Object Tracking by Structure Tensor Analysis
Covariance matrices have recently been a popular choice for versatile tasks like recognition and tracking due to their powerful properties as local descriptor and their low computational demands. This paper outlines similarities of covariance matrices to the well-known structure tensor. We show that...
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 | 2603 |
|---|---|
| container_issue | |
| container_start_page | 2600 |
| container_title | |
| container_volume | |
| creator | Donoser, M Kluckner, S Bischof, H |
| description | Covariance matrices have recently been a popular choice for versatile tasks like recognition and tracking due to their powerful properties as local descriptor and their low computational demands. This paper outlines similarities of covariance matrices to the well-known structure tensor. We show that the generalized version of the structure tensor is a powerful descriptor and that it can be calculated in constant time by exploiting the properties of integral images. To measure the similarities between several structure tensors, we describe an approximation scheme which allows comparison in a Euclidean space. Such an approach is also much more efficient than the common, computationally demanding Riemannian Manifold distances. Experimental evaluation proves the applicability for the task of object tracking demonstrating improved performance compared to covariance tracking. |
| doi_str_mv | 10.1109/ICPR.2010.637 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5595997</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5595997</ieee_id><sourcerecordid>5595997</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-a1261f45180e0bc00e76beb97374d8a3eee2113c22ee683146b03031aa71796f3</originalsourceid><addsrcrecordid>eNo1jktLxDAUheMLrGOXrtz0B5jx3jyb5VB8DAyMaPdDUm8lOlZJOov-ewvq6vBxDh-HsSuEJSK423Xz9LwUMKOR9oiVztaohFJWK1THrBC1RG5nPGEX_4UQp6xA0MiV0XjOypxjAGGssVrrgt1swzt1Y9Um333E4a0KU_UypkM3HhJVLQ35K1Wrwe-nHPMlO-v9PlP5lwvW3t-1zSPfbB_WzWrDo4ORexQGe6WxBoLQAZA1gYKz0qrX2ksiEoiyE4LIzJeVCSBBovcWrTO9XLDrX22cp7vvFD99mnZaO-1myQ_q7UUP</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Object Tracking by Structure Tensor Analysis</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Donoser, M ; Kluckner, S ; Bischof, H</creator><creatorcontrib>Donoser, M ; Kluckner, S ; Bischof, H</creatorcontrib><description>Covariance matrices have recently been a popular choice for versatile tasks like recognition and tracking due to their powerful properties as local descriptor and their low computational demands. This paper outlines similarities of covariance matrices to the well-known structure tensor. We show that the generalized version of the structure tensor is a powerful descriptor and that it can be calculated in constant time by exploiting the properties of integral images. To measure the similarities between several structure tensors, we describe an approximation scheme which allows comparison in a Euclidean space. Such an approach is also much more efficient than the common, computationally demanding Riemannian Manifold distances. Experimental evaluation proves the applicability for the task of object tracking demonstrating improved performance compared to covariance tracking.</description><identifier>ISSN: 1051-4651</identifier><identifier>ISBN: 1424475422</identifier><identifier>ISBN: 9781424475421</identifier><identifier>EISSN: 2831-7475</identifier><identifier>EISBN: 9781424475414</identifier><identifier>EISBN: 9780769541099</identifier><identifier>EISBN: 1424475414</identifier><identifier>EISBN: 0769541097</identifier><identifier>DOI: 10.1109/ICPR.2010.637</identifier><language>eng</language><publisher>IEEE</publisher><subject>Approximation methods ; Computer vision ; Covariance matrix ; Pattern recognition ; Pixel ; Structure Tensor ; Tensile stress ; Tracking ; Visualization</subject><ispartof>2010 20th International Conference on Pattern Recognition, 2010, p.2600-2603</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/5595997$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5595997$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Donoser, M</creatorcontrib><creatorcontrib>Kluckner, S</creatorcontrib><creatorcontrib>Bischof, H</creatorcontrib><title>Object Tracking by Structure Tensor Analysis</title><title>2010 20th International Conference on Pattern Recognition</title><addtitle>ICPR</addtitle><description>Covariance matrices have recently been a popular choice for versatile tasks like recognition and tracking due to their powerful properties as local descriptor and their low computational demands. This paper outlines similarities of covariance matrices to the well-known structure tensor. We show that the generalized version of the structure tensor is a powerful descriptor and that it can be calculated in constant time by exploiting the properties of integral images. To measure the similarities between several structure tensors, we describe an approximation scheme which allows comparison in a Euclidean space. Such an approach is also much more efficient than the common, computationally demanding Riemannian Manifold distances. Experimental evaluation proves the applicability for the task of object tracking demonstrating improved performance compared to covariance tracking.</description><subject>Approximation methods</subject><subject>Computer vision</subject><subject>Covariance matrix</subject><subject>Pattern recognition</subject><subject>Pixel</subject><subject>Structure Tensor</subject><subject>Tensile stress</subject><subject>Tracking</subject><subject>Visualization</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>1424475422</isbn><isbn>9781424475421</isbn><isbn>9781424475414</isbn><isbn>9780769541099</isbn><isbn>1424475414</isbn><isbn>0769541097</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1jktLxDAUheMLrGOXrtz0B5jx3jyb5VB8DAyMaPdDUm8lOlZJOov-ewvq6vBxDh-HsSuEJSK423Xz9LwUMKOR9oiVztaohFJWK1THrBC1RG5nPGEX_4UQp6xA0MiV0XjOypxjAGGssVrrgt1swzt1Y9Um333E4a0KU_UypkM3HhJVLQ35K1Wrwe-nHPMlO-v9PlP5lwvW3t-1zSPfbB_WzWrDo4ORexQGe6WxBoLQAZA1gYKz0qrX2ksiEoiyE4LIzJeVCSBBovcWrTO9XLDrX22cp7vvFD99mnZaO-1myQ_q7UUP</recordid><startdate>201008</startdate><enddate>201008</enddate><creator>Donoser, M</creator><creator>Kluckner, S</creator><creator>Bischof, H</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201008</creationdate><title>Object Tracking by Structure Tensor Analysis</title><author>Donoser, M ; Kluckner, S ; Bischof, H</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-a1261f45180e0bc00e76beb97374d8a3eee2113c22ee683146b03031aa71796f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Approximation methods</topic><topic>Computer vision</topic><topic>Covariance matrix</topic><topic>Pattern recognition</topic><topic>Pixel</topic><topic>Structure Tensor</topic><topic>Tensile stress</topic><topic>Tracking</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Donoser, M</creatorcontrib><creatorcontrib>Kluckner, S</creatorcontrib><creatorcontrib>Bischof, H</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>Donoser, M</au><au>Kluckner, S</au><au>Bischof, H</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Object Tracking by Structure Tensor Analysis</atitle><btitle>2010 20th International Conference on Pattern Recognition</btitle><stitle>ICPR</stitle><date>2010-08</date><risdate>2010</risdate><spage>2600</spage><epage>2603</epage><pages>2600-2603</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><isbn>1424475422</isbn><isbn>9781424475421</isbn><eisbn>9781424475414</eisbn><eisbn>9780769541099</eisbn><eisbn>1424475414</eisbn><eisbn>0769541097</eisbn><abstract>Covariance matrices have recently been a popular choice for versatile tasks like recognition and tracking due to their powerful properties as local descriptor and their low computational demands. This paper outlines similarities of covariance matrices to the well-known structure tensor. We show that the generalized version of the structure tensor is a powerful descriptor and that it can be calculated in constant time by exploiting the properties of integral images. To measure the similarities between several structure tensors, we describe an approximation scheme which allows comparison in a Euclidean space. Such an approach is also much more efficient than the common, computationally demanding Riemannian Manifold distances. Experimental evaluation proves the applicability for the task of object tracking demonstrating improved performance compared to covariance tracking.</abstract><pub>IEEE</pub><doi>10.1109/ICPR.2010.637</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-4651 |
| ispartof | 2010 20th International Conference on Pattern Recognition, 2010, p.2600-2603 |
| issn | 1051-4651 2831-7475 |
| language | eng |
| recordid | cdi_ieee_primary_5595997 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Approximation methods Computer vision Covariance matrix Pattern recognition Pixel Structure Tensor Tensile stress Tracking Visualization |
| title | Object Tracking by Structure Tensor Analysis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T04%3A55%3A47IST&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=Object%20Tracking%20by%20Structure%20Tensor%20Analysis&rft.btitle=2010%2020th%20International%20Conference%20on%20Pattern%20Recognition&rft.au=Donoser,%20M&rft.date=2010-08&rft.spage=2600&rft.epage=2603&rft.pages=2600-2603&rft.issn=1051-4651&rft.eissn=2831-7475&rft.isbn=1424475422&rft.isbn_list=9781424475421&rft_id=info:doi/10.1109/ICPR.2010.637&rft_dat=%3Cieee_6IE%3E5595997%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424475414&rft.eisbn_list=9780769541099&rft.eisbn_list=1424475414&rft.eisbn_list=0769541097&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5595997&rfr_iscdi=true |