Behavior representation in visual crowd scenes using space-time features

In this paper, we present a motion and oriented gradient based approach for behavior representation in a sparse crowd scene. We present a method that builds upon the previous ideas such as local space-time features and space-time pyramid. The method is aimed at exploiting the activity coherently and...

Full description

Main Authors: Shuaibu, A.N., Malik, A.S., Faye, I.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.20223 /
Published: Institute of Electrical and Electronics Engineers Inc. 2017
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85012008426&doi=10.1109%2fICIAS.2016.7824073&partnerID=40&md5=8a0897c6184bb1e6c602d221686d2f23
http://eprints.utp.edu.my/20223/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.20223
recordtype eprints
spelling utp-eprints.202232018-04-22T14:46:16Z Behavior representation in visual crowd scenes using space-time features Shuaibu, A.N. Malik, A.S. Faye, I. In this paper, we present a motion and oriented gradient based approach for behavior representation in a sparse crowd scene. We present a method that builds upon the previous ideas such as local space-time features and space-time pyramid. The method is aimed at exploiting the activity coherently and effectively by extracting low-level features at spatial-temporal interest point's neighborhood; a histogram of optical flow and a histogram of the oriented gradient. Relying on the measurable attributes of objects description and motion characteristics, specific behavior such as crossing, walking, merging and splitting can be detected more accurately. We present a new method for crowd behavior classification based on space-time features. An experimental evaluation is conducted on publicly available crowd analytic datasets. The result indicates that radial basis function support vector machine shows a good accuracy, precision and recall in classifying human behavior when compared to a nearest neighbor classifier. © 2016 IEEE. Institute of Electrical and Electronics Engineers Inc. 2017 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85012008426&doi=10.1109%2fICIAS.2016.7824073&partnerID=40&md5=8a0897c6184bb1e6c602d221686d2f23 Shuaibu, A.N. and Malik, A.S. and Faye, I. (2017) Behavior representation in visual crowd scenes using space-time features. International Conference on Intelligent and Advanced Systems, ICIAS 2016 . http://eprints.utp.edu.my/20223/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description In this paper, we present a motion and oriented gradient based approach for behavior representation in a sparse crowd scene. We present a method that builds upon the previous ideas such as local space-time features and space-time pyramid. The method is aimed at exploiting the activity coherently and effectively by extracting low-level features at spatial-temporal interest point's neighborhood; a histogram of optical flow and a histogram of the oriented gradient. Relying on the measurable attributes of objects description and motion characteristics, specific behavior such as crossing, walking, merging and splitting can be detected more accurately. We present a new method for crowd behavior classification based on space-time features. An experimental evaluation is conducted on publicly available crowd analytic datasets. The result indicates that radial basis function support vector machine shows a good accuracy, precision and recall in classifying human behavior when compared to a nearest neighbor classifier. © 2016 IEEE.
format Article
author Shuaibu, A.N.
Malik, A.S.
Faye, I.
spellingShingle Shuaibu, A.N.
Malik, A.S.
Faye, I.
Behavior representation in visual crowd scenes using space-time features
author_sort Shuaibu, A.N.
title Behavior representation in visual crowd scenes using space-time features
title_short Behavior representation in visual crowd scenes using space-time features
title_full Behavior representation in visual crowd scenes using space-time features
title_fullStr Behavior representation in visual crowd scenes using space-time features
title_full_unstemmed Behavior representation in visual crowd scenes using space-time features
title_sort behavior representation in visual crowd scenes using space-time features
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2017
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85012008426&doi=10.1109%2fICIAS.2016.7824073&partnerID=40&md5=8a0897c6184bb1e6c602d221686d2f23
http://eprints.utp.edu.my/20223/
_version_ 1741196337481777152
score 11.62408

Similar Items