Kernel based articulated object tracking with scale adaptation and model update
Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and...
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 | 948 |
|---|---|
| container_issue | |
| container_start_page | 945 |
| container_title | |
| container_volume | |
| creator | Anbang Yao Guijin Wang Xinggang Lin Hao Wang |
| description | Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and target model update for articulated object tracking task. After predicating the object center with scale fixed KBOT, we extend scale selection theory to estimate the local optimal object scale. Once the object scale has been estimated, a kernel density estimation based strategy is developed to update the target model. Experimental results show that our approach is superior to traditional KBOT in the following two aspects: 1) it is less affected by the object scale change; 2) it is less prone to appearance variation. |
| doi_str_mv | 10.1109/ICASSP.2008.4517767 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4517767</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4517767</ieee_id><sourcerecordid>4517767</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-70382b21bc2683aa58c43268beb0f76b10e24f885798b76f30ad0090ba56c02f3</originalsourceid><addsrcrecordid>eNo1UNtKw0AUXG9grPmCvuwPpJ69ZXcfpXjDQoUq-FbObja6NU1CskX8ewPWeZmBYQZmCJkzWDAG9uZpebvZvCw4gFlIxbQu9Qm5YpJLyaSR9pRkXGhbMAvvZyS32vx7QpyTjCkORcmkvST5OO5gglRCWZWR9XMY2tBQh2OoKA4p-kODadKd2wWfaBrQf8X2g37H9ElHj02gWGGfMMWupdhWdN9VU8Ohr6bcNbmosRlDfuQZebu_e10-Fqv1w7RiVUSmVSo0CMMdZ87z0ghEZbwUk3TBQa1LxyBwWRujtDVOl7UArAAsOFSlB16LGZn_9cYQwrYf4h6Hn-3xG_ELUAFT5Q</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Kernel based articulated object tracking with scale adaptation and model update</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Anbang Yao ; Guijin Wang ; Xinggang Lin ; Hao Wang</creator><creatorcontrib>Anbang Yao ; Guijin Wang ; Xinggang Lin ; Hao Wang</creatorcontrib><description>Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and target model update for articulated object tracking task. After predicating the object center with scale fixed KBOT, we extend scale selection theory to estimate the local optimal object scale. Once the object scale has been estimated, a kernel density estimation based strategy is developed to update the target model. Experimental results show that our approach is superior to traditional KBOT in the following two aspects: 1) it is less affected by the object scale change; 2) it is less prone to appearance variation.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424414833</identifier><identifier>ISBN: 1424414830</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 1424414849</identifier><identifier>EISBN: 9781424414840</identifier><identifier>DOI: 10.1109/ICASSP.2008.4517767</identifier><language>eng</language><publisher>IEEE</publisher><subject>Adaptation model ; Articulated object ; Bandwidth ; Concurrent computing ; Convergence ; Extraterrestrial measurements ; Interleaved codes ; Kernel ; Kernel based object tracking ; Kernel density estimation ; Robustness ; Scale space ; Target tracking ; Video compression</subject><ispartof>2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.945-948</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/4517767$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4517767$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Anbang Yao</creatorcontrib><creatorcontrib>Guijin Wang</creatorcontrib><creatorcontrib>Xinggang Lin</creatorcontrib><creatorcontrib>Hao Wang</creatorcontrib><title>Kernel based articulated object tracking with scale adaptation and model update</title><title>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</title><addtitle>ICASSP</addtitle><description>Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and target model update for articulated object tracking task. After predicating the object center with scale fixed KBOT, we extend scale selection theory to estimate the local optimal object scale. Once the object scale has been estimated, a kernel density estimation based strategy is developed to update the target model. Experimental results show that our approach is superior to traditional KBOT in the following two aspects: 1) it is less affected by the object scale change; 2) it is less prone to appearance variation.</description><subject>Adaptation model</subject><subject>Articulated object</subject><subject>Bandwidth</subject><subject>Concurrent computing</subject><subject>Convergence</subject><subject>Extraterrestrial measurements</subject><subject>Interleaved codes</subject><subject>Kernel</subject><subject>Kernel based object tracking</subject><subject>Kernel density estimation</subject><subject>Robustness</subject><subject>Scale space</subject><subject>Target tracking</subject><subject>Video compression</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424414833</isbn><isbn>1424414830</isbn><isbn>1424414849</isbn><isbn>9781424414840</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1UNtKw0AUXG9grPmCvuwPpJ69ZXcfpXjDQoUq-FbObja6NU1CskX8ewPWeZmBYQZmCJkzWDAG9uZpebvZvCw4gFlIxbQu9Qm5YpJLyaSR9pRkXGhbMAvvZyS32vx7QpyTjCkORcmkvST5OO5gglRCWZWR9XMY2tBQh2OoKA4p-kODadKd2wWfaBrQf8X2g37H9ElHj02gWGGfMMWupdhWdN9VU8Ohr6bcNbmosRlDfuQZebu_e10-Fqv1w7RiVUSmVSo0CMMdZ87z0ghEZbwUk3TBQa1LxyBwWRujtDVOl7UArAAsOFSlB16LGZn_9cYQwrYf4h6Hn-3xG_ELUAFT5Q</recordid><startdate>200803</startdate><enddate>200803</enddate><creator>Anbang Yao</creator><creator>Guijin Wang</creator><creator>Xinggang Lin</creator><creator>Hao Wang</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200803</creationdate><title>Kernel based articulated object tracking with scale adaptation and model update</title><author>Anbang Yao ; Guijin Wang ; Xinggang Lin ; Hao Wang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-70382b21bc2683aa58c43268beb0f76b10e24f885798b76f30ad0090ba56c02f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Adaptation model</topic><topic>Articulated object</topic><topic>Bandwidth</topic><topic>Concurrent computing</topic><topic>Convergence</topic><topic>Extraterrestrial measurements</topic><topic>Interleaved codes</topic><topic>Kernel</topic><topic>Kernel based object tracking</topic><topic>Kernel density estimation</topic><topic>Robustness</topic><topic>Scale space</topic><topic>Target tracking</topic><topic>Video compression</topic><toplevel>online_resources</toplevel><creatorcontrib>Anbang Yao</creatorcontrib><creatorcontrib>Guijin Wang</creatorcontrib><creatorcontrib>Xinggang Lin</creatorcontrib><creatorcontrib>Hao Wang</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>Anbang Yao</au><au>Guijin Wang</au><au>Xinggang Lin</au><au>Hao Wang</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Kernel based articulated object tracking with scale adaptation and model update</atitle><btitle>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</btitle><stitle>ICASSP</stitle><date>2008-03</date><risdate>2008</risdate><spage>945</spage><epage>948</epage><pages>945-948</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424414833</isbn><isbn>1424414830</isbn><eisbn>1424414849</eisbn><eisbn>9781424414840</eisbn><abstract>Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and target model update for articulated object tracking task. After predicating the object center with scale fixed KBOT, we extend scale selection theory to estimate the local optimal object scale. Once the object scale has been estimated, a kernel density estimation based strategy is developed to update the target model. Experimental results show that our approach is superior to traditional KBOT in the following two aspects: 1) it is less affected by the object scale change; 2) it is less prone to appearance variation.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2008.4517767</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.945-948 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_4517767 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Adaptation model Articulated object Bandwidth Concurrent computing Convergence Extraterrestrial measurements Interleaved codes Kernel Kernel based object tracking Kernel density estimation Robustness Scale space Target tracking Video compression |
| title | Kernel based articulated object tracking with scale adaptation and model update |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T00%3A42%3A24IST&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=Kernel%20based%20articulated%20object%20tracking%20with%20scale%20adaptation%20and%20model%20update&rft.btitle=2008%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing&rft.au=Anbang%20Yao&rft.date=2008-03&rft.spage=945&rft.epage=948&rft.pages=945-948&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424414833&rft.isbn_list=1424414830&rft_id=info:doi/10.1109/ICASSP.2008.4517767&rft_dat=%3Cieee_6IE%3E4517767%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424414849&rft.eisbn_list=9781424414840&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4517767&rfr_iscdi=true |