Multi-View Large Population Gait Database With Human Meshes and Its Performance Evaluation
Existing model-based gait databases provide the 2D poses (i.e., joint locations) extracted by general pose estimators as the human model. However, these 2D poses suffer from information loss and are of relatively low quality. In this paper, we consider a more informative 3D human mesh model with par...
Uloženo v:
| Vydáno v: | IEEE transactions on biometrics, behavior, and identity science Ročník 4; číslo 2; s. 234 - 248 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Piscataway
IEEE
01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 2637-6407, 2637-6407 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Existing model-based gait databases provide the 2D poses (i.e., joint locations) extracted by general pose estimators as the human model. However, these 2D poses suffer from information loss and are of relatively low quality. In this paper, we consider a more informative 3D human mesh model with parametric pose and shape features, and propose a multi-view training framework for accurate mesh estimation. Unlike existing methods, which estimate a mesh from a single view and suffer from the ill-posed estimation problem in 3D space, the proposed framework takes asynchronous multi-view gait sequences as input and uses both multi-view and single-view streams to learn consistent and accurate mesh models for both multi-view and single-view sequences. After applying the proposed framework to the existing OU-MVLP database, we establish a large-scale gait database with human meshes (i.e., OUMVLP-Mesh), containing over 10,000 subjects and up to 14 view angles. Experimental results show that the proposed framework estimates human mesh models more accurately than similar methods, providing models of sufficient quality to improve the recognition performance of a baseline model-based gait recognition approach. |
|---|---|
| AbstractList | Existing model-based gait databases provide the 2D poses (i.e., joint locations) extracted by general pose estimators as the human model. However, these 2D poses suffer from information loss and are of relatively low quality. In this paper, we consider a more informative 3D human mesh model with parametric pose and shape features, and propose a multi-view training framework for accurate mesh estimation. Unlike existing methods, which estimate a mesh from a single view and suffer from the ill-posed estimation problem in 3D space, the proposed framework takes asynchronous multi-view gait sequences as input and uses both multi-view and single-view streams to learn consistent and accurate mesh models for both multi-view and single-view sequences. After applying the proposed framework to the existing OU-MVLP database, we establish a large-scale gait database with human meshes (i.e., OUMVLP-Mesh), containing over 10,000 subjects and up to 14 view angles. Experimental results show that the proposed framework estimates human mesh models more accurately than similar methods, providing models of sufficient quality to improve the recognition performance of a baseline model-based gait recognition approach. |
| Author | Makihara, Yasushi Yagi, Yasushi Li, Xiang Xu, Chi |
| Author_xml | – sequence: 1 givenname: Xiang orcidid: 0000-0002-8044-7050 surname: Li fullname: Li, Xiang email: li@am.sanken.osaka-u.ac.jp organization: Department of Intelligent Media, SANKEN, Osaka University, Osaka, Japan – sequence: 2 givenname: Yasushi surname: Makihara fullname: Makihara, Yasushi email: makihara@am.sanken.osaka-u.ac.jp organization: Department of Intelligent Media, SANKEN, Osaka University, Osaka, Japan – sequence: 3 givenname: Chi orcidid: 0000-0001-6036-5763 surname: Xu fullname: Xu, Chi email: xu@am.sanken.osaka-u.ac.jp organization: Department of Intelligent Media, SANKEN, Osaka University, Osaka, Japan – sequence: 4 givenname: Yasushi orcidid: 0000-0002-3546-8071 surname: Yagi fullname: Yagi, Yasushi email: yagi@am.sanken.osaka-u.ac.jp organization: Department of Intelligent Media, SANKEN, Osaka University, Osaka, Japan |
| BookMark | eNp9kE1Lw0AQhhdRsNb-Ab0seE7djySbPWqtbaGlPVQFL2GaTuyWNKm7G8V_b_qBiAdhYAbmfWZe3gtyWlYlEnLFWZdzpm_n96PppCuYEF3JVRhF-oS0RCxVEIdMnf6az0nHuTVjTLBQN9Uir5O68CZ4NvhJx2DfkM6qbV2AN1VJB2A8fQAPC3BIX4xf0WG9gZJO0K3QUSiXdOQdnaHNK9ssMqT9DyjqPX5JznIoHHaOvU2eHvvz3jAYTwej3t04yKTUPgCZKMkEiAjiHDnGC954i7IYOaBWcpGHTKssjLJltlRSRFECC7VkUsa5YqBlm9wc7m5t9V6j8-m6qm3ZvExFrLTUCY-TRpUcVJmtnLOYp5nxe5_egilSztJdmOk-zHQXZnoMs0HFH3RrzQbs1__Q9QEyiPgDaKWkDLX8BsDZgUo |
| CitedBy_id | crossref_primary_10_3390_s25113471 crossref_primary_10_1007_s00521_025_11505_x crossref_primary_10_1109_TPAMI_2025_3577594 crossref_primary_10_1109_TPAMI_2023_3312419 crossref_primary_10_1007_s11227_024_06172_z crossref_primary_10_1109_TIFS_2023_3236181 crossref_primary_10_1109_ACCESS_2025_3545787 crossref_primary_10_1109_TIFS_2024_3428371 crossref_primary_10_1007_s11227_023_05143_0 crossref_primary_10_1109_ACCESS_2025_3542837 crossref_primary_10_1109_ACCESS_2025_3570280 crossref_primary_10_1109_TMM_2023_3312931 crossref_primary_10_1109_TCSVT_2025_3545210 crossref_primary_10_1109_TPAMI_2025_3546482 crossref_primary_10_1007_s11227_024_06089_7 crossref_primary_10_1109_TIP_2024_3360870 crossref_primary_10_1109_TNNLS_2025_3526815 crossref_primary_10_3390_jimaging10040088 |
| Cites_doi | 10.2197/ipsjtcva.5.163 10.1109/ICIP.2002.1038998 10.1117/12.2018145 10.1109/ICCVW54120.2021.00456 10.1109/CVPR.2018.00411 10.1007/978-3-030-58529-7_23 10.1109/AFGR.2004.1301502 10.1007/978-3-319-13323-2_3 10.1109/ICCV48922.2021.01465 10.1007/978-3-319-69923-3_51 10.1007/978-3-030-58545-7_22 10.1109/TBIOM.2020.3008862 10.1145/2661229.2661273 10.1016/j.patcog.2019.04.023 10.1109/TPAMI.2014.2366766 10.1145/2816795.2818013 10.1016/j.patcog.2003.09.012 10.1109/CVPR.2012.6247844 10.1109/3DV.2017.00064 10.1007/11744078_12 10.1109/CVPR.2018.00744 10.1049/iet-bmt.2013.0090 10.1016/j.patcog.2019.107069 10.1109/ICB.2012.6199832 10.1109/TPAMI.2019.2929257 10.1109/ICPR.2010.849 10.1109/CVPR.2018.00055 10.1109/CVPR42600.2020.00530 10.1109/TPAMI.2013.248 10.1109/CVPR.2019.00484 10.1016/j.patcog.2018.10.019 10.1109/TPAMI.2006.38 10.1109/TCSVT.2017.2760835 10.1109/ICCV.2019.00445 10.1109/TIP.2014.2371335 10.1109/ICCV.2019.00554 10.1007/978-3-030-69535-4_1 10.1007/978-3-319-46454-1_34 10.1111/j.1556-4029.2011.01793.x 10.1109/ICPR.2006.67 10.1007/978-3-319-46493-0_38 10.1109/ICCV.2017.256 10.1109/CVPR.2017.718 10.1109/TIFS.2019.2912577 10.1186/s41074-018-0039-6 10.1109/CVPR.2019.00483 10.1109/CVPR.2010.5540113 10.1109/AFGR.2004.1301521 10.1609/aaai.v33i01.33018126 10.1109/CVPR42600.2020.01423 10.1016/S1077-3142(03)00008-0 10.1109/TIFS.2012.2204253 10.1109/TPAMI.2016.2545669 10.3115/v1/D14-1179 10.1109/CVPR.2001.990506 10.1109/ICB.2016.7550060 10.1109/TIFS.2018.2844819 10.1109/TPAMI.2005.39 10.1109/EST.2010.19 10.1109/CVPR.2014.323 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SP 8FD L7M |
| DOI | 10.1109/TBIOM.2022.3174559 |
| DatabaseName | IEEE Xplore (IEEE) IEEE Xplore Open Access (Activated by CARLI) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 2637-6407 |
| EndPage | 248 |
| ExternalDocumentID | 10_1109_TBIOM_2022_3174559 9773349 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: JSPS KAKENHI grantid: JP19H05692; JP20H00607 |
| GroupedDBID | 0R~ 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL IFIPE JAVBF OCL RIA RIE AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c339t-a387302a25a6fe1e6b14905c6e1ae973bf4097c45cdcd732558ab7d0336f70a93 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 31 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001301688600009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2637-6407 |
| IngestDate | Sun Nov 30 04:59:01 EST 2025 Sat Nov 29 04:02:38 EST 2025 Tue Nov 18 19:50:36 EST 2025 Wed Aug 27 02:23:54 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | https://creativecommons.org/licenses/by-nc-nd/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c339t-a387302a25a6fe1e6b14905c6e1ae973bf4097c45cdcd732558ab7d0336f70a93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-6036-5763 0000-0002-8044-7050 0000-0002-3546-8071 |
| OpenAccessLink | https://ieeexplore.ieee.org/document/9773349 |
| PQID | 2679398168 |
| PQPubID | 4437219 |
| PageCount | 15 |
| ParticipantIDs | crossref_citationtrail_10_1109_TBIOM_2022_3174559 proquest_journals_2679398168 crossref_primary_10_1109_TBIOM_2022_3174559 ieee_primary_9773349 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-04-01 |
| PublicationDateYYYYMMDD | 2022-04-01 |
| PublicationDate_xml | – month: 04 year: 2022 text: 2022-04-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on biometrics, behavior, and identity science |
| PublicationTitleAbbrev | TBIOM |
| PublicationYear | 2022 |
| 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 ref57 ref12 ref56 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref10 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 Kingma (ref61) 2014 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 Makihara (ref15) ref24 ref23 ref26 ref25 ref20 ref64 ref63 ref22 ref21 ref65 Shin (ref54) 2020 Gross (ref34) 2001 ref28 ref27 ref29 ref60 |
| References_xml | – ident: ref2 doi: 10.2197/ipsjtcva.5.163 – ident: ref37 doi: 10.1109/ICIP.2002.1038998 – ident: ref39 doi: 10.1117/12.2018145 – ident: ref45 doi: 10.1109/ICCVW54120.2021.00456 – ident: ref60 doi: 10.1109/CVPR.2018.00411 – ident: ref58 doi: 10.1007/978-3-030-58529-7_23 – ident: ref21 doi: 10.1109/AFGR.2004.1301502 – ident: ref38 doi: 10.1007/978-3-319-13323-2_3 – ident: ref65 doi: 10.1109/ICCV48922.2021.01465 – ident: ref30 doi: 10.1007/978-3-319-69923-3_51 – ident: ref64 doi: 10.1007/978-3-030-58545-7_22 – ident: ref43 doi: 10.1109/TBIOM.2020.3008862 – ident: ref57 doi: 10.1145/2661229.2661273 – ident: ref33 doi: 10.1016/j.patcog.2019.04.023 – ident: ref5 doi: 10.1109/TPAMI.2014.2366766 – ident: ref46 doi: 10.1145/2816795.2818013 – ident: ref22 doi: 10.1016/j.patcog.2003.09.012 – ident: ref18 doi: 10.1109/CVPR.2012.6247844 – ident: ref56 doi: 10.1109/3DV.2017.00064 – ident: ref14 doi: 10.1007/11744078_12 – ident: ref49 doi: 10.1109/CVPR.2018.00744 – ident: ref3 doi: 10.1049/iet-bmt.2013.0090 – ident: ref31 doi: 10.1016/j.patcog.2019.107069 – ident: ref26 doi: 10.1109/ICB.2012.6199832 – ident: ref27 doi: 10.1109/TPAMI.2019.2929257 – ident: ref25 doi: 10.1109/ICPR.2010.849 – ident: ref48 doi: 10.1109/CVPR.2018.00055 – ident: ref50 doi: 10.1109/CVPR42600.2020.00530 – ident: ref55 doi: 10.1109/TPAMI.2013.248 – start-page: 717 volume-title: Proc. CVPR ident: ref15 article-title: Silhouette transformation based on walking speed for gait identification – ident: ref41 doi: 10.1109/CVPR.2019.00484 – ident: ref19 doi: 10.1016/j.patcog.2018.10.019 – ident: ref4 doi: 10.1109/TPAMI.2006.38 – year: 2020 ident: ref54 article-title: Multi-view human pose and shape estimation using learnable volumetric aggregation publication-title: arXiv:2011.13427 – year: 2014 ident: ref61 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref9 doi: 10.1109/TCSVT.2017.2760835 – ident: ref53 doi: 10.1109/ICCV.2019.00445 – ident: ref16 doi: 10.1109/TIP.2014.2371335 – ident: ref52 doi: 10.1109/ICCV.2019.00554 – ident: ref44 doi: 10.1007/978-3-030-69535-4_1 – ident: ref47 doi: 10.1007/978-3-319-46454-1_34 – ident: ref1 doi: 10.1111/j.1556-4029.2011.01793.x – ident: ref32 doi: 10.1109/ICPR.2006.67 – ident: ref59 doi: 10.1007/978-3-319-46493-0_38 – ident: ref28 doi: 10.1109/ICCV.2017.256 – ident: ref6 doi: 10.1109/CVPR.2017.718 – ident: ref12 doi: 10.1109/TIFS.2019.2912577 – ident: ref29 doi: 10.1186/s41074-018-0039-6 – ident: ref10 doi: 10.1109/CVPR.2019.00483 – ident: ref13 doi: 10.1109/CVPR.2010.5540113 – ident: ref35 doi: 10.1109/AFGR.2004.1301521 – ident: ref11 doi: 10.1609/aaai.v33i01.33018126 – ident: ref63 doi: 10.1109/CVPR42600.2020.01423 – ident: ref24 doi: 10.1016/S1077-3142(03)00008-0 – ident: ref42 doi: 10.1109/TIFS.2012.2204253 – ident: ref8 doi: 10.1109/TPAMI.2016.2545669 – ident: ref51 doi: 10.3115/v1/D14-1179 – ident: ref23 doi: 10.1109/CVPR.2001.990506 – ident: ref7 doi: 10.1109/ICB.2016.7550060 – ident: ref20 doi: 10.1109/TIFS.2018.2844819 – ident: ref36 doi: 10.1109/TPAMI.2005.39 – ident: ref40 doi: 10.1109/EST.2010.19 – ident: ref17 doi: 10.1109/CVPR.2014.323 – year: 2001 ident: ref34 article-title: The CMU motion of body (MoBo) database |
| SSID | ssj0002049049 |
| Score | 2.3884916 |
| Snippet | Existing model-based gait databases provide the 2D poses (i.e., joint locations) extracted by general pose estimators as the human model. However, these 2D... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 234 |
| SubjectTerms | Asynchronous multi-view sequences Finite element method gait database Gait recognition Human performance Performance evaluation Shape Skeleton Solid modeling Three dimensional models Three-dimensional displays three-dimensional human pose/shape estimation Videos |
| Title | Multi-View Large Population Gait Database With Human Meshes and Its Performance Evaluation |
| URI | https://ieeexplore.ieee.org/document/9773349 https://www.proquest.com/docview/2679398168 |
| Volume | 4 |
| WOSCitedRecordID | wos001301688600009&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: 2637-6407 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002049049 issn: 2637-6407 databaseCode: RIE dateStart: 20190101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB50UfDiW1xdJQdvWu02abI5-lbwsQdfeClJOsEFWcVWxX9vknaroAjeekhKmelk8iUz3wewYZmVOjE8MjFXEWMWI51aF1dUcqVNTBVWYhPi4qJ3dyf7Y7DV9MIgYig-w23_GO7y8yfz6o_KdtxehVImx2FcCF71ajXnKYm_wmJy1BcTy52rvdPLc4cAk8QBU8FST0f6LfcEMZUfK3BIK0cz__ugWZiut49kt_L3HIzhcB4mK0HJjwW4D_200c0A38mZr_Em_UagixyrQUkOVKl85iK3g_KBhCN8co7FAxZEDXNyWhak_9VLQA4bMvBFuD46vNo_iWr1hMhQKstI0Z6L3kQlqeIWu8i1A0Nxajh2FUpBtfVUV4alJje5oA5a9JQWeUwptyJWki5Ba_g0xGUgjGqNVKCHL0w4hGa15Z4Yj6c0Rmna0B3ZNTM1tbhXuHjMAsSIZRZ8kXlfZLUv2rDZzHmuiDX-HL3grd-MrA3fhs7IfVkde0WWcLfmSK8nsvL7rFWY8u-u6m860CpfXnENJsxbOShe1sNv9QkHc8rX |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0BBbUXyqdYoOBDb5CuN3ac9ZFvVt1d9rAFxCWynbFYqVoQCUX8e2wnmyK1qtRbDrYSzWQ8fvbMewBfLbdSx0ZEhgoVcW4x0ol1ccWkUNpQprASm0iHw-7trRzNwWHTC4OIofgMv_nHcJefP5hnf1TWdnsVxrichw8J5zGturWaE5XYX2JxOeuMobI9Pu5dDRwGjGMHTVOeeELSd9knyKn8sQaHxHL--f8-aQWW6w0kOao8vgpzOF2DpUpS8nUd7kJHbXQ9wRfS91XeZNRIdJELNSnJqSqVz13kZlLek3CITwZY3GNB1DQnvbIgo9_dBOSsoQPfgB_nZ-OTy6jWT4gMY7KMFOu6-I1VnChhsYNCOzhEEyOwo1CmTFtPdmV4YnKTp8yBi67SaU4ZEzalSrJNWJg-THELCGdaI0vRAxieOoxmtRWeGk8kjKI0LejM7JqZmlzca1z8zALIoDILvsi8L7LaFy04aOY8VtQa_xy97q3fjKwN34LdmfuyOvqKLBZu1ZFeUWT777P24ePleNDP-r3h9x345N9TVePswkL59IxfYNH8KifF0174xd4Av0jOHg |
| 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=Multi-View+Large+Population+Gait+Database+With+Human+Meshes+and+Its+Performance+Evaluation&rft.jtitle=IEEE+transactions+on+biometrics%2C+behavior%2C+and+identity+science&rft.au=Li%2C+Xiang&rft.au=Makihara%2C+Yasushi&rft.au=Xu%2C+Chi&rft.au=Yagi%2C+Yasushi&rft.date=2022-04-01&rft.pub=IEEE&rft.eissn=2637-6407&rft.volume=4&rft.issue=2&rft.spage=234&rft.epage=248&rft_id=info:doi/10.1109%2FTBIOM.2022.3174559&rft.externalDocID=9773349 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2637-6407&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2637-6407&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2637-6407&client=summon |