Detection of dominant flow and abnormal events in surveillance video

We propose an algorithm for abnormal event detection in surveillance video. The proposed algorithm is based on a semi-unsupervised learning method, a kind of feature-based approach so that it does not detect the moving object individually. The proposed algorithm identifies dominant flow without indi...

Full description

Saved in:
Bibliographic Details
Published in:Optical Engineering 2011-02, Vol.50 (2), p.027202-027202
Main Authors: Kwak, Sooyeong, Byun, Hyeran
Format: Article
Language:English
Subjects:
Algorithms
Allocations
Dirichlet problem
Learning
Real time
Surveillance
Tracking
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683
cites cdi_FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683
container_end_page 027202
container_issue 2
container_start_page 027202
container_title Optical Engineering
container_volume 50
creator Kwak, Sooyeong
Byun, Hyeran
description We propose an algorithm for abnormal event detection in surveillance video. The proposed algorithm is based on a semi-unsupervised learning method, a kind of feature-based approach so that it does not detect the moving object individually. The proposed algorithm identifies dominant flow without individual object tracking using a latent Dirichlet allocation model in crowded environments. It can also automatically detect and localize an abnormally moving object in real-life video. The performance tests are taken with several real-life databases, and their results show that the proposed algorithm can efficiently detect abnormally moving objects in real time. The proposed algorithm can be applied to any situation in which abnormal directions or abnormal speeds are detected regardless of direction.
doi_str_mv 10.1117/1.3542038
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_889406244</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>889406244</sourcerecordid><originalsourceid>FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683</originalsourceid><addsrcrecordid>eNo9kE1LAzEQhoMoWKsH_0Fu4mHrTJLNZo-lrVUoVETPS7pJILKb1M224r93-4EDw8zh4eXlIeQeYYKIxRNOeC4YcHVBRphLyBgHfklGACVmnCl5TW5S-gIAVio1IvO57W3d-xhodNTE1gcdeuqa-EN1MFRvQuxa3VC7t6FP1Aeadt3e-qbRobZ0742Nt-TK6SbZu_Mdk8_nxcfsJVutl6-z6SqrOYg-c-AUoNsUiGIjjANlrZHaKFbK3Gk0UNqylELXtStyhNw5aYRGKYUAlIqPycMpd9vF751NfdX6VNtDFRt3qVKqFCCZEAP5eCLrLqbUWVdtO9_q7rdCqA6iKqzOogaWndi09fafW78tltP3wRPkcBwGrBj2-CP_A7jsZ-s</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>889406244</pqid></control><display><type>article</type><title>Detection of dominant flow and abnormal events in surveillance video</title><source>SPIE Digital Library</source><creator>Kwak, Sooyeong ; Byun, Hyeran</creator><creatorcontrib>Kwak, Sooyeong ; Byun, Hyeran</creatorcontrib><description>We propose an algorithm for abnormal event detection in surveillance video. The proposed algorithm is based on a semi-unsupervised learning method, a kind of feature-based approach so that it does not detect the moving object individually. The proposed algorithm identifies dominant flow without individual object tracking using a latent Dirichlet allocation model in crowded environments. It can also automatically detect and localize an abnormally moving object in real-life video. The performance tests are taken with several real-life databases, and their results show that the proposed algorithm can efficiently detect abnormally moving objects in real time. The proposed algorithm can be applied to any situation in which abnormal directions or abnormal speeds are detected regardless of direction.</description><identifier>ISSN: 0091-3286</identifier><identifier>EISSN: 1560-2303</identifier><identifier>DOI: 10.1117/1.3542038</identifier><identifier>CODEN: OPEGAR</identifier><language>eng</language><subject>Algorithms ; Allocations ; Dirichlet problem ; Learning ; Real time ; Surveillance ; Tracking</subject><ispartof>Optical Engineering, 2011-02, Vol.50 (2), p.027202-027202</ispartof><rights>2011 COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683</citedby><cites>FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.spiedigitallibrary.org/journalArticle/Download?urlId=10.1117/1.3542038$$EPDF$$P50$$Gspie$$H</linktopdf><linktohtml>$$Uhttp://dx.doi.org/10.1117/1.3542038$$EHTML$$P50$$Gspie$$H</linktohtml><link.rule.ids>314,776,780,18944,27901,27902,55361,55362</link.rule.ids></links><search><creatorcontrib>Kwak, Sooyeong</creatorcontrib><creatorcontrib>Byun, Hyeran</creatorcontrib><title>Detection of dominant flow and abnormal events in surveillance video</title><title>Optical Engineering</title><description>We propose an algorithm for abnormal event detection in surveillance video. The proposed algorithm is based on a semi-unsupervised learning method, a kind of feature-based approach so that it does not detect the moving object individually. The proposed algorithm identifies dominant flow without individual object tracking using a latent Dirichlet allocation model in crowded environments. It can also automatically detect and localize an abnormally moving object in real-life video. The performance tests are taken with several real-life databases, and their results show that the proposed algorithm can efficiently detect abnormally moving objects in real time. The proposed algorithm can be applied to any situation in which abnormal directions or abnormal speeds are detected regardless of direction.</description><subject>Algorithms</subject><subject>Allocations</subject><subject>Dirichlet problem</subject><subject>Learning</subject><subject>Real time</subject><subject>Surveillance</subject><subject>Tracking</subject><issn>0091-3286</issn><issn>1560-2303</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><recordid>eNo9kE1LAzEQhoMoWKsH_0Fu4mHrTJLNZo-lrVUoVETPS7pJILKb1M224r93-4EDw8zh4eXlIeQeYYKIxRNOeC4YcHVBRphLyBgHfklGACVmnCl5TW5S-gIAVio1IvO57W3d-xhodNTE1gcdeuqa-EN1MFRvQuxa3VC7t6FP1Aeadt3e-qbRobZ0742Nt-TK6SbZu_Mdk8_nxcfsJVutl6-z6SqrOYg-c-AUoNsUiGIjjANlrZHaKFbK3Gk0UNqylELXtStyhNw5aYRGKYUAlIqPycMpd9vF751NfdX6VNtDFRt3qVKqFCCZEAP5eCLrLqbUWVdtO9_q7rdCqA6iKqzOogaWndi09fafW78tltP3wRPkcBwGrBj2-CP_A7jsZ-s</recordid><startdate>20110201</startdate><enddate>20110201</enddate><creator>Kwak, Sooyeong</creator><creator>Byun, Hyeran</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope></search><sort><creationdate>20110201</creationdate><title>Detection of dominant flow and abnormal events in surveillance video</title><author>Kwak, Sooyeong ; Byun, Hyeran</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Algorithms</topic><topic>Allocations</topic><topic>Dirichlet problem</topic><topic>Learning</topic><topic>Real time</topic><topic>Surveillance</topic><topic>Tracking</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kwak, Sooyeong</creatorcontrib><creatorcontrib>Byun, Hyeran</creatorcontrib><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Optical Engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kwak, Sooyeong</au><au>Byun, Hyeran</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detection of dominant flow and abnormal events in surveillance video</atitle><jtitle>Optical Engineering</jtitle><date>2011-02-01</date><risdate>2011</risdate><volume>50</volume><issue>2</issue><spage>027202</spage><epage>027202</epage><pages>027202-027202</pages><issn>0091-3286</issn><eissn>1560-2303</eissn><coden>OPEGAR</coden><abstract>We propose an algorithm for abnormal event detection in surveillance video. The proposed algorithm is based on a semi-unsupervised learning method, a kind of feature-based approach so that it does not detect the moving object individually. The proposed algorithm identifies dominant flow without individual object tracking using a latent Dirichlet allocation model in crowded environments. It can also automatically detect and localize an abnormally moving object in real-life video. The performance tests are taken with several real-life databases, and their results show that the proposed algorithm can efficiently detect abnormally moving objects in real time. The proposed algorithm can be applied to any situation in which abnormal directions or abnormal speeds are detected regardless of direction.</abstract><doi>10.1117/1.3542038</doi><tpages>1</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0091-3286
ispartof Optical Engineering, 2011-02, Vol.50 (2), p.027202-027202
issn 0091-3286
1560-2303
language eng
recordid cdi_proquest_miscellaneous_889406244
source SPIE Digital Library
subjects Algorithms
Allocations
Dirichlet problem
Learning
Real time
Surveillance
Tracking
title Detection of dominant flow and abnormal events in surveillance video
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T17%3A41%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Detection%20of%20dominant%20flow%20and%20abnormal%20events%20in%20surveillance%20video&rft.jtitle=Optical%20Engineering&rft.au=Kwak,%20Sooyeong&rft.date=2011-02-01&rft.volume=50&rft.issue=2&rft.spage=027202&rft.epage=027202&rft.pages=027202-027202&rft.issn=0091-3286&rft.eissn=1560-2303&rft.coden=OPEGAR&rft_id=info:doi/10.1117/1.3542038&rft_dat=%3Cproquest_cross%3E889406244%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c304t-f0f801fb7114b4df08eed6ad82965fa1d09e9964accf75105ff6d4a1664401683%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=889406244&rft_id=info:pmid/&rfr_iscdi=true