A fast voting-based technique for human action recognition in video sequences

Human action recognition has been an active research area in recent years. However, building a robust human action recognition system still remains a challenging task due to the large variations in action classes, varying human appearances, illumination changes, camera motion, occlusions and backgro...

Full description

Saved in:
Bibliographic Details
Main Authors: Goh, Wooi-Boon, Tran, Duc-Hieu
Other Authors: School of Computer Engineering
Format: Conference or Workshop Item
Language:English
Published: 2015
Subjects:
Online Access:https://hdl.handle.net/10356/106629
http://hdl.handle.net/10220/25061
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-106629
record_format dspace
spelling sg-ntu-dr.10356-1066292020-05-28T07:17:43Z A fast voting-based technique for human action recognition in video sequences Goh, Wooi-Boon Tran, Duc-Hieu School of Computer Engineering International Conference on Computer Vision Theory and Applications DRNTU::Engineering::Computer science and engineering Human action recognition has been an active research area in recent years. However, building a robust human action recognition system still remains a challenging task due to the large variations in action classes, varying human appearances, illumination changes, camera motion, occlusions and background clutter. Most previous work focus on the goal of improving recognition rates. This paper describes a computationally fast votingbased approach for human action recognition, in which the action in the video sequence is recognized based on the support of the local spatio-temporal features. The proposed technique requires no parameter tuning and can produce recognition rates that are comparable to those in recent published literature. Moreover, the technique can localize the single human action in the video sequence without much additional computation. Recognition results on the KTH and Weizmann action dataset are presented. Published version 2015-02-16T02:20:21Z 2019-12-06T22:15:12Z 2015-02-16T02:20:21Z 2019-12-06T22:15:12Z 2012 2012 Conference Paper Tran, D.-H., & Goh, W.-B. (2012). A fast voting-based technique for human action recognition in video sequences. Proceedings of the International Conference on Computer Vision Theory and Applications. https://hdl.handle.net/10356/106629 http://hdl.handle.net/10220/25061 10.5220/0003850606130619 en © 2012 Scitepress. This paper was published in Proceedings of the International Conference on Computer Vision Theory and Applications and is made available as an electronic reprint (preprint) with permission of Scitepress. The paper can be found at the following official DOI: [http://dx.doi.org/10.5220/0003850606130619].  One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. 6 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Goh, Wooi-Boon
Tran, Duc-Hieu
A fast voting-based technique for human action recognition in video sequences
description Human action recognition has been an active research area in recent years. However, building a robust human action recognition system still remains a challenging task due to the large variations in action classes, varying human appearances, illumination changes, camera motion, occlusions and background clutter. Most previous work focus on the goal of improving recognition rates. This paper describes a computationally fast votingbased approach for human action recognition, in which the action in the video sequence is recognized based on the support of the local spatio-temporal features. The proposed technique requires no parameter tuning and can produce recognition rates that are comparable to those in recent published literature. Moreover, the technique can localize the single human action in the video sequence without much additional computation. Recognition results on the KTH and Weizmann action dataset are presented.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Goh, Wooi-Boon
Tran, Duc-Hieu
format Conference or Workshop Item
author Goh, Wooi-Boon
Tran, Duc-Hieu
author_sort Goh, Wooi-Boon
title A fast voting-based technique for human action recognition in video sequences
title_short A fast voting-based technique for human action recognition in video sequences
title_full A fast voting-based technique for human action recognition in video sequences
title_fullStr A fast voting-based technique for human action recognition in video sequences
title_full_unstemmed A fast voting-based technique for human action recognition in video sequences
title_sort fast voting-based technique for human action recognition in video sequences
publishDate 2015
url https://hdl.handle.net/10356/106629
http://hdl.handle.net/10220/25061
_version_ 1681059128331468800