Informatics Report Series


Report   

EDI-INF-RR-1298


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:A Computer Vision Model for Visual-Object-Based Attention and Eye Movements
Authors: Youru Sun ; Robert Fisher ; Fang Wang ; Herman Gomes
Date: 2008
Publication Title:Computer Vision and Image Understanding
Publisher:Elsevier
Publication Type:Journal Article Publication Status:Published
Volume No:112(2) Page Nos:126-142
DOI:10.1016/j.cviu.2008.01.005
Abstract:
This paper presents a new computational framework for modelling visual-object based attention and attention-driven eye movements within an integrated system in a biologically inspired approach. Attention operates at multiple levels of visual selection by space, feature, object and group depending on the nature of targets and visual tasks. Attentional shifts and gaze shifts are constructed upon their common process circuits and control mechanisms but also separated from their different function roles, working together to fulfil flexible visual selection tasks in complicated visual environments. The framework integrates the important aspects of human visual attention and eye movements resulting in sophisticated performance in complicated natural scenes. The proposed approach aims at exploring a useful visual selection system for computer vision, especially for usage in cluttered natural visual environments.
Copyright:
2008 by The University of Edinburgh and Elsevier. All Rights Reserved
Links To Paper
Elsevier/CVIU web site
Bibtex format
@Article{EDI-INF-RR-1298,
author = { Youru Sun and Robert Fisher and Fang Wang and Herman Gomes },
title = {A Computer Vision Model for Visual-Object-Based Attention and Eye Movements},
journal = {Computer Vision and Image Understanding},
publisher = {Elsevier},
year = 2008,
volume = {112(2)},
pages = {126-142},
doi = {10.1016/j.cviu.2008.01.005},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh