<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<identifier>8JMKD3MGPBW34M/3JRJS95</identifier>
		<repository>sid.inpe.br/sibgrapi/2015/07.13.13.26</repository>
		<lastupdate>2015:07.13.13.26.54 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2015/07.13.13.26.54</metadatarepository>
		<metadatalastupdate>2016:06.03.21.18.36 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2015}</metadatalastupdate>
		<citationkey>AlmeidaVida:2015:ClNãEv</citationkey>
		<title>Classificação não-supervisionada de eventos em imagens de videomonitoramento baseada em altas frequências do fluxo ótico diferencial</title>
		<format>On-line</format>
		<year>2015</year>
		<numberoffiles>1</numberoffiles>
		<size>7321 KiB</size>
		<author>Almeida, Ana Paula Gonçalves S. de,</author>
		<author>Vidal, Flavio de Barros,</author>
		<affiliation>Programa de Pós-Graduação em Sistemas Mecatrônicos - Universidade de Brasília</affiliation>
		<affiliation>Departamento de Ciência da Computação - Universidade de Brasilia</affiliation>
		<editor>Rios, Ricardo Araujo,</editor>
		<editor>Paiva, Afonso,</editor>
		<e-mailaddress>fbvidal@unb.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)</conferencename>
		<conferencelocation>Salvador</conferencelocation>
		<date>Aug. 26-29, 2015</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Work in Progress</tertiarytype>
		<transferableflag>1</transferableflag>
		<keywords>event classification, motion analysis, optical flow.</keywords>
		<abstract>Events related to vandalism and violence often occur in crowded environments and mostly in unstructured environments (dynamic). The use of security cameras in crowd monitoring analysis for anomaly detection and alarms could be an efficient and inexpensive method. The goal of this paper is to build an unsupervised classification method to abnormal events that is robust and stable. The main idea is based on analysis of Fourier Transform's high-frequency spatial components features of optical flow, allowing the detection of abnormal acts in surveillance videos. Preliminary results show that the proposed methodology is capable of successfully execute the process of detection, permitting the development of an efficient recognition stage for future works.</abstract>
		<language>pt</language>
		<targetfile>sibgrapi-cameraready.pdf</targetfile>
		<usergroup>administrator</usergroup>
		<usergroup>fbvidal@unb.br</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPBW34M/3K24PF8</nexthigherunit>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2015/07.13.13.26</url>
	</metadata>
</metadatalist>