academic Journal)

VL - 3 (4)

SP - 22:1 - 22:15

JO - ACM Transactions on Multimedia Computing, Communications and Applications

JF - ACM Transactions on Multimedia Computing, Communications and Applications

SN - 1551-6857

ER -

Towards efficient context-specific video coding based on gaze-tracking analysis

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Projects

ACADEMIC FELLOWSHIP RCUK

Cite this