Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/62
Title: Spatiotemporal saliency for video classification
Authors: Tsapatsoulis, Nicolas 
Rapantzikos, Konstantinos 
Avrithis, Yannis 
Kollias, Stefanos D. 
Keywords: Spatiotemporal visual saliency;Video classification
Category: Media and Communications
Field: Social Sciences
Issue Date: 2009
Publisher: Elsevier B.V.
Source: Signal Processing: Image Communication, 2009, Volume 24, Issue 7, Pages 557–571
Journal: Signal Processing: Image Communication 
Abstract: Computer vision applications often need to process only a representative part of the visual input rather than the whole image/sequence. Considerable research has been carried out into salient region detection methods based either on models emulating human visual attention (VA) mechanisms or on computational approximations. Most of the proposed methods are bottom-up and their major goal is to filter out redundant visual information. In this paper, we propose and elaborate on a saliency detection model that treats a video sequence as a spatiotemporal volume and generates a local saliency measure for each visual unit (voxel). This computation involves an optimization process incorporating inter- and intra-feature competition at the voxel level. Perceptual decomposition of the input, spatiotemporal center-surround interactions and the integration of heterogeneous feature conspicuity values are described and an experimental framework for video classification is set up. This framework consists of a series of experiments that shows the effect of saliency in classification performance and let us draw conclusions on how well the detected salient regions represent the visual input. A comparison is attempted that shows the potential of the proposed method.
URI: http://ktisis.cut.ac.cy/handle/10488/62
http://ktisis.cut.ac.cy/handle/10488/62
http://hdl.handle.net/10488/62
ISSN: 0923-5965
DOI: 10.1016/j.image.2009.03.002
Rights: Copyright © 2009 Elsevier B.V. All rights reserved.
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

SCOPUSTM   
Citations 50

22
checked on Feb 13, 2018

WEB OF SCIENCETM
Citations 50

21
checked on Aug 5, 2019

Page view(s) 50

123
Last Week
1
Last month
6
checked on Aug 21, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.