Tracking-by-Detection of 3D Human Shapes: From Surfaces to Volumes

3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences....

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 40; číslo 8; s. 1994 - 2008
Hlavní autoři:	Huang, Chun-Hao Paul, Allain, Benjamin, Boyer, Edmond, Franco, Jean-Sebastien, Tombari, Federico, Navab, Nassir, Ilic, Slobodan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.08.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Témata:	3D tracking-by-detection centroidal Voronoi tessellation Computer Science Computer Vision and Pattern Recognition Data models Deformable models Deformation discriminative associations Iterative closest point algorithm Iterative methods random forest Robustness Shape Shape memory Shape recognition Shape tracking Stability analysis State of the art Surface reconstruction Tessellation Three-dimensional displays Tracking Tracking errors Visual observation 3D tracking-by-detection centroidal Voronoi tessellation random forest Shape tracking discriminative associations
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.
AbstractList	3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as ‘tracking-bydetection of 3D human shapes.’ It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art. 3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art. 3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art. 3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate overtime. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as `tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking overtime. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.
Author	Allain, Benjamin Boyer, Edmond Tombari, Federico Franco, Jean-Sebastien Navab, Nassir Ilic, Slobodan Huang, Chun-Hao Paul
Author_xml	– sequence: 1 givenname: Chun-Hao Paul orcidid: 0000-0002-1268-6527 surname: Huang fullname: Huang, Chun-Hao Paul email: paulchhuang1109@gmail.com organization: Computer Aided Medical Procedures, Technische Universität München, München, Germany – sequence: 2 givenname: Benjamin surname: Allain fullname: Allain, Benjamin email: benjaminallain@hotmail.com organization: Inria, LJK, Grenoble, France – sequence: 3 givenname: Edmond surname: Boyer fullname: Boyer, Edmond email: edmond.boyer@inrialpes.fr organization: Inria, LJK, Grenoble, France – sequence: 4 givenname: Jean-Sebastien surname: Franco fullname: Franco, Jean-Sebastien email: jean-sebastien.franco@inria.fr organization: Inria, LJK, Grenoble, France – sequence: 5 givenname: Federico surname: Tombari fullname: Tombari, Federico email: federico.tombari@unibo.it organization: Computer Aided Medical Procedures, Technische Universität München, München, Germany – sequence: 6 givenname: Nassir surname: Navab fullname: Navab, Nassir email: navab@cs.tum.edu organization: Computer Aided Medical Procedures, Technische Universität München, München, Germany – sequence: 7 givenname: Slobodan surname: Ilic fullname: Ilic, Slobodan email: Slobodan.Ilic@in.tum.de organization: Siemens AG, Munich, Germany
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/28816656$$D View this record in MEDLINE/PubMed https://inria.hal.science/hal-01588272$$DView record in HAL
BookMark	eNp9kU1v1DAQhi3Uim4LfwAkFIkLHLKMPxLbvS0tZSttBVIXrpbXGdOUJF7sBKn_noTd7qGHniyNn3fG4-eUHHWhQ0LeUJhTCvrT-vvi5nrOgMo5kwI4qBdkxmgJuWaaHZEZ0JLlSjF1Qk5TugegogD-kpwwpWhZFuWMfF5H637X3a9885BfYo-ur0OXBZ_xy2w5tLbLbu_sFtN5dhVDm90O0VuHKetD9jM0Q4vpFTn2tkn4en-ekR9XX9YXy3z17ev1xWKVO8F0n6P0hfYVU-gloKw4Q-W9tbKqxPhEbzdMeqRM0o1klQNQkjtVOq5kVWhZ8jPycdf3zjZmG-vWxgcTbG2Wi5WZakCLcVnJ_tKR_bBjtzH8GTD1pq2Tw6axHYYhGao5CEW1FiP6_gl6H4bYjZsYRqUQUotiot7tqWHTYnWY__iTI8B2gIshpYj-gFAwky7zX5eZdJm9rjGknoRc3dvJQB9t3TwffbuL1oh4mKWAjneK_wN6Up7O
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_cviu_2020_103072 crossref_primary_10_1016_j_cag_2021_10_015 crossref_primary_10_1016_j_cag_2024_103943 crossref_primary_10_1016_j_cviu_2021_103275
Cites_doi	10.1145/2366145.2366207 10.1109/CVPR.2016.419 10.5244/C.27.4 10.1145/1057432.1057456 10.1109/CVPR.2012.6247664 10.1109/CVPR.2015.7298941 10.1007/978-3-642-33718-5_52 10.1109/ROBOT.1991.132043 10.1109/CVPR.2014.440 10.1145/344779.344862 10.1109/3DV.2013.45 10.1109/CVPR.2015.7299029 10.1109/34.121791 10.1109/ICCVW.2011.6130444 10.1145/2897824.2925969 10.1016/0262-8856(92)90066-C 10.1145/1015706.1015736 10.1109/ICCV.2007.4409108 10.1145/1360612.1360696 10.1145/1198555.1198747 10.1145/1618452.1618521 10.1162/neco.1989.1.4.541 10.1109/CVPR.2011.5995316 10.1007/s11263-015-0832-y 10.1007/978-3-642-15558-1_26 10.1111/cgf.12716 10.1007/978-1-4471-4929-3 10.1007/s11263-012-0528-5 10.1109/3DIMPVT.2012.51 10.1137/S0036144599352836 10.1109/CVPR.2014.532 10.1007/978-3-642-18421-5_11 10.1109/TPAMI.2008.104 10.1109/3DV.2015.49 10.1007/s11263-015-0824-y 10.1007/s11263-012-0549-0 10.1007/978-3-642-33765-9_53 10.1109/3DIMPVT.2012.29 10.1109/TPAMI.2016.2557783 10.1109/ICCV.2011.6126503 10.1109/CVPR.2014.491 10.1007/s11263-009-0296-z 10.1145/2601097.2601165 10.1016/j.cviu.2006.08.002 10.1111/j.1467-8659.2009.01515.x 10.1109/ICCV.2015.236 10.1007/978-3-319-46487-9_11 10.1109/CVPR.2010.5539838 10.1109/TPAMI.2010.223 10.1145/2766945 10.1109/34.1000236 10.1109/TPAMI.2013.47 10.1023/B:VISI.0000013087.49260.fb 10.1145/1276377.1276467 10.1109/CVPR.2016.171 10.1111/j.2517-6161.1977.tb01600.x 10.1109/CVPR.2015.7298623 10.1109/ISMAR.2011.6092378 10.1023/A:1007981719186 10.1007/s11263-009-0284-3 10.1145/1399504.1360697
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 1XC VOOES
DOI	10.1109/TPAMI.2017.2740308
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	PubMed MEDLINE - Academic Technology Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	2008
ExternalDocumentID	oai:HAL:hal-01588272v1 28816656 10_1109_TPAMI_2017_2740308 8010838
Genre	orig-research Journal Article
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 5VS 9M8 AAYOK ABFSI ADRHT AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM PKN RIC RIG RNI RZB VH1 XJT Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 1XC VOOES
ID	FETCH-LOGICAL-c429t-e7f59fd28ef70e7d32e8ffaa7dd4828fab27fe1271b72dc00873c86c387d59763
IEDL.DBID	RIE
ISICitedReferencesCount	7
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000437271100015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Tue Oct 14 20:50:46 EDT 2025 Wed Oct 01 14:43:52 EDT 2025 Sun Jun 29 12:38:02 EDT 2025 Wed Feb 19 02:31:47 EST 2025 Sat Nov 29 05:15:58 EST 2025 Tue Nov 18 22:11:38 EST 2025 Wed Aug 27 02:47:52 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	8
Keywords	3D tracking-by-detection centroidal Voronoi tessellation random forest Shape tracking discriminative associations
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c429t-e7f59fd28ef70e7d32e8ffaa7dd4828fab27fe1271b72dc00873c86c387d59763
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-1268-6527 0000-0002-4721-1441 0000-0002-1182-3729
OpenAccessLink	https://inria.hal.science/hal-01588272
PMID	28816656
PQID	2174479454
PQPubID	85458
PageCount	15
ParticipantIDs	crossref_primary_10_1109_TPAMI_2017_2740308 ieee_primary_8010838 proquest_miscellaneous_1930481994 crossref_citationtrail_10_1109_TPAMI_2017_2740308 proquest_journals_2174479454 hal_primary_oai_HAL_hal_01588272v1 pubmed_primary_28816656
PublicationCentury	2000
PublicationDate	2018-08-01
PublicationDateYYYYMMDD	2018-08-01
PublicationDate_xml	– month: 08 year: 2018 text: 2018-08-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) – name: Institute of Electrical and Electronics Engineers
References	ref57 ref56 ref59 ref15 ref14 ref53 ref52 ref55 ref11 ref10 vlasic (ref1) 2008; 27 li (ref25) 2009; 28 ref17 ref19 novatnack (ref49) 2008 ref18 collet (ref12) 2015; 34 criminisi (ref39) 2013 ref51 ref50 ref46 ref45 ref48 ref47 baran (ref58) 2007; 26 ref42 ref41 ref44 ref8 ref7 liu (ref4) 2013; 35 ref9 ref3 ref6 wei (ref26) 2012; 31 ref5 ref35 kehl (ref43) 2014 ref34 ref36 ref31 ref30 ref33 ref32 boyer (ref28) 2011 ref2 ref38 boscaini (ref37) 2016 zollhöfer (ref60) 2014; 33 sumner (ref54) 2004; 23 ref24 ref23 osher (ref16) 2006 ref64 ref20 ref63 ref66 ref22 ref65 ref21 dou (ref13) 2016; 35 ref27 ref29 criminisi (ref40) 2011 ref62 ref61
References_xml	– volume: 31 year: 2012 ident: ref26 article-title: Accurate realtime full-body motion capture using a single depth camera publication-title: ACM Trans Graph doi: 10.1145/2366145.2366207 – ident: ref53 doi: 10.1109/CVPR.2016.419 – ident: ref5 doi: 10.5244/C.27.4 – start-page: 440 year: 2008 ident: ref49 article-title: Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images publication-title: Proc Eur Conf Comput Vis – ident: ref59 doi: 10.1145/1057432.1057456 – ident: ref6 doi: 10.1109/CVPR.2012.6247664 – ident: ref27 doi: 10.1109/CVPR.2015.7298941 – ident: ref20 doi: 10.1007/978-3-642-33718-5_52 – ident: ref21 doi: 10.1109/ROBOT.1991.132043 – ident: ref3 doi: 10.1109/CVPR.2014.440 – ident: ref57 doi: 10.1145/344779.344862 – ident: ref66 doi: 10.1109/3DV.2013.45 – ident: ref14 doi: 10.1109/CVPR.2015.7299029 – ident: ref7 doi: 10.1109/34.121791 – ident: ref31 doi: 10.1109/ICCVW.2011.6130444 – volume: 35 year: 2016 ident: ref13 article-title: Fusion4D: Real-time performance capture of challenging scenes publication-title: ACM Trans Graph doi: 10.1145/2897824.2925969 – ident: ref8 doi: 10.1016/0262-8856(92)90066-C – volume: 23 start-page: 399 year: 2004 ident: ref54 article-title: Deformation transfer for triangle meshes publication-title: ACM Trans Graph doi: 10.1145/1015706.1015736 – ident: ref35 doi: 10.1109/ICCV.2007.4409108 – volume: 27 year: 2008 ident: ref1 article-title: Articulated mesh animation from multi-view silhouettes publication-title: ACM Trans Graph doi: 10.1145/1360612.1360696 – ident: ref42 doi: 10.1145/1198555.1198747 – volume: 28 year: 2009 ident: ref25 article-title: Robust single-view geometry and motion reconstruction publication-title: ACM Trans Graph doi: 10.1145/1618452.1618521 – start-page: 71 year: 2011 ident: ref28 article-title: SHREC 2011: Robust feature detection and description benchmark publication-title: Proc Eurographics Workshop 3D Object Retrieval – ident: ref36 doi: 10.1162/neco.1989.1.4.541 – ident: ref11 doi: 10.1109/CVPR.2011.5995316 – ident: ref2 doi: 10.1007/s11263-015-0832-y – ident: ref33 doi: 10.1007/978-3-642-15558-1_26 – ident: ref63 doi: 10.1111/cgf.12716 – year: 2013 ident: ref39 publication-title: Decision Forests for Computer Vision and Medical Image Analysis doi: 10.1007/978-1-4471-4929-3 – ident: ref32 doi: 10.1007/s11263-012-0528-5 – ident: ref48 doi: 10.1109/3DIMPVT.2012.51 – ident: ref17 doi: 10.1137/S0036144599352836 – ident: ref9 doi: 10.1109/CVPR.2014.532 – year: 2011 ident: ref40 article-title: Regression forests for efficient anatomy detection and localization in CT studies publication-title: Medical Computer Vision Recognition Techniques and Applications in Medical Imaging doi: 10.1007/978-3-642-18421-5_11 – ident: ref38 doi: 10.1109/TPAMI.2008.104 – ident: ref50 doi: 10.1109/3DV.2015.49 – ident: ref29 doi: 10.1007/s11263-015-0824-y – ident: ref56 doi: 10.1007/s11263-012-0549-0 – ident: ref22 doi: 10.1007/978-3-642-33765-9_53 – ident: ref62 doi: 10.1109/3DIMPVT.2012.29 – ident: ref61 doi: 10.1109/TPAMI.2016.2557783 – ident: ref45 doi: 10.1109/ICCV.2011.6126503 – ident: ref65 doi: 10.1109/CVPR.2014.491 – start-page: 3189 year: 2016 ident: ref37 article-title: Learning shape correspondence with anisotropic convolutional neural networks publication-title: Proc Conf Neural Inf Process Syst – ident: ref47 doi: 10.1007/s11263-009-0296-z – volume: 33 year: 2014 ident: ref60 article-title: Real-time non-rigid reconstruction using an RGB-D camera publication-title: ACM Trans Graph doi: 10.1145/2601097.2601165 – ident: ref19 doi: 10.1016/j.cviu.2006.08.002 – ident: ref30 doi: 10.1111/j.1467-8659.2009.01515.x – ident: ref34 doi: 10.1109/ICCV.2015.236 – ident: ref52 doi: 10.1007/978-3-319-46487-9_11 – ident: ref64 doi: 10.1109/CVPR.2010.5539838 – ident: ref24 doi: 10.1109/TPAMI.2010.223 – volume: 34 year: 2015 ident: ref12 article-title: High-quality streamable free-viewpoint video publication-title: ACM Trans Graph doi: 10.1145/2766945 – ident: ref55 doi: 10.1109/34.1000236 – volume: 35 start-page: 2720 year: 2013 ident: ref4 article-title: Markerless motion capture of multiple characters using multiview image segmentation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2013.47 – ident: ref41 doi: 10.1023/B:VISI.0000013087.49260.fb – volume: 26 year: 2007 ident: ref58 article-title: Automatic rigging and animation of 3d characters publication-title: ACM Trans Graph doi: 10.1145/1276377.1276467 – year: 2006 ident: ref16 publication-title: Level Set Methods and Dynamic Implicit Surfaces – year: 2014 ident: ref43 article-title: Coloured signed distance fields for full 3D object reconstruction publication-title: Proc British Mach Vis Conf – ident: ref10 doi: 10.1109/CVPR.2016.171 – ident: ref23 doi: 10.1111/j.2517-6161.1977.tb01600.x – ident: ref51 doi: 10.1109/CVPR.2015.7298623 – ident: ref44 doi: 10.1109/ISMAR.2011.6092378 – ident: ref46 doi: 10.1023/A:1007981719186 – ident: ref18 doi: 10.1007/s11263-009-0284-3 – ident: ref15 doi: 10.1145/1399504.1360697
SSID	ssj0014503
Score	2.3325515
Snippet	3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds...
SourceID	hal proquest pubmed crossref ieee
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	1994
SubjectTerms	3D tracking-by-detection centroidal Voronoi tessellation Computer Science Computer Vision and Pattern Recognition Data models Deformable models Deformation discriminative associations Iterative closest point algorithm Iterative methods random forest Robustness Shape Shape memory Shape recognition Shape tracking Stability analysis State of the art Surface reconstruction Tessellation Three-dimensional displays Tracking Tracking errors Visual observation
Title	Tracking-by-Detection of 3D Human Shapes: From Surfaces to Volumes
URI	https://ieeexplore.ieee.org/document/8010838 https://www.ncbi.nlm.nih.gov/pubmed/28816656 https://www.proquest.com/docview/2174479454 https://www.proquest.com/docview/1930481994 https://inria.hal.science/hal-01588272
Volume	40
WOSCitedRecordID	wos000437271100015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9RADLa6FQc4tNACDZRqQNwgbV6bmeG2UFZFgqpSC9rbKPNSkSCpNtlK_HvsyUM9ABK3KHGS0dge22PPZ4DXHI2mSDIbZ9oWcaE9j6Wel3GJ1l2bUugq86HZBD8_F6uVvNiCt9NZGOdcKD5zx3QZcvm2MRvaKjvB1RQ9BjGDGedlf1ZryhgU89AFGT0Y1HAMI8YDMok8ubpYfPlEVVz8GGMwAmghCGBBGTPqW33HHs2uqRoytFn5u8cZLM9y9__G_BB2Bg-TLXqReARbrt6D3bF7AxuUeQ8e3IEi3If3aLQMbZvH-ld86rpQoVWzxrP8lIWdfnZ5Xd249h1brpuf7HKz9lTNxbqGfQsrXPsYvi4_Xn04i4f-CrFBK9TFjvu59DYTzvPEcZtnTnhfVdzaAmfQVzrj3qUZTzXPrCH0utyI0uSCW4xDyvwJbNdN7Q6AFVbIqvQ8d8YXzmptpDQJLp06lZXjIoJ0nGVlBvBx6oHxQ4UgJJEqMEkRk9TApAjeTO_c9NAb_6R-hcybCAk1-2zxWdE99HhQInh2m0awTxyaqAbmRHA48loNKtwqitUIfn9eRPByeozKRxmVqnbNplXo_RLejpRI87SXkenbo4A9-_M_n8N9HL7oawkPYbtbb9wLuGduu-_t-gglfCWOgoT_BoII8mE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61BQk4UGh5BAoYxA3SZp2HbW4LZbUV21WlLqg3K36pSJBUm2wl_j1j56EeAIlblExenhnPjGf8DcBbhkaTJ9TEVJkszpRjsVB5ERdo3ZUuuCqpC80m2HLJLy7E2Ra8H_fCWGtD8Zk99Ichl29qvfFLZUc4m6LHwLfhVp5lNOl2a405gywPfZDRh0Edx0Bi2CKTiKPV2fT0xNdxsUOMwjxEiwcB5j5n5jtX37BI25e-HjI0Wvm7zxlsz2z3_776AdzvfUwy7YTiIWzZag92h_4NpFfnPbh3A4xwHz6i2dJ-4TxWv-Jj24YarYrUjqTHJKz1k_PL8so2H8hsXf8k55u18_VcpK3JtzDHNY_g6-zz6tM87jssxBrtUBtb5nLhDOXWscQyk1LLnStLZkyGI-hKRZmzE8omilGjPX5dqnmhU84MRiJF-hh2qrqyT4FkhouycCy12mXWKKWF0AlOnmoiSst4BJNhlKXu4cd9F4wfMoQhiZCBSdIzSfZMiuDdeM9VB77xT-o3yLyR0ONmz6cL6c-hz4MSwej1JIJ9z6GRqmdOBAcDr2WvxI300ZoH4M-zCF6Pl1H9fE6lrGy9aST6vx5xRwikedLJyPjsQcCe_fmdr-DOfHW6kIuT5ZfncBd_hXeVhQew06439gXc1tft92b9Msj5b40G9MA
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%3Ajournal&rft.genre=article&rft.atitle=Tracking-by-Detection+of+3D+Human+Shapes%3A+From+Surfaces+to+Volumes&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Huang%2C+Chun-Hao+Paul&rft.au=Allain%2C+Benjamin&rft.au=Boyer%2C+Edmond&rft.au=Franco%2C+Jean-Sebastien&rft.date=2018-08-01&rft.eissn=1939-3539&rft.volume=40&rft.issue=8&rft.spage=1994&rft_id=info:doi/10.1109%2FTPAMI.2017.2740308&rft_id=info%3Apmid%2F28816656&rft.externalDocID=28816656
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon