Classifying Human Dynamics Without Contact Forces

We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statistics are extracted from the images, and we use them to infer a dynamical system that explicitly models contact forces. We...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Bissacco, A., Soatto, S.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Character recognition Computer science Displays Humans Image recognition Linear systems Motion analysis Power system modeling Statistics System identification
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	1685
container_issue
container_start_page	1678
container_title
container_volume	2
creator	Bissacco, A. Soatto, S.
description	We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statistics are extracted from the images, and we use them to infer a dynamical system that explicitly models contact forces. We then develop a distance between such models that explicitly factors out exogenous inputs that are not unique to an individual or her gait. We show that such a distance is more discriminative than the distance between simple linear systems, where most of the energy is devoted to modeling the dynamics of spurious nuisances such as contact forces.
doi_str_mv	10.1109/CVPR.2006.75
format	Conference Proceeding
fullrecord	<record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1640957</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1640957</ieee_id><sourcerecordid>1640957</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-922be2de12dfbc39f9e9edd3f61219163ec04a842f2256cd2c6ac98477953b2f3</originalsourceid><addsrcrecordid>eNotzM1KxDAUQOGACg5jd-7c9AVac2_-epcSHUcYUGTQ5ZCmiUamrTSdRd9eQc_m2x3GroHXAJxu7dvLa42c69qoM1aQabjRpFCR0edsBVyLShPQJSty_uK_SSUF8hUDe3Q5p7ik4aPcnno3lPfL4Prkc_me5s_xNJd2HGbn53IzTj7kK3YR3TGH4t81228e9nZb7Z4fn-zdrkrE54oQ24BdAOxi6wVFChS6TkQNCARaBM-layRGRKV9h147T400hpRoMYo1u_nbphDC4XtKvZuWA2jJSRnxA3YuQ44</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Classifying Human Dynamics Without Contact Forces</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Bissacco, A. ; Soatto, S.</creator><creatorcontrib>Bissacco, A. ; Soatto, S.</creatorcontrib><description>We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statistics are extracted from the images, and we use them to infer a dynamical system that explicitly models contact forces. We then develop a distance between such models that explicitly factors out exogenous inputs that are not unique to an individual or her gait. We show that such a distance is more discriminative than the distance between simple linear systems, where most of the energy is devoted to modeling the dynamics of spurious nuisances such as contact forces.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 9780769525976</identifier><identifier>ISBN: 0769525970</identifier><identifier>DOI: 10.1109/CVPR.2006.75</identifier><language>eng</language><publisher>IEEE</publisher><subject>Character recognition ; Computer science ; Displays ; Humans ; Image recognition ; Linear systems ; Motion analysis ; Power system modeling ; Statistics ; System identification</subject><ispartof>2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), 2006, Vol.2, p.1678-1685</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1640957$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1640957$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Bissacco, A.</creatorcontrib><creatorcontrib>Soatto, S.</creatorcontrib><title>Classifying Human Dynamics Without Contact Forces</title><title>2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)</title><addtitle>CVPR</addtitle><description>We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statistics are extracted from the images, and we use them to infer a dynamical system that explicitly models contact forces. We then develop a distance between such models that explicitly factors out exogenous inputs that are not unique to an individual or her gait. We show that such a distance is more discriminative than the distance between simple linear systems, where most of the energy is devoted to modeling the dynamics of spurious nuisances such as contact forces.</description><subject>Character recognition</subject><subject>Computer science</subject><subject>Displays</subject><subject>Humans</subject><subject>Image recognition</subject><subject>Linear systems</subject><subject>Motion analysis</subject><subject>Power system modeling</subject><subject>Statistics</subject><subject>System identification</subject><issn>1063-6919</issn><isbn>9780769525976</isbn><isbn>0769525970</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotzM1KxDAUQOGACg5jd-7c9AVac2_-epcSHUcYUGTQ5ZCmiUamrTSdRd9eQc_m2x3GroHXAJxu7dvLa42c69qoM1aQabjRpFCR0edsBVyLShPQJSty_uK_SSUF8hUDe3Q5p7ik4aPcnno3lPfL4Prkc_me5s_xNJd2HGbn53IzTj7kK3YR3TGH4t81228e9nZb7Z4fn-zdrkrE54oQ24BdAOxi6wVFChS6TkQNCARaBM-layRGRKV9h147T400hpRoMYo1u_nbphDC4XtKvZuWA2jJSRnxA3YuQ44</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Bissacco, A.</creator><creator>Soatto, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2006</creationdate><title>Classifying Human Dynamics Without Contact Forces</title><author>Bissacco, A. ; Soatto, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-922be2de12dfbc39f9e9edd3f61219163ec04a842f2256cd2c6ac98477953b2f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Character recognition</topic><topic>Computer science</topic><topic>Displays</topic><topic>Humans</topic><topic>Image recognition</topic><topic>Linear systems</topic><topic>Motion analysis</topic><topic>Power system modeling</topic><topic>Statistics</topic><topic>System identification</topic><toplevel>online_resources</toplevel><creatorcontrib>Bissacco, A.</creatorcontrib><creatorcontrib>Soatto, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bissacco, A.</au><au>Soatto, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Classifying Human Dynamics Without Contact Forces</atitle><btitle>2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)</btitle><stitle>CVPR</stitle><date>2006</date><risdate>2006</risdate><volume>2</volume><spage>1678</spage><epage>1685</epage><pages>1678-1685</pages><issn>1063-6919</issn><isbn>9780769525976</isbn><isbn>0769525970</isbn><abstract>We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statistics are extracted from the images, and we use them to infer a dynamical system that explicitly models contact forces. We then develop a distance between such models that explicitly factors out exogenous inputs that are not unique to an individual or her gait. We show that such a distance is more discriminative than the distance between simple linear systems, where most of the energy is devoted to modeling the dynamics of spurious nuisances such as contact forces.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.2006.75</doi><tpages>8</tpages></addata></record>
fulltext	fulltext_linktorsrc
identifier	ISSN: 1063-6919
ispartof	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), 2006, Vol.2, p.1678-1685
issn	1063-6919
language	eng
recordid	cdi_ieee_primary_1640957
source	IEEE Electronic Library (IEL) Conference Proceedings
subjects	Character recognition Computer science Displays Humans Image recognition Linear systems Motion analysis Power system modeling Statistics System identification
title	Classifying Human Dynamics Without Contact Forces
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T22%3A06%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Classifying%20Human%20Dynamics%20Without%20Contact%20Forces&rft.btitle=2006%20IEEE%20Computer%20Society%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20(CVPR'06)&rft.au=Bissacco,%20A.&rft.date=2006&rft.volume=2&rft.spage=1678&rft.epage=1685&rft.pages=1678-1685&rft.issn=1063-6919&rft.isbn=9780769525976&rft.isbn_list=0769525970&rft_id=info:doi/10.1109/CVPR.2006.75&rft_dat=%3Cieee_6IE%3E1640957%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1640957&rfr_iscdi=true