Deep Learning-Based Automated Extraction of Anthropometric Measurements From a Single 3-D Scan

The appearance of 3-D scanners, generating point clouds, has revolutionized anthropometric data collection systems and their applications. Anthropometric data are of paramount importance in several applications, including fashion design, medical diagnosis, and virtual character modeling, all of whic...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on instrumentation and measurement Ročník 70; s. 1 - 14
Hlavní autoři:	Kaashki, Nastaran Nourbakhsh, Hu, Pengpeng, Munteanu, Adrian
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Anthropometric measurement Anthropometry Coders Data collection Deep learning Deformation encoder–decoder architectures Feature extraction Machine learning Missing data Modules Neural networks Noise measurement Noise sensitivity point cloud Scanners template fitting Three dimensional models Three-dimensional displays
ISSN:	0018-9456, 1557-9662
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The appearance of 3-D scanners, generating point clouds, has revolutionized anthropometric data collection systems and their applications. Anthropometric data are of paramount importance in several applications, including fashion design, medical diagnosis, and virtual character modeling, all of which require a fully automatic anthropometric measurement extraction method. 3-D-based methods for anthropometric measurement extraction becomes more and more popular due to their improved accuracy compared to classical image-based approaches. Existing 3-D methods can be mainly classified into two categories: landmark and template-based methods. The former is highly dependent on the estimated landmarks which are highly sensitive to noise in the input or missing data. The latter has to iteratively solve an objective function to deform a body template to fit the scan, which is time-consuming while being also sensitive to noise and missing data. In this study, we propose the first approach for automatic contact-less anthropometric measurements extraction based on deep-learning (AM-DL). A novel module dubbed multiscale EdgeConv is proposed to learn local features from point clouds at multiple scales. Multiscale EdgeConv can be directly integrated with other neural networks for various tasks, e.g., classification of point clouds. We exploit this module to design an encoder-decoder architecture that learns to deform a template model to fit a given scan. The measurement values are then calculated on the deformed template model. To evaluate the proposed method, 27 female and 25 male subjects were scanned using a photogrametry-based scanner and measured by an experienced tailor. Experimental results on the synthetic ModelNet40 dataset and on the real scans demonstrate that the proposed method outperforms state-of-the-art methods, and performs sufficiently close to a professional tailor.
AbstractList	The appearance of 3-D scanners, generating point clouds, has revolutionized anthropometric data collection systems and their applications. Anthropometric data are of paramount importance in several applications, including fashion design, medical diagnosis, and virtual character modeling, all of which require a fully automatic anthropometric measurement extraction method. 3-D-based methods for anthropometric measurement extraction becomes more and more popular due to their improved accuracy compared to classical image-based approaches. Existing 3-D methods can be mainly classified into two categories: landmark and template-based methods. The former is highly dependent on the estimated landmarks which are highly sensitive to noise in the input or missing data. The latter has to iteratively solve an objective function to deform a body template to fit the scan, which is time-consuming while being also sensitive to noise and missing data. In this study, we propose the first approach for automatic contact-less anthropometric measurements extraction based on deep-learning (AM-DL). A novel module dubbed multiscale EdgeConv is proposed to learn local features from point clouds at multiple scales. Multiscale EdgeConv can be directly integrated with other neural networks for various tasks, e.g., classification of point clouds. We exploit this module to design an encoder–decoder architecture that learns to deform a template model to fit a given scan. The measurement values are then calculated on the deformed template model. To evaluate the proposed method, 27 female and 25 male subjects were scanned using a photogrametry-based scanner and measured by an experienced tailor. Experimental results on the synthetic ModelNet40 dataset and on the real scans demonstrate that the proposed method outperforms state-of-the-art methods, and performs sufficiently close to a professional tailor.
Author	Kaashki, Nastaran Nourbakhsh Hu, Pengpeng Munteanu, Adrian
Author_xml	– sequence: 1 givenname: Nastaran Nourbakhsh orcidid: 0000-0001-8317-4994 surname: Kaashki fullname: Kaashki, Nastaran Nourbakhsh email: nknourba@etrovub.be organization: Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium – sequence: 2 givenname: Pengpeng orcidid: 0000-0002-2547-1517 surname: Hu fullname: Hu, Pengpeng email: phu@etrovub.be organization: Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium – sequence: 3 givenname: Adrian orcidid: 0000-0001-7290-0428 surname: Munteanu fullname: Munteanu, Adrian email: acmuntea@etrovub.be organization: Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium
BookMark	eNp9kE1LAzEQhoMoWD_ugpeA562TdDe7OVZttVDx0Hp1mcZZ3dJNapIF_femVDx48DTD8H4wzwk7tM4SYxcChkKAvl7OHocSpBiOBCgh1QEbiKIoM62UPGQDAFFlOi_UMTsJYQ0ApcrLAXu5I9ryOaG3rX3LbjDQKx_30XUY0zb5jB5NbJ3lruFjG9-927qOom8NfyQMvaeObAx86l3HkS9Syob4KLvjC4P2jB01uAl0_jNP2fN0srx9yOZP97Pb8TwzUouYSY1NhSXJ1wYNaW10jihlQ3mVg073ErBqxEpirlHlFZiVIp1DaUwjyeDolF3tc7feffQUYr12vbepspZFCRIqqWVSwV5lvAvBU1Nvfduh_6oF1DuKdaJY7yjWPxSTRf2xmDbiDkgC027-M17ujS0R_fboQpTpmdE3kwGBDQ
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_1109_TIM_2023_3298426 crossref_primary_10_3390_e24111647 crossref_primary_10_1109_ACCESS_2024_3519671 crossref_primary_10_1109_TIM_2023_3334341 crossref_primary_10_1109_TIM_2022_3222501 crossref_primary_10_1109_TIM_2022_3186072 crossref_primary_10_1016_j_imavis_2024_105306 crossref_primary_10_1186_s40691_023_00357_5 crossref_primary_10_1109_TIM_2023_3284948 crossref_primary_10_3389_frai_2024_1336320 crossref_primary_10_3390_s22051885 crossref_primary_10_1109_TCE_2024_3363616 crossref_primary_10_1016_j_patcog_2025_112060 crossref_primary_10_3390_electronics11071048 crossref_primary_10_1002_cav_2159
Cites_doi	10.1117/12.57955 10.1155/2015/404261 10.1109/ISPA.2019.8868844 10.15221/15.155 10.1109/WACV.2014.6836115 10.1016/j.jcm.2016.02.012 10.1016/j.measurement.2018.08.019 10.1007/978-3-030-01216-8_15 10.1109/TIM.2012.2193693 10.1109/CVPR.2010.5539838 10.1109/MSP.2017.2693418 10.1049/iet-smt.2015.0252 10.1016/j.measurement.2014.10.044 10.1145/3197517.3201301 10.1109/CVPR.2007.383165 10.1109/ICCV.2017.230 10.1109/TIM.2007.903605 10.1109/CVPR.2017.492 10.1016/j.gmod.2018.05.003 10.1016/j.eswa.2017.04.052 10.1037/1040-3590.6.4.284 10.1109/ACCESS.2021.3076595 10.1016/j.cag.2017.11.008 10.1016/j.measurement.2020.108519 10.1016/j.jvlc.2018.05.002 10.1037/1082-989X.1.1.30 10.1016/0020-0190(72)90045-2 10.1109/CVPR.2017.16 10.1007/978-3-642-33783-3_18 10.1016/j.eswa.2017.09.006 10.1109/TIM.2019.2906969 10.1109/TIM.2009.2031847 10.1145/2816795.2818013 10.1145/3272127.3275028 10.1016/j.measurement.2020.107751 10.1109/TPAMI.2010.46 10.1109/TII.2020.3016591 10.3390/s19020393 10.1016/j.measurement.2019.106949 10.1016/j.measurement.2020.108173 10.1016/0925-2312(91)90023-5
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TIM.2021.3106126
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	14
ExternalDocumentID	10_1109_TIM_2021_3106126 9517270
Genre	orig-research
GrantInformation_xml	– fundername: Innoviris through the Project eTailor in close collaboration with Treedy’s funderid: 10.13039/501100004744 – fundername: Fonds voor Wetenschappelijk Onderzoek (FWO) grantid: G084117 funderid: 10.13039/501100003130
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ VH1 VJK AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c291t-29af8a7e2dface99c94aa22fe484097e270a8f1b2a49a6480cb6e9407ccf2eca3
IEDL.DBID	RIE
ISICitedReferencesCount	22
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000698641700009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9456
IngestDate	Mon Jun 30 07:25:06 EDT 2025 Sat Nov 29 04:38:14 EST 2025 Tue Nov 18 22:35:35 EST 2025 Wed Aug 27 02:49:30 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-29af8a7e2dface99c94aa22fe484097e270a8f1b2a49a6480cb6e9407ccf2eca3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-2547-1517 0000-0001-7290-0428 0000-0001-8317-4994
PQID	2570208292
PQPubID	85462
PageCount	14
ParticipantIDs	crossref_primary_10_1109_TIM_2021_3106126 proquest_journals_2570208292 ieee_primary_9517270 crossref_citationtrail_10_1109_TIM_2021_3106126
PublicationCentury	2000
PublicationDate	20210000 2021-00-00 20210101
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– year: 2021 text: 20210000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref56 ref15 ref14 ref53 ref52 ref55 ref11 ref54 ref10 kouchi (ref27) 2020 ref17 uçar (ref2) 2021; 167 ref19 ref42 ref41 yan (ref12) 2021 (ref24) 2020 ref43 ref49 kingma (ref48) 2014 ref8 ref7 ref9 ref4 ref3 qi (ref44) 2017 ref6 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref1 ref39 (ref25) 2020 ref38 (ref45) 2021 yan (ref16) 2019 ref26 ref20 ref22 ref21 loshchilov (ref51) 2016 ref28 ref29 wu (ref50) 2015 barrow (ref47) 1977 wang (ref18) 2018 (ref46) 2021 apeagyei (ref5) 2010; 4 (ref23) 2020
References_xml	– ident: ref32 doi: 10.1117/12.57955 – start-page: 29 year: 2020 ident: ref27 publication-title: Anthropometric Methods for Apparel Design Body Measurement Devices and Techniques – start-page: 659 year: 1977 ident: ref47 article-title: Parametric correspondence and chamfer matching: Two new techniques for image matching publication-title: Proc 5th Int Joint Conf Artif Intell – ident: ref1 doi: 10.1155/2015/404261 – ident: ref22 doi: 10.1109/ISPA.2019.8868844 – ident: ref15 doi: 10.15221/15.155 – ident: ref36 doi: 10.1109/WACV.2014.6836115 – ident: ref54 doi: 10.1016/j.jcm.2016.02.012 – ident: ref10 doi: 10.1016/j.measurement.2018.08.019 – ident: ref19 doi: 10.1007/978-3-030-01216-8_15 – ident: ref26 doi: 10.1109/TIM.2012.2193693 – year: 2020 ident: ref25 – start-page: 1912 year: 2015 ident: ref50 article-title: 3D ShapeNets: A deep representation for volumetric shapes publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref29 doi: 10.1109/CVPR.2010.5539838 – ident: ref42 doi: 10.1109/MSP.2017.2693418 – ident: ref9 doi: 10.1049/iet-smt.2015.0252 – year: 2018 ident: ref18 article-title: Dynamic graph CNN for learning on point clouds publication-title: arXiv 1801 07829 – ident: ref28 doi: 10.1016/j.measurement.2014.10.044 – ident: ref52 doi: 10.1145/3197517.3201301 – ident: ref39 doi: 10.1109/CVPR.2007.383165 – ident: ref41 doi: 10.1109/ICCV.2017.230 – ident: ref4 doi: 10.1109/TIM.2007.903605 – ident: ref40 doi: 10.1109/CVPR.2017.492 – ident: ref33 doi: 10.1016/j.gmod.2018.05.003 – ident: ref13 doi: 10.1016/j.eswa.2017.04.052 – year: 2014 ident: ref48 article-title: Adam: A method for stochastic optimization publication-title: arXiv 1412 6980 – year: 2017 ident: ref44 article-title: PointNet++: Deep hierarchical feature learning on point sets in a metric space publication-title: arXiv 1706 02413 – ident: ref56 doi: 10.1037/1040-3590.6.4.284 – year: 2019 ident: ref16 article-title: Anthropometric clothing measurements from 3D body scans publication-title: arXiv 1911 00694 – ident: ref20 doi: 10.1109/ACCESS.2021.3076595 – ident: ref30 doi: 10.1016/j.cag.2017.11.008 – ident: ref3 doi: 10.1016/j.measurement.2020.108519 – year: 2021 ident: ref45 publication-title: Treedy's 3D Scanner – ident: ref14 doi: 10.1016/j.jvlc.2018.05.002 – ident: ref53 doi: 10.1037/1082-989X.1.1.30 – ident: ref49 doi: 10.1016/0020-0190(72)90045-2 – ident: ref17 doi: 10.1109/CVPR.2017.16 – ident: ref37 doi: 10.1007/978-3-642-33783-3_18 – ident: ref11 doi: 10.1016/j.eswa.2017.09.006 – ident: ref6 doi: 10.1109/TIM.2019.2906969 – ident: ref55 doi: 10.1109/TIM.2009.2031847 – year: 2021 ident: ref46 publication-title: PhotoScan Agisoft – ident: ref31 doi: 10.1145/2816795.2818013 – year: 2016 ident: ref51 article-title: SGDR: Stochastic gradient descent with warm restarts publication-title: arXiv 1608 03983 – volume: 4 start-page: 58 year: 2010 ident: ref5 article-title: Application of 3D body scanning technology to human measurement for clothing fit publication-title: Int J Digit Content Technol Appl – year: 2020 ident: ref24 – ident: ref35 doi: 10.1145/3272127.3275028 – ident: ref8 doi: 10.1016/j.measurement.2020.107751 – ident: ref38 doi: 10.1109/TPAMI.2010.46 – year: 2021 ident: ref12 article-title: Learning anthropometry from rendered humans publication-title: arXiv 2101 02515 – ident: ref43 doi: 10.1109/TII.2020.3016591 – ident: ref21 doi: 10.3390/s19020393 – ident: ref7 doi: 10.1016/j.measurement.2019.106949 – volume: 167 year: 2021 ident: ref2 article-title: Estimation of body fat percentage using hybrid machine learning algorithms publication-title: Measurement doi: 10.1016/j.measurement.2020.108173 – year: 2020 ident: ref23 – ident: ref34 doi: 10.1016/0925-2312(91)90023-5
SSID	ssj0007647
Score	2.4135756
Snippet	The appearance of 3-D scanners, generating point clouds, has revolutionized anthropometric data collection systems and their applications. Anthropometric data...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Anthropometric measurement Anthropometry Coders Data collection Deep learning Deformation encoder–decoder architectures Feature extraction Machine learning Missing data Modules Neural networks Noise measurement Noise sensitivity point cloud Scanners template fitting Three dimensional models Three-dimensional displays
Title	Deep Learning-Based Automated Extraction of Anthropometric Measurements From a Single 3-D Scan
URI	https://ieeexplore.ieee.org/document/9517270 https://www.proquest.com/docview/2570208292
Volume	70
WOSCitedRecordID	wos000698641700009&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: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1BT9swFH7qEEjjwBgwUWDIh10mLWviuHZ8hEE1DkWTYBKnRY79jCa1TdWkiJ_Pc5J2Q0xIu1mR7UT-Yn9-z37vA_jEXea0HrpoKKyMhHAYFTql6R7YOkPiHBc3YhPq-jq7u9M_evBlHQuDiM3lM_wais1ZvivtMrjKBrQbILolA_2NUqqN1VqvukqKNj9mQhOY3rM6koz14PZqTIYgT8g-DYQun1FQo6nyYiFu2GX07v--axd2ul0kO2thfw89nO3B9l-5Bfdgq7nbaat9-HWBOGddItX76Jx4y7GzZV3SZpVKl4_1oo1uYKVnK-GEaVDasmz8x4VYsdGinDLDbqiXCbI0umA3BMwB_Bxd3n77HnWyCpHlOqkjro3PjELuvLGotdXCGM49imDs0XMVm8wnBTdCGymy2BYSNRl-1nqO1qQfYGNWzvAQWFYoGRuXSqkEVRZGJQVKX_g0dlmsfR8Gq5HObZdzPEhfTPLG9oh1TtjkAZu8w6YPn9ct5m2-jVfq7gcs1vU6GPpwsgIz7yZklQexPh7iiPnRv1sdw9vQd-tdOYGNerHEj7BpH-rf1eK0-deeABXO0FI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fT9swED4hYAIeNn6KMsb8wMukhSaO68SPMKhajVZIdBJPixz7jJCgQW2K-PM5J2kBbZq0Nyuy48hf7M939t0HcMxtapXq2KAjjAyEsBjkKqbp7tk6ReIcG1ZiE8lwmN7cqKsl-L6IhUHE6vIZnvhidZZvCzPzrrI27QaIbslAX-kIwaM6Wmux7iZS1BkyI5rC1NP8UDJU7VF_QKYgj8hC9ZQu35FQparyx1Jc8Uv30_992SZ8bPaR7LQGfguWcLwNG2-yC27Dh-p2p5nuwO9zxEfWpFK9Dc6IuSw7nZUFbVepdPFcTur4BlY4NpdOePBaW4YNXp2IU9adFA9Ms2t6yz2yODhn1wTNLvzqXox-9IJGWCEwXEVlwJV2qU6QW6cNKmWU0Jpzh8Kbe_Q8CXXqopxrobQUaWhyiYpMP2McR6PjPVgeF2PcB5bmiQy1jaVMBFUWOolylC53cWjTULkWtOcjnZkm67gXv7jPKusjVBlhk3lssgabFnxbtHisM278o-6Ox2JRr4GhBYdzMLNmSk4zL9fHfSQxP_h7q6-w1hsNLrPL_vDnZ1j3_dS-lkNYLicz_AKr5qm8m06Oqv_uBRUL05k
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=Deep+Learning-Based+Automated+Extraction+of+Anthropometric+Measurements+From+a+Single+3-D+Scan&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Kaashki%2C+Nastaran+Nourbakhsh&rft.au=Hu%2C+Pengpeng&rft.au=Munteanu%2C+Adrian&rft.date=2021&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=70&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1109%2FTIM.2021.3106126&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIM_2021_3106126
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon