A group sparsity-driven approach to 3-D action recognition

A group sparsity-driven approach to 3-D action recognition

In this paper, a novel 3-D action recognition method based on sparse representation is presented. Silhouette images from multiple cameras are combined to obtain motion history volumes (MHVs). Cylindrical Fourier transform of MHVs is used as action descriptors. We assume that a test sample has a spar...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cosar, S., Cetin, M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Accuracy
Cameras
History
Noise
Principal component analysis
Strontium
Training
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1911
container_issue
container_start_page 1904
container_title
container_volume
creator Cosar, S.
Cetin, M.
description In this paper, a novel 3-D action recognition method based on sparse representation is presented. Silhouette images from multiple cameras are combined to obtain motion history volumes (MHVs). Cylindrical Fourier transform of MHVs is used as action descriptors. We assume that a test sample has a sparse representation in the space of training samples. We cast the action classification problem as an optimization problem and classify actions using group sparsity based on l 1 regularization. We show experimental results using the IXMAS multi-view database and demonstrate the superiority of our method, especially when observations are low resolution, occluded, and noisy and when the feature dimension is reduced.
doi_str_mv 10.1109/ICCVW.2011.6130481
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6130481</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6130481</ieee_id><sourcerecordid>6130481</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-1820c5b3a8bb54de8d5f048ebe8ac538ff87643575c3135cb7ef65d0f3309d173</originalsourceid><addsrcrecordid>eNpFj81OwzAQhI0QElD6AnDxCyTsZuOfcKsChUqVuFRwrBzHLkaQWHZA6ttTRCXmMvNdRjOMXSOUiNDcrtr25bWsALGUSFBrPGGXWEtFABLl6T9U9Tmb5_wOB0mpGwkX7G7Bd2n8ijxHk3KY9kWfwrcbuIkxjca-8WnkVNxzY6cwDjw5O-6G8Juv2Jk3H9nNjz5jm-XDpn0q1s-Pq3axLkIDU4G6Ais6MrrrRN073Qt_GOk6p40VpL3XStYklLCEJGynnJeiB08ETY-KZuzmrzY457YxhU-T9tvjVfoB2hlHIg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A group sparsity-driven approach to 3-D action recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Cosar, S. ; Cetin, M.</creator><creatorcontrib>Cosar, S. ; Cetin, M.</creatorcontrib><description>In this paper, a novel 3-D action recognition method based on sparse representation is presented. Silhouette images from multiple cameras are combined to obtain motion history volumes (MHVs). Cylindrical Fourier transform of MHVs is used as action descriptors. We assume that a test sample has a sparse representation in the space of training samples. We cast the action classification problem as an optimization problem and classify actions using group sparsity based on l 1 regularization. We show experimental results using the IXMAS multi-view database and demonstrate the superiority of our method, especially when observations are low resolution, occluded, and noisy and when the feature dimension is reduced.</description><identifier>ISBN: 1467300624</identifier><identifier>ISBN: 9781467300629</identifier><identifier>EISBN: 1467300616</identifier><identifier>EISBN: 9781467300612</identifier><identifier>EISBN: 1467300632</identifier><identifier>EISBN: 9781467300636</identifier><identifier>DOI: 10.1109/ICCVW.2011.6130481</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Cameras ; History ; Noise ; Principal component analysis ; Strontium ; Training</subject><ispartof>2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011, p.1904-1911</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/6130481$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6130481$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Cosar, S.</creatorcontrib><creatorcontrib>Cetin, M.</creatorcontrib><title>A group sparsity-driven approach to 3-D action recognition</title><title>2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)</title><addtitle>ICCVW</addtitle><description>In this paper, a novel 3-D action recognition method based on sparse representation is presented. Silhouette images from multiple cameras are combined to obtain motion history volumes (MHVs). Cylindrical Fourier transform of MHVs is used as action descriptors. We assume that a test sample has a sparse representation in the space of training samples. We cast the action classification problem as an optimization problem and classify actions using group sparsity based on l 1 regularization. We show experimental results using the IXMAS multi-view database and demonstrate the superiority of our method, especially when observations are low resolution, occluded, and noisy and when the feature dimension is reduced.</description><subject>Accuracy</subject><subject>Cameras</subject><subject>History</subject><subject>Noise</subject><subject>Principal component analysis</subject><subject>Strontium</subject><subject>Training</subject><isbn>1467300624</isbn><isbn>9781467300629</isbn><isbn>1467300616</isbn><isbn>9781467300612</isbn><isbn>1467300632</isbn><isbn>9781467300636</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFj81OwzAQhI0QElD6AnDxCyTsZuOfcKsChUqVuFRwrBzHLkaQWHZA6ttTRCXmMvNdRjOMXSOUiNDcrtr25bWsALGUSFBrPGGXWEtFABLl6T9U9Tmb5_wOB0mpGwkX7G7Bd2n8ijxHk3KY9kWfwrcbuIkxjca-8WnkVNxzY6cwDjw5O-6G8Juv2Jk3H9nNjz5jm-XDpn0q1s-Pq3axLkIDU4G6Ais6MrrrRN073Qt_GOk6p40VpL3XStYklLCEJGynnJeiB08ETY-KZuzmrzY457YxhU-T9tvjVfoB2hlHIg</recordid><startdate>201111</startdate><enddate>201111</enddate><creator>Cosar, S.</creator><creator>Cetin, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201111</creationdate><title>A group sparsity-driven approach to 3-D action recognition</title><author>Cosar, S. ; Cetin, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-1820c5b3a8bb54de8d5f048ebe8ac538ff87643575c3135cb7ef65d0f3309d173</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Accuracy</topic><topic>Cameras</topic><topic>History</topic><topic>Noise</topic><topic>Principal component analysis</topic><topic>Strontium</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Cosar, S.</creatorcontrib><creatorcontrib>Cetin, M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cosar, S.</au><au>Cetin, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A group sparsity-driven approach to 3-D action recognition</atitle><btitle>2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)</btitle><stitle>ICCVW</stitle><date>2011-11</date><risdate>2011</risdate><spage>1904</spage><epage>1911</epage><pages>1904-1911</pages><isbn>1467300624</isbn><isbn>9781467300629</isbn><eisbn>1467300616</eisbn><eisbn>9781467300612</eisbn><eisbn>1467300632</eisbn><eisbn>9781467300636</eisbn><abstract>In this paper, a novel 3-D action recognition method based on sparse representation is presented. Silhouette images from multiple cameras are combined to obtain motion history volumes (MHVs). Cylindrical Fourier transform of MHVs is used as action descriptors. We assume that a test sample has a sparse representation in the space of training samples. We cast the action classification problem as an optimization problem and classify actions using group sparsity based on l 1 regularization. We show experimental results using the IXMAS multi-view database and demonstrate the superiority of our method, especially when observations are low resolution, occluded, and noisy and when the feature dimension is reduced.</abstract><pub>IEEE</pub><doi>10.1109/ICCVW.2011.6130481</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1467300624
ispartof 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011, p.1904-1911
issn
language eng
recordid cdi_ieee_primary_6130481
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Accuracy
Cameras
History
Noise
Principal component analysis
Strontium
Training
title A group sparsity-driven approach to 3-D action recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T16%3A10%3A48IST&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=A%20group%20sparsity-driven%20approach%20to%203-D%20action%20recognition&rft.btitle=2011%20IEEE%20International%20Conference%20on%20Computer%20Vision%20Workshops%20(ICCV%20Workshops)&rft.au=Cosar,%20S.&rft.date=2011-11&rft.spage=1904&rft.epage=1911&rft.pages=1904-1911&rft.isbn=1467300624&rft.isbn_list=9781467300629&rft_id=info:doi/10.1109/ICCVW.2011.6130481&rft_dat=%3Cieee_6IE%3E6130481%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467300616&rft.eisbn_list=9781467300612&rft.eisbn_list=1467300632&rft.eisbn_list=9781467300636&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6130481&rfr_iscdi=true