Real-time hand posture analysis based on neural network
In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 896 |
|---|---|
| container_issue | |
| container_start_page | 893 |
| container_title | |
| container_volume | |
| creator | Yang Shi Xiang Chen Kongqiao Wang Yikai Fang Lei Xu |
| description | In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable for real-time applications. With segmented hand area, the topology representation can be obtained based on neural network. The topology based representation of hand shape will further facilitate both fingertip localization and posture recognition. Experiments show the accuracy and the speed of our method can satisfy realtime requirements of interaction applications, even on mobile devices. |
| doi_str_mv | 10.1109/ICOSP.2010.5656041 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5656041</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5656041</ieee_id><sourcerecordid>5656041</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-22fbbb8c8b0ca9e07d18d173d1b907ef148f378b73783c985f9c5d0522e38c783</originalsourceid><addsrcrecordid>eNpVT81KAzEYjKhgqfsCeskLbM2XTTbJURZ_CoVKq-eSny-4ut0tmy3StzdgL85hhpnDMEPIHbAFADMPy2a9fVtwlr2sZc0EXJDCKA2CCyG1Mfryn1fiisw41KKUnMMNKVL6YhmSK27qGVEbtF05tXukn7YP9DCk6Tgitb3tTqlN1NmEgQ497fE42i7L9DOM37fkOtouYXHWOfl4fnpvXsvV-mXZPK7KFpScSs6jc0577Zi3BpkKoAOoKoAzTGEEoWOltFOZKm-0jMbLkNdxrLTP2Zzc__W2iLg7jO3ejqfd-Xr1C9u8Scg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Real-time hand posture analysis based on neural network</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yang Shi ; Xiang Chen ; Kongqiao Wang ; Yikai Fang ; Lei Xu</creator><creatorcontrib>Yang Shi ; Xiang Chen ; Kongqiao Wang ; Yikai Fang ; Lei Xu</creatorcontrib><description>In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable for real-time applications. With segmented hand area, the topology representation can be obtained based on neural network. The topology based representation of hand shape will further facilitate both fingertip localization and posture recognition. Experiments show the accuracy and the speed of our method can satisfy realtime requirements of interaction applications, even on mobile devices.</description><identifier>ISSN: 2164-5221</identifier><identifier>ISBN: 9781424458974</identifier><identifier>ISBN: 1424458978</identifier><identifier>EISBN: 9781424458998</identifier><identifier>EISBN: 9781424459001</identifier><identifier>EISBN: 1424459001</identifier><identifier>EISBN: 1424458994</identifier><identifier>DOI: 10.1109/ICOSP.2010.5656041</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial neural networks ; camera-projector system ; Gesture recognition ; hand posture recognition ; Network topology ; Neural Gas ; Real time systems ; Shape ; shape represention ; Topology ; Training</subject><ispartof>IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, 2010, p.893-896</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/5656041$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5656041$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yang Shi</creatorcontrib><creatorcontrib>Xiang Chen</creatorcontrib><creatorcontrib>Kongqiao Wang</creatorcontrib><creatorcontrib>Yikai Fang</creatorcontrib><creatorcontrib>Lei Xu</creatorcontrib><title>Real-time hand posture analysis based on neural network</title><title>IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS</title><addtitle>ICOSP</addtitle><description>In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable for real-time applications. With segmented hand area, the topology representation can be obtained based on neural network. The topology based representation of hand shape will further facilitate both fingertip localization and posture recognition. Experiments show the accuracy and the speed of our method can satisfy realtime requirements of interaction applications, even on mobile devices.</description><subject>Artificial neural networks</subject><subject>camera-projector system</subject><subject>Gesture recognition</subject><subject>hand posture recognition</subject><subject>Network topology</subject><subject>Neural Gas</subject><subject>Real time systems</subject><subject>Shape</subject><subject>shape represention</subject><subject>Topology</subject><subject>Training</subject><issn>2164-5221</issn><isbn>9781424458974</isbn><isbn>1424458978</isbn><isbn>9781424458998</isbn><isbn>9781424459001</isbn><isbn>1424459001</isbn><isbn>1424458994</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVT81KAzEYjKhgqfsCeskLbM2XTTbJURZ_CoVKq-eSny-4ut0tmy3StzdgL85hhpnDMEPIHbAFADMPy2a9fVtwlr2sZc0EXJDCKA2CCyG1Mfryn1fiisw41KKUnMMNKVL6YhmSK27qGVEbtF05tXukn7YP9DCk6Tgitb3tTqlN1NmEgQ497fE42i7L9DOM37fkOtouYXHWOfl4fnpvXsvV-mXZPK7KFpScSs6jc0577Zi3BpkKoAOoKoAzTGEEoWOltFOZKm-0jMbLkNdxrLTP2Zzc__W2iLg7jO3ejqfd-Xr1C9u8Scg</recordid><startdate>201010</startdate><enddate>201010</enddate><creator>Yang Shi</creator><creator>Xiang Chen</creator><creator>Kongqiao Wang</creator><creator>Yikai Fang</creator><creator>Lei Xu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201010</creationdate><title>Real-time hand posture analysis based on neural network</title><author>Yang Shi ; Xiang Chen ; Kongqiao Wang ; Yikai Fang ; Lei Xu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-22fbbb8c8b0ca9e07d18d173d1b907ef148f378b73783c985f9c5d0522e38c783</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Artificial neural networks</topic><topic>camera-projector system</topic><topic>Gesture recognition</topic><topic>hand posture recognition</topic><topic>Network topology</topic><topic>Neural Gas</topic><topic>Real time systems</topic><topic>Shape</topic><topic>shape represention</topic><topic>Topology</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Yang Shi</creatorcontrib><creatorcontrib>Xiang Chen</creatorcontrib><creatorcontrib>Kongqiao Wang</creatorcontrib><creatorcontrib>Yikai Fang</creatorcontrib><creatorcontrib>Lei Xu</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>Yang Shi</au><au>Xiang Chen</au><au>Kongqiao Wang</au><au>Yikai Fang</au><au>Lei Xu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Real-time hand posture analysis based on neural network</atitle><btitle>IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS</btitle><stitle>ICOSP</stitle><date>2010-10</date><risdate>2010</risdate><spage>893</spage><epage>896</epage><pages>893-896</pages><issn>2164-5221</issn><isbn>9781424458974</isbn><isbn>1424458978</isbn><eisbn>9781424458998</eisbn><eisbn>9781424459001</eisbn><eisbn>1424459001</eisbn><eisbn>1424458994</eisbn><abstract>In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable for real-time applications. With segmented hand area, the topology representation can be obtained based on neural network. The topology based representation of hand shape will further facilitate both fingertip localization and posture recognition. Experiments show the accuracy and the speed of our method can satisfy realtime requirements of interaction applications, even on mobile devices.</abstract><pub>IEEE</pub><doi>10.1109/ICOSP.2010.5656041</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2164-5221 |
| ispartof | IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, 2010, p.893-896 |
| issn | 2164-5221 |
| language | eng |
| recordid | cdi_ieee_primary_5656041 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Artificial neural networks camera-projector system Gesture recognition hand posture recognition Network topology Neural Gas Real time systems Shape shape represention Topology Training |
| title | Real-time hand posture analysis based on neural network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T06%3A33%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=Real-time%20hand%20posture%20analysis%20based%20on%20neural%20network&rft.btitle=IEEE%2010th%20INTERNATIONAL%20CONFERENCE%20ON%20SIGNAL%20PROCESSING%20PROCEEDINGS&rft.au=Yang%20Shi&rft.date=2010-10&rft.spage=893&rft.epage=896&rft.pages=893-896&rft.issn=2164-5221&rft.isbn=9781424458974&rft.isbn_list=1424458978&rft_id=info:doi/10.1109/ICOSP.2010.5656041&rft_dat=%3Cieee_6IE%3E5656041%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424458998&rft.eisbn_list=9781424459001&rft.eisbn_list=1424459001&rft.eisbn_list=1424458994&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5656041&rfr_iscdi=true |