Evaluation of features detectors and descriptors based on 3D objects
We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collec...
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 | 807 Vol. 1 |
|---|---|
| container_issue | |
| container_start_page | 800 |
| container_title | |
| container_volume | 1 |
| creator | Moreels, P. Perona, P. |
| description | We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30/spl deg/. |
| doi_str_mv | 10.1109/ICCV.2005.89 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1541335</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1541335</ieee_id><sourcerecordid>1541335</sourcerecordid><originalsourceid>FETCH-LOGICAL-i213t-797bfe885c39ac7d21847514c1e551c8bf218667068a2fad50e1527cd2e0d3cf3</originalsourceid><addsrcrecordid>eNotjM1KAzEURoM_4LS6c-cmLzD1JnfuJFnKtGqh4EbFXckkNzCldspkKvj2Durq43wcjhC3ChZKgbtfN837QgPQwrozUWi0UBqC6lzMwNSONGL1cSEKRQQlVc5diVnOOwB02taFWK6-_P7kx64_yD7JxH48DZxl5JHD2A9Z-kOcKIehO_5y6zNHOem4lH27m6x8LS6T32e--d-5eHtcvTbP5eblad08bMpOKxxL40yb2FoK6HwwUStbGVJVUEykgm3T9NS1gdp6nXwkYEXahKgZIoaEc3H31-2YeXscuk8_fG8VVQqR8AeIfkr4</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Evaluation of features detectors and descriptors based on 3D objects</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Moreels, P. ; Perona, P.</creator><creatorcontrib>Moreels, P. ; Perona, P.</creatorcontrib><description>We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30/spl deg/.</description><identifier>ISSN: 1550-5499</identifier><identifier>ISBN: 076952334X</identifier><identifier>ISBN: 9780769523347</identifier><identifier>EISSN: 2380-7504</identifier><identifier>DOI: 10.1109/ICCV.2005.89</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computer vision ; Detectors ; Frequency ; Layout ; Object detection ; Object recognition ; Robustness ; Shape ; Simultaneous localization and mapping ; Stereo vision</subject><ispartof>Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005, Vol.1, p.800-807 Vol. 1</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1541335$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1541335$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Moreels, P.</creatorcontrib><creatorcontrib>Perona, P.</creatorcontrib><title>Evaluation of features detectors and descriptors based on 3D objects</title><title>Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1</title><addtitle>ICCV</addtitle><description>We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30/spl deg/.</description><subject>Computer vision</subject><subject>Detectors</subject><subject>Frequency</subject><subject>Layout</subject><subject>Object detection</subject><subject>Object recognition</subject><subject>Robustness</subject><subject>Shape</subject><subject>Simultaneous localization and mapping</subject><subject>Stereo vision</subject><issn>1550-5499</issn><issn>2380-7504</issn><isbn>076952334X</isbn><isbn>9780769523347</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotjM1KAzEURoM_4LS6c-cmLzD1JnfuJFnKtGqh4EbFXckkNzCldspkKvj2Durq43wcjhC3ChZKgbtfN837QgPQwrozUWi0UBqC6lzMwNSONGL1cSEKRQQlVc5diVnOOwB02taFWK6-_P7kx64_yD7JxH48DZxl5JHD2A9Z-kOcKIehO_5y6zNHOem4lH27m6x8LS6T32e--d-5eHtcvTbP5eblad08bMpOKxxL40yb2FoK6HwwUStbGVJVUEykgm3T9NS1gdp6nXwkYEXahKgZIoaEc3H31-2YeXscuk8_fG8VVQqR8AeIfkr4</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Moreels, P.</creator><creator>Perona, P.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2005</creationdate><title>Evaluation of features detectors and descriptors based on 3D objects</title><author>Moreels, P. ; Perona, P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i213t-797bfe885c39ac7d21847514c1e551c8bf218667068a2fad50e1527cd2e0d3cf3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Computer vision</topic><topic>Detectors</topic><topic>Frequency</topic><topic>Layout</topic><topic>Object detection</topic><topic>Object recognition</topic><topic>Robustness</topic><topic>Shape</topic><topic>Simultaneous localization and mapping</topic><topic>Stereo vision</topic><toplevel>online_resources</toplevel><creatorcontrib>Moreels, P.</creatorcontrib><creatorcontrib>Perona, P.</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>Moreels, P.</au><au>Perona, P.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Evaluation of features detectors and descriptors based on 3D objects</atitle><btitle>Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1</btitle><stitle>ICCV</stitle><date>2005</date><risdate>2005</risdate><volume>1</volume><spage>800</spage><epage>807 Vol. 1</epage><pages>800-807 Vol. 1</pages><issn>1550-5499</issn><eissn>2380-7504</eissn><isbn>076952334X</isbn><isbn>9780769523347</isbn><abstract>We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30/spl deg/.</abstract><pub>IEEE</pub><doi>10.1109/ICCV.2005.89</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1550-5499 |
| ispartof | Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005, Vol.1, p.800-807 Vol. 1 |
| issn | 1550-5499 2380-7504 |
| language | eng |
| recordid | cdi_ieee_primary_1541335 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computer vision Detectors Frequency Layout Object detection Object recognition Robustness Shape Simultaneous localization and mapping Stereo vision |
| title | Evaluation of features detectors and descriptors based on 3D objects |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T02%3A38%3A29IST&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=Evaluation%20of%20features%20detectors%20and%20descriptors%20based%20on%203D%20objects&rft.btitle=Tenth%20IEEE%20International%20Conference%20on%20Computer%20Vision%20(ICCV'05)%20Volume%201&rft.au=Moreels,%20P.&rft.date=2005&rft.volume=1&rft.spage=800&rft.epage=807%20Vol.%201&rft.pages=800-807%20Vol.%201&rft.issn=1550-5499&rft.eissn=2380-7504&rft.isbn=076952334X&rft.isbn_list=9780769523347&rft_id=info:doi/10.1109/ICCV.2005.89&rft_dat=%3Cieee_6IE%3E1541335%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=1541335&rfr_iscdi=true |