Object detection via foreground contour feature selection and part-based shape model
In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape model from cluttered training images without need to explicitly given bounding box on objects. Our approach commences by extracting a set of fe...
Saved in:
Published in | Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) pp. 2524 - 2527 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.11.2012
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape model from cluttered training images without need to explicitly given bounding box on objects. Our approach commences by extracting a set of feature descriptors, and iteratively selects the foreground features using Earth Movers Distances based matching. This leads to a part-based shape model that can be used for object detection. Experimental results show that the proposed method has comparable performance with the state-of-the-art shape-based detection methods but with less requirements on the data at the training stage. |
---|---|
AbstractList | In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape model from cluttered training images without need to explicitly given bounding box on objects. Our approach commences by extracting a set of feature descriptors, and iteratively selects the foreground features using Earth Movers Distances based matching. This leads to a part-based shape model that can be used for object detection. Experimental results show that the proposed method has comparable performance with the state-of-the-art shape-based detection methods but with less requirements on the data at the training stage. |
Author | Cheng Jian Wang Junxiu Zhou Jun Zhang Huigang Zhao Huijie Bai Xiao |
Author_xml | – sequence: 1 surname: Zhang Huigang fullname: Zhang Huigang email: huigang2010@gmail.com – sequence: 2 surname: Wang Junxiu fullname: Wang Junxiu email: junxiuwang2008@163.com – sequence: 3 surname: Bai Xiao fullname: Bai Xiao email: baixiao.buaa@googlemail.com – sequence: 4 surname: Zhou Jun fullname: Zhou Jun email: junzhou.gary@gmail.com – sequence: 5 surname: Cheng Jian fullname: Cheng Jian email: jcheng@nlpr.ia.ac.cn – sequence: 6 surname: Zhao Huijie fullname: Zhao Huijie email: hjzhao@buaa.edu.cn |
BookMark | eNotj8tqwzAQRdU2hTppvqAb_YBBI40la1lCH4FANuk6yNKodXAsI9uF_n1Dm9VZnMuBu2SLPvV0w9bW1Git0Igg7C0rZK2gNGiquz8HqI2SEjQuWAGighJ1BQ9sOY4nIaRQVV2ww745kZ94oOmCNvX8u3U8pkyfOc194D71U5ozj-SmORMfqbsO3cUOLk9l40YKfPxyA_FzCtQ9svvoupHWV67Yx-vLYfNe7vZv283zrmzBVFMZEaS3YMlo0iJAaBCc0zEqsh69r8gaCLIhsNLLJuLlqq-DC16pBr1UK_b0322J6Djk9uzyz1GjFroG9Qug31Mn |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library Online IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Computer Science |
EISBN | 9784990644109 4990644107 |
EISSN | 2831-7475 |
EndPage | 2527 |
ExternalDocumentID | 6460681 |
Genre | orig-research |
GroupedDBID | 29J 6IE 6IF 6IK 6IL 6IN AAJGR ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IPLJI JC5 OCL RIE RIG RIL RNS |
ID | FETCH-LOGICAL-i175t-f412c919e76e60d1db41aa6ff3e9c4cc5e971d2be192c2bf4064c8dadc33b4c23 |
IEDL.DBID | RIE |
ISBN | 9781467322164 1467322164 |
ISSN | 1051-4651 |
IngestDate | Wed Jun 26 19:23:40 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i175t-f412c919e76e60d1db41aa6ff3e9c4cc5e971d2be192c2bf4064c8dadc33b4c23 |
PageCount | 4 |
ParticipantIDs | ieee_primary_6460681 |
PublicationCentury | 2000 |
PublicationDate | 2012-Nov. |
PublicationDateYYYYMMDD | 2012-11-01 |
PublicationDate_xml | – month: 11 year: 2012 text: 2012-Nov. |
PublicationDecade | 2010 |
PublicationTitle | Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) |
PublicationTitleAbbrev | ICPR |
PublicationYear | 2012 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0020358 ssj0001106415 |
Score | 1.9047925 |
Snippet | In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 2524 |
SubjectTerms | Computational modeling Context Educational institutions Feature extraction Object detection Shape Training |
Title | Object detection via foreground contour feature selection and part-based shape model |
URI | https://ieeexplore.ieee.org/document/6460681 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwED2VTrAU2iK-5YGRlMRxnGRGoAqpwNBK3Sp_XESFlFY0ZeDXc3bSFhADW5xEkeWcde-d790BXCNZrtJxShsJbSAiZYLMJdjQkPyR5KEyTpw8epLDiXicJtMW3Gy1MIjok89w4C79Wb5dmLULld1KQXDb6az3spDXWq1dPIW4jacGDdkK46SWwSXEkWQSeVGXTMl-iSBsaj1txj9aq3jP8tCB0WZOdULJ22Bd6YH5_FWu8b-TPoT-TsPHXrbe6QhaWHahs2niwJo93YWDbxUJezB-1i4wwyxWPkerZB9zxQjYopN_lJa51HYyP1agrwjKVr6PjntR0dMlGWLgHKNlq1e1ROYb7fRh8nA_vhsGTeOFYE5oogoKEXGTRzmmEmVoI6vpJypZFDHmRhiTYJ5GlmskeGi4LggUCJNZZU0ca2F4fAztclHiCTBDDIxnUUGf0SLNkjw0OUFOmyeua1IsTqHnlmy2rGtrzJrVOvv79jnsE2DhtRbwAtrV-xovCRRU-spbwxf5ObOU |
link.rule.ids | 310,311,786,790,795,796,802,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8JAEJ4QPKgXFDC-3YNHi31sX2cjQQX0AAk3so9pJCaFSPHgr3d2W0CNB2_dtmk229nM983ONwNwjWS5QgYxbSTUDveEchKTYEND8keR7wplxMmDYdQb88dJOKnBzUYLg4g2-Qw75tKe5eu5WplQ2W3ECW4bnfUO-Xk3LtVa24gKsRtLDiq65QZhKYQLiSVFoWdlXVFMFkwUYV3taT3-0VzF-pZuAwbrWZUpJW-dVSE76vNXwcb_TvsA2lsVH3vZ-KdDqGHehMa6jQOrdnUT9r_VJGzB6Fma0AzTWNgsrZx9zAQjaItGAJJrZpLbyQBZhrYmKFvaTjrmRUFPF2SKjnGNmi1fxQKZbbXThnH3fnTXc6rWC86M8EThZNzzVeqlGEcYudrTkn6jiLIswFRxpUJMY0_7EgkgKl9mBAu4SrTQKggkV35wBPV8nuMxMEUczE-8jD4jeZyEqatSAp06DU3fpICfQMss2XRRVteYVqt1-vftK9jtjQb9af9h-HQGewRf_FIZeA714n2FFwQRCnlpLeMLoKa26A |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+21st+International+Conference+on+Pattern+Recognition+%28ICPR2012%29&rft.atitle=Object+detection+via+foreground+contour+feature+selection+and+part-based+shape+model&rft.au=Zhang+Huigang&rft.au=Wang+Junxiu&rft.au=Bai+Xiao&rft.au=Zhou+Jun&rft.date=2012-11-01&rft.pub=IEEE&rft.isbn=9781467322164&rft.issn=1051-4651&rft.eissn=2831-7475&rft.spage=2524&rft.epage=2527&rft.externalDocID=6460681 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-4651&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-4651&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-4651&client=summon |