Visual attention modeling : region-of-interest versus fixation patterns

Ulrich Engelke; Hans-Jurgen Zepernick; Anthony Maeder

Visual attention modeling : region-of-interest versus fixation patterns

Ulrich Engelke
, Hans-Jurgen Zepernick
, Anthony Maeder

Research output: Chapter in Book / Conference Paper › Conference Paper

Abstract

Visual attention (VA) is an integral property of the human visual system. The deployment of a VA model can be beneficial for many image and video applications, such as, compression, transmission, and quality assessment. However, the design of a VA model is highly dependent on the subjective VA data used as ground truth and the application that the model is intended for. In this paper, we discuss two ways of obtaining subjective VA data that can subsequently be used to develop VA models; selective regions-of-interest and visual fixation patterns. The feasibility of both methods will be discussed, in particular, with respect to visual quality assessment.

Original language	English
Title of host publication	PCS 2009 : 27th Picture Coding Symposium, May 6-8, 2009, Chicago, Illinois, USA
Publisher	I.E.E.E.
Pages	1-4
Number of pages	4
ISBN (Print)	9781424445936
Publication status	Published - 2010
Event	PCS 2009 : 27th Picture Coding Symposium - Duration: 1 Jan 2010 → …

Conference

Conference	PCS 2009 : 27th Picture Coding Symposium
Period	1/01/10 → …

Keywords

image quality
attention

Cite this

@inproceedings{42945740cfaf4cedb980a372693c1c2f,

title = "Visual attention modeling : region-of-interest versus fixation patterns",

abstract = "Visual attention (VA) is an integral property of the human visual system. The deployment of a VA model can be beneficial for many image and video applications, such as, compression, transmission, and quality assessment. However, the design of a VA model is highly dependent on the subjective VA data used as ground truth and the application that the model is intended for. In this paper, we discuss two ways of obtaining subjective VA data that can subsequently be used to develop VA models; selective regions-of-interest and visual fixation patterns. The feasibility of both methods will be discussed, in particular, with respect to visual quality assessment.",

keywords = "image quality, attention",

author = "Ulrich Engelke and Hans-Jurgen Zepernick and Anthony Maeder",

year = "2010",

language = "English",

isbn = "9781424445936",

pages = "1--4",

booktitle = "PCS 2009 : 27th Picture Coding Symposium, May 6-8, 2009, Chicago, Illinois, USA",

publisher = "I.E.E.E.",

note = "PCS 2009 : 27th Picture Coding Symposium ; Conference date: 01-01-2010",

}

TY - GEN

T1 - Visual attention modeling : region-of-interest versus fixation patterns

AU - Engelke, Ulrich

AU - Zepernick, Hans-Jurgen

AU - Maeder, Anthony

PY - 2010

Y1 - 2010

N2 - Visual attention (VA) is an integral property of the human visual system. The deployment of a VA model can be beneficial for many image and video applications, such as, compression, transmission, and quality assessment. However, the design of a VA model is highly dependent on the subjective VA data used as ground truth and the application that the model is intended for. In this paper, we discuss two ways of obtaining subjective VA data that can subsequently be used to develop VA models; selective regions-of-interest and visual fixation patterns. The feasibility of both methods will be discussed, in particular, with respect to visual quality assessment.

AB - Visual attention (VA) is an integral property of the human visual system. The deployment of a VA model can be beneficial for many image and video applications, such as, compression, transmission, and quality assessment. However, the design of a VA model is highly dependent on the subjective VA data used as ground truth and the application that the model is intended for. In this paper, we discuss two ways of obtaining subjective VA data that can subsequently be used to develop VA models; selective regions-of-interest and visual fixation patterns. The feasibility of both methods will be discussed, in particular, with respect to visual quality assessment.

KW - image quality

KW - attention

UR - http://handle.uws.edu.au:8081/1959.7/504448

M3 - Conference Paper

SN - 9781424445936

SP - 1

EP - 4

BT - PCS 2009 : 27th Picture Coding Symposium, May 6-8, 2009, Chicago, Illinois, USA

PB - I.E.E.E.

T2 - PCS 2009 : 27th Picture Coding Symposium

Y2 - 1 January 2010

ER -

Visual attention modeling : region-of-interest versus fixation patterns

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this