Single Shot Corrective CNN for Anatomically Correct 3D Hand Pose Estimation
Hand pose estimation in 3D from depth images is a highly complex task. Current state-of-the-art 3D hand pose estimators focus only on the accuracy of the model as measured by how closely it matches the ground truth hand pose but overlook the resulting hand pose's anatomical correctness. In this...
Saved in:
Published in | Frontiers in artificial intelligence Vol. 5; p. 759255 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Switzerland
Frontiers Media S.A
21.02.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Hand pose estimation in 3D from depth images is a highly complex task. Current state-of-the-art 3D hand pose estimators focus only on the accuracy of the model as measured by how closely it matches the ground truth hand pose but overlook the resulting hand pose's anatomical correctness. In this paper, we present the Single Shot Corrective CNN (SSC-CNN) to tackle the problem of enforcing anatomical correctness at the architecture level. In contrast to previous works which use post-facto pose filters, SSC-CNN predicts the hand pose that conforms to the human hand's biomechanical bounds and rules in a single forward pass. The model was trained and tested on the HANDS2017 and MSRA datasets. Experiments show that our proposed model shows comparable accuracy to the state-of-the-art models as measured by the ground truth pose. However, the previous methods have high anatomical errors, whereas our model is free from such errors. Experiments show that our proposed model shows zero anatomical errors along with comparable accuracy to the state-of-the-art models as measured by the ground truth pose. The previous methods have high anatomical errors, whereas our model is free from such errors. Surprisingly even the ground truth provided in the existing datasets suffers from anatomical errors, and therefore Anatomical Error Free (AEF) versions of the datasets, namely AEF-HANDS2017 and AEF-MSRA, were created. |
---|---|
AbstractList | Hand pose estimation in 3D from depth images is a highly complex task. Current state-of-the-art 3D hand pose estimators focus only on the accuracy of the model as measured by how closely it matches the ground truth hand pose but overlook the resulting hand pose's anatomical correctness. In this paper, we present the Single Shot Corrective CNN (SSC-CNN) to tackle the problem of enforcing anatomical correctness at the architecture level. In contrast to previous works which use post-facto pose filters, SSC-CNN predicts the hand pose that conforms to the human hand's biomechanical bounds and rules in a single forward pass. The model was trained and tested on the HANDS2017 and MSRA datasets. Experiments show that our proposed model shows comparable accuracy to the state-of-the-art models as measured by the ground truth pose. However, the previous methods have high anatomical errors, whereas our model is free from such errors. Experiments show that our proposed model shows zero anatomical errors along with comparable accuracy to the state-of-the-art models as measured by the ground truth pose. The previous methods have high anatomical errors, whereas our model is free from such errors. Surprisingly even the ground truth provided in the existing datasets suffers from anatomical errors, and therefore Anatomical Error Free (AEF) versions of the datasets, namely AEF-HANDS2017 and AEF-MSRA, were created. |
Author | Manivannan, Muniyandi Ravindran, Balaraman Isaac, Joseph H R |
AuthorAffiliation | 3 Robert Bosch Center for Data Science and Artificial Intelligence (RBC-DSAI), Department of Computer Science and Engineering, Indian Institute of Technology Madras , Chennai , India 2 Touch Lab, Department of Applied Mechanics, Indian Institute of Technology Madras , Chennai , India 1 Department of Computer Science and Engineering, Indian Institute of Technology Madras , Chennai , India |
AuthorAffiliation_xml | – name: 1 Department of Computer Science and Engineering, Indian Institute of Technology Madras , Chennai , India – name: 2 Touch Lab, Department of Applied Mechanics, Indian Institute of Technology Madras , Chennai , India – name: 3 Robert Bosch Center for Data Science and Artificial Intelligence (RBC-DSAI), Department of Computer Science and Engineering, Indian Institute of Technology Madras , Chennai , India |
Author_xml | – sequence: 1 givenname: Joseph H R surname: Isaac fullname: Isaac, Joseph H R organization: Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India – sequence: 2 givenname: Muniyandi surname: Manivannan fullname: Manivannan, Muniyandi organization: Touch Lab, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India – sequence: 3 givenname: Balaraman surname: Ravindran fullname: Ravindran, Balaraman organization: Robert Bosch Center for Data Science and Artificial Intelligence (RBC-DSAI), Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35265829$$D View this record in MEDLINE/PubMed |
BookMark | eNpVkUtPWzEQRq2KqlDKvqvKy24S_L72phIKtKAiWol2bU38CEY3NrUdJP59bwggWNnyzHdmrPMR7eWSA0KfKZlzrs1xrJDmjDA2H6RhUr5DB0wxMdOMsr1X93101NotIYRJIillH9A-l0xJzcwB-nmd8moM-PqmdLwotQbX033Ai6srHEvFJxl6WScH4_jwXMf8FJ9D9vh3aQGftZ7W0FPJn9D7CGMLR0_nIfr7_ezP4nx2-evHxeLkcuYElX0WuGBGgqOKScEDV9zTwTFnghRaREoUASV0dEs6ePDBS2ckJwakIEbRJT9EFzuuL3Br7-o0vj7YAsk-PpS6slB7cmOwglMRo5CKTelIAdgA09f90oPUg4aJ9W3Hutss18G7kHuF8Q30bSWnG7sq91ZrYwZiJsDXJ0At_zahdbtOzYVxhBzKplmmuCZ02kNPrWTX6mpprYb4MoYSu1Vqt0rtVqndKZ0iX16v9xJ4Fsj_A4WRnZo |
Cites_doi | 10.1007/s00371-016-1327-8 10.1109/TPAMI.2016.2599170 10.1016/j.neucom.2018.06.097 10.1016/j.jvcir.2018.04.005 10.1145/2702613.2728655 10.1109/CVPR.2009.5206848 10.1109/ACCESS.2020.3001637 10.1007/s11042-013-1501-1 10.1007/s00590-017-1991-z 10.1145/2448196.2448232 10.1109/ICIP.2017.8297136 10.1109/3DV.2017.00025 10.1016/0020-1383(95)90116-7 10.1109/SIEDS.2011.5876867 10.1093/cercor/bhi064 10.1007/978-3-319-70353-4_6 10.1109/IROS.2008.4651053 10.1007/978-3-030-58520-4_13 10.1145/2629500 10.1109/ACCESS.2018.2863540 10.1109/ICME.2007.4284820 10.1016/j.jhsa.2003.12.016 10.1145/2897824.2925965 10.1145/3130800.3130883 10.1109/WACV.2019.00153 10.1016/j.ergon.2015.10.004 10.3390/s18113872 10.1097/PRS.0000000000003745 10.1155/2013/910961 10.3389/frvir.2021.663618 10.1007/s00371-021-02250-y |
ContentType | Journal Article |
Copyright | Copyright © 2022 Isaac, Manivannan and Ravindran. Copyright © 2022 Isaac, Manivannan and Ravindran. 2022 Isaac, Manivannan and Ravindran |
Copyright_xml | – notice: Copyright © 2022 Isaac, Manivannan and Ravindran. – notice: Copyright © 2022 Isaac, Manivannan and Ravindran. 2022 Isaac, Manivannan and Ravindran |
DBID | NPM AAYXX CITATION 7X8 5PM DOA |
DOI | 10.3389/frai.2022.759255 |
DatabaseName | PubMed CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
DatabaseTitle | PubMed CrossRef MEDLINE - Academic |
DatabaseTitleList | PubMed CrossRef |
Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 2624-8212 |
EndPage | 759255 |
ExternalDocumentID | oai_doaj_org_article_4314ff4562a54f1aa27a265dbda5878a 10_3389_frai_2022_759255 35265829 |
Genre | Journal Article |
GroupedDBID | 53G 9T4 AAFWJ ACXDI ADBBV AFPKN ALMA_UNASSIGNED_HOLDINGS BCNDV GROUPED_DOAJ NPM OK1 RPM AAYXX CITATION PGMZT 7X8 5PM |
ID | FETCH-LOGICAL-c415t-e34295ac162543e363d17c2c9e5484f1060a648fcb17daded5c95309a540961b3 |
IEDL.DBID | RPM |
ISSN | 2624-8212 |
IngestDate | Thu Jul 04 21:05:50 EDT 2024 Tue Sep 17 21:14:22 EDT 2024 Fri Aug 16 21:20:29 EDT 2024 Fri Aug 23 02:35:14 EDT 2024 Tue Dec 20 17:57:50 EST 2022 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | anatomically correct tracking depth based hand tracking biomechanical constraints single shot corrective CNN 3D hand pose estimation |
Language | English |
License | Copyright © 2022 Isaac, Manivannan and Ravindran. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c415t-e34295ac162543e363d17c2c9e5484f1060a648fcb17daded5c95309a540961b3 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Edited by: Mohan Sridharan, University of Birmingham, United Kingdom Reviewed by: Chiranjoy Chattopadhyay, Indian Institute of Technology Jodhpur, India; Kalidas Yeturu, Indian Institute of Technology Tirupati, India This article was submitted to Machine Learning and Artificial Intelligence, a section of the journal Frontiers in Artificial Intelligence |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8899709/ |
PMID | 35265829 |
PQID | 2638014318 |
PQPubID | 23479 |
PageCount | 1 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_4314ff4562a54f1aa27a265dbda5878a pubmedcentral_primary_oai_pubmedcentral_nih_gov_8899709 proquest_miscellaneous_2638014318 crossref_primary_10_3389_frai_2022_759255 pubmed_primary_35265829 |
PublicationCentury | 2000 |
PublicationDate | 2022-02-21 |
PublicationDateYYYYMMDD | 2022-02-21 |
PublicationDate_xml | – month: 02 year: 2022 text: 2022-02-21 day: 21 |
PublicationDecade | 2020 |
PublicationPlace | Switzerland |
PublicationPlace_xml | – name: Switzerland |
PublicationTitle | Frontiers in artificial intelligence |
PublicationTitleAlternate | Front Artif Intell |
PublicationYear | 2022 |
Publisher | Frontiers Media S.A |
Publisher_xml | – name: Frontiers Media S.A |
References | Lee (B25) 2019 Oberweger (B36) 2016 Yoo (B61) 2020; 8 Sunil (B50) 2004; 29 Kehr (B24) 2017; 27 Chen (B8) 2019 Xiong (B58) 2019 Spurr (B46) 2020 Sridhar (B47) 2013 Tang (B51) 2016; 39 Wang (B57) 2018; 55 Poier (B38) 2019 Rad (B40) 2018 Oberweger (B35) 2017 Ross (B42) 2006 Tompson (B53) 2014; 33 Guo (B20) 2017 Chan Jee (B4) 2016; 53 Du (B14) 2019 Simon (B45) 2017 Malik (B30); 18 Li (B28) 2021; 37 Pelphrey (B37) 2005; 15 Hochschild (B22) 2015 Sun (B48) 2017 Ge (B19) Schwarz (B44) 1955; 2 Ge (B18) 2017 Cobos (B11) 2008 Aristidou (B1) 2018; 34 Deng (B12) 2009 Xu (B59) 2013 Lee (B26) 2015 Wan (B55) 2019 Cai (B2) 2019 Melax (B32) 2013 Poier (B39) 2015 Dibra (B13) 2017 Ryf (B43) 1995; 26 Li (B27) 2019 Cameron (B3) 2011 Choi (B10) 2020 Vollmer (B54) 1999 Ferche (B16); 9 Moon (B33) 2018 Lyubanenko (B29) 2017 Wan (B56) 2018 Zhou (B63) 2017 Yeo (B60) 2015; 74 Chen Chen (B5) 2013; 2013 Naik (B34) 2006 Chim (B9) 2017; 140 Sun (B49) 2015 Malik (B31) Isaac (B23) 2021; 2 Ge (B17) Yuan (B62) 2017 Chen (B7) 2018; 6 He (B21) 2016 Chen (B6) 2020; 395 Taylor (B52) 2016; 35 Fang (B15) 2007 Romero (B41) 2017; 36 |
References_xml | – volume: 34 start-page: 213 year: 2018 ident: B1 article-title: Hand tracking with physiological constraints publication-title: Vis. Comput doi: 10.1007/s00371-016-1327-8 contributor: fullname: Aristidou – volume: 39 start-page: 1374 year: 2016 ident: B51 article-title: Latent regression forest: structured estimation of 3d hand poses publication-title: IEEE Trans. Pattern Anal. Mach. Intell doi: 10.1109/TPAMI.2016.2599170 contributor: fullname: Tang – volume: 395 start-page: 138 year: 2020 ident: B6 article-title: Pose guided structured region ensemble network for cascaded hand pose estimation publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.06.097 contributor: fullname: Chen – volume: 9 start-page: 85 ident: B16 article-title: Evaluating lightweight optical hand tracking for Virtual Reality rehabilitation publication-title: Romanian J. Hum. Comput. Interact contributor: fullname: Ferche – start-page: 1145 volume-title: In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition year: 2017 ident: B45 article-title: Hand keypoint detection in single images using multiview bootstrapping contributor: fullname: Simon – start-page: 2272 volume-title: Proceedings of the IEEE/CVF International Conference on Computer Vision year: 2019 ident: B2 article-title: Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks contributor: fullname: Cai – start-page: 793 volume-title: Proceedings of the IEEE International Conference on Computer Vision 2019-October year: 2019 ident: B58 article-title: A2J: anchor-to-joint regression network for 3D articulated pose estimation from a single depth image contributor: fullname: Xiong – start-page: 10853 volume-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition year: 2019 ident: B55 article-title: Self-supervised 3d hand pose estimation through training by fitting contributor: fullname: Wan – start-page: 398 volume-title: Proceedings of the IEEE International Conference on Computer Vision year: 2017 ident: B63 article-title: Towards 3d human pose estimation in the wild: a weakly-supervised approach contributor: fullname: Zhou – start-page: 770 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2016 ident: B21 article-title: Deep residual learning for image recognition contributor: fullname: He – volume: 55 start-page: 404 year: 2018 ident: B57 article-title: Region ensemble network: towards good practices for deep 3d hand pose estimation publication-title: J. Vis. Commun. Image Represent doi: 10.1016/j.jvcir.2018.04.005 contributor: fullname: Wang – volume-title: Functional Anatomy for Physical Therapists year: 2015 ident: B22 contributor: fullname: Hochschild – start-page: 4866 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2017 ident: B62 article-title: Bighand2. 2m benchmark: hand pose dataset and state of the art analysis contributor: fullname: Yuan – start-page: 73 year: 2015 ident: B26 article-title: Transection: hand-based interaction for playing a game within a virtual reality game publication-title: Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems doi: 10.1145/2702613.2728655 contributor: fullname: Lee – start-page: 248 volume-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition year: 2009 ident: B12 article-title: Imagenet: a large-scale hierarchical image database doi: 10.1109/CVPR.2009.5206848 contributor: fullname: Deng – volume: 8 start-page: 114010 year: 2020 ident: B61 article-title: Fast and accurate 3d hand pose estimation via recurrent neural network for capturing hand articulations publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3001637 contributor: fullname: Yoo – volume: 74 start-page: 2687 year: 2015 ident: B60 article-title: Hand tracking and gesture recognition system for human-computer interaction using low-cost hardware publication-title: Multimed Tools Appl doi: 10.1007/s11042-013-1501-1 contributor: fullname: Yeo – volume: 27 start-page: 1029 year: 2017 ident: B24 article-title: B. Hirt, H. Seyhan, M. Wagner, r. Zumhasch: hand and wrist anatomy and biomechanics: a comprehensive guide publication-title: Eur. J. Orthopaedic Surg. Traumatol doi: 10.1007/s00590-017-1991-z contributor: fullname: Kehr – start-page: 184 volume-title: Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games year: 2013 ident: B32 article-title: Dynamics based 3D skeletal hand tracking doi: 10.1145/2448196.2448232 contributor: fullname: Melax – start-page: 6961 volume-title: Proceedings of the IEEE/CVF International Conference on Computer Vision year: 2019 ident: B8 article-title: So-handnet: self-organizing network for 3d hand pose estimation with semi-supervised learning contributor: fullname: Chen – start-page: 4512 volume-title: 2017 IEEE International Conference on Image Processing (ICIP) year: 2017 ident: B20 article-title: Region ensemble network: Improving convolutional network for hand pose estimation doi: 10.1109/ICIP.2017.8297136 contributor: fullname: Guo – start-page: 585 volume-title: Proceedings of the IEEE International Conference on Computer Vision Workshops year: 2017 ident: B35 article-title: Deepprior++: Improving fast and accurate 3d hand pose estimation contributor: fullname: Oberweger – start-page: 135 volume-title: 2017 International Conference on 3D Vision (3DV) year: 2017 ident: B13 article-title: How to refine 3d hand pose estimation from unlabelled depth data? doi: 10.1109/3DV.2017.00025 contributor: fullname: Dibra – volume: 26 start-page: 1 year: 1995 ident: B43 article-title: The neutral zero method–a principle of measuring joint function publication-title: Injury doi: 10.1016/0020-1383(95)90116-7 contributor: fullname: Ryf – start-page: 127 volume-title: 2011 IEEE Systems and Information Engineering Design Symposium year: 2011 ident: B3 article-title: Hand tracking and visualization in a virtual reality simulation doi: 10.1109/SIEDS.2011.5876867 contributor: fullname: Cameron – start-page: 182 volume-title: Proceedings of the British Machine Vision Conference 2015, BMVC 2015, Swansea, UK, September 7–10, 2015 year: 2015 ident: B39 article-title: Hybrid one-shot 3d hand pose estimation by exploiting uncertainties contributor: fullname: Poier – start-page: 3 volume-title: International Conference on Virtual Reality and Augmented Reality ident: B31 article-title: Structure-aware 3d hand pose regression from a single depth image contributor: fullname: Malik – start-page: 1 year: 2019 ident: B25 article-title: Torc: a virtual reality controller for in-hand high-dexterity finger interaction publication-title: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems contributor: fullname: Lee – start-page: 4663 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2018 ident: B40 article-title: Feature mapping for learning fast and accurate 3d pose inference from synthetic images contributor: fullname: Rad – volume: 15 start-page: 1866 year: 2005 ident: B37 article-title: Functional anatomy of biological motion perception in posterior temporal cortex: an fmri study of eye, mouth and hand movements publication-title: Cereb. Cortex doi: 10.1093/cercor/bhi064 contributor: fullname: Pelphrey – volume-title: Thieme Atlas of Anatomy: General Anatomy and Musculoskeletal System year: 2006 ident: B42 contributor: fullname: Ross – start-page: 67 volume-title: ACM International Conference Proceeding Series, Vol year: 2006 ident: B34 article-title: Hand gestures for hci using ica of emg contributor: fullname: Naik – start-page: 9896 volume-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition year: 2019 ident: B14 article-title: Crossinfonet: multi-task information sharing based hand pose estimation contributor: fullname: Du – volume: 2 start-page: 22 year: 1955 ident: B44 article-title: The anatomy and mechanics of the human hand publication-title: Artif. Limbs contributor: fullname: Schwarz – start-page: 5079 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2018 ident: B33 article-title: V2v-posenet: Voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map contributor: fullname: Moon – start-page: 11919 volume-title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2019-June year: 2019 ident: B27 article-title: Point-to-pose voting based hand pose estimation using residual permutation equivariant layer contributor: fullname: Li – start-page: 63 volume-title: International Conference on Advanced Concepts for Intelligent Vision Systems year: 2017 ident: B29 article-title: Multi-camera finger tracking and 3d trajectory reconstruction for hci studies doi: 10.1007/978-3-319-70353-4_6 contributor: fullname: Lyubanenko – volume-title: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS year: 2008 ident: B11 article-title: Efficient human hand kinematics for manipulation tasks doi: 10.1109/IROS.2008.4651053 contributor: fullname: Cobos – start-page: 4957 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2016 ident: B36 article-title: Efficiently creating 3d training data for fine hand pose estimation contributor: fullname: Oberweger – start-page: 2456 volume-title: Proceedings of the IEEE International Conference on Computer Vision year: 2013 ident: B47 article-title: Interactive markerless articulated hand motion tracking using RGB and depth data contributor: fullname: Sridhar – start-page: 211 volume-title: Computer Vision-ECCV 2020 year: 2020 ident: B46 article-title: Weakly supervised 3D hand pose estimation via biomechanical constraints doi: 10.1007/978-3-030-58520-4_13 contributor: fullname: Spurr – start-page: 1991 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2017 ident: B18 article-title: 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images contributor: fullname: Ge – volume: 33 start-page: 1 year: 2014 ident: B53 article-title: Real-time continuous pose recovery of human hands using convolutional networks publication-title: ACM Trans Graph doi: 10.1145/2629500 contributor: fullname: Tompson – start-page: 769 volume-title: European Conference on Computer Vision year: 2020 ident: B10 article-title: Pose2mesh: graph convolutional network for 3d human pose and mesh recovery from a 2d human pose contributor: fullname: Choi – volume: 6 start-page: 43425 year: 2018 ident: B7 article-title: Shpr-net: deep semantic hand pose regression from point clouds publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2863540 contributor: fullname: Chen – start-page: 995 volume-title: 2007 IEEE International Conference on Multimedia and Expo year: 2007 ident: B15 article-title: A real-time hand gesture recognition method doi: 10.1109/ICME.2007.4284820 contributor: fullname: Fang – volume: 29 start-page: 489 year: 2004 ident: B50 article-title: Clinical indicators of normal thumb length in adults1 1no benefits in any form have been received or will be received by a commercial party related directly or indirectly to the subject of this article publication-title: J. Hand. Surg. Am doi: 10.1016/j.jhsa.2003.12.016 contributor: fullname: Sunil – start-page: 5147 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2018 ident: B56 article-title: Dense 3d regression for hand pose estimation. contributor: fullname: Wan – volume: 35 start-page: 1 year: 2016 ident: B52 article-title: Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences publication-title: ACM Trans. Graph doi: 10.1145/2897824.2925965 contributor: fullname: Taylor – volume: 36 start-page: 1 year: 2017 ident: B41 article-title: Embodied hands: modeling and capturing hands and bodies together publication-title: ACM Trans. Graph doi: 10.1145/3130800.3130883 contributor: fullname: Romero – volume-title: Improved Laplacian Smoothing of Noisy Surface Meshes, Vo. 18-3 year: 1999 ident: B54 contributor: fullname: Vollmer – start-page: 1393 volume-title: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) year: 2019 ident: B38 article-title: Murauer: Mapping unlabeled real data for label austerity doi: 10.1109/WACV.2019.00153 contributor: fullname: Poier – start-page: 3456 volume-title: Proceedings of the IEEE International Conference on Computer Vision year: 2013 ident: B59 article-title: Efficient hand pose estimation from a single depth image contributor: fullname: Xu – volume: 53 start-page: 10 year: 2016 ident: B4 article-title: An anthropometric survey of korean hand and hand shape types publication-title: Int. J. Ind. Ergon doi: 10.1016/j.ergon.2015.10.004 contributor: fullname: Chan Jee – start-page: 2602 volume-title: Proceedings of the IEEE International Conference on Computer Vision year: 2017 ident: B48 article-title: Compositional human pose regression contributor: fullname: Sun – start-page: 475 volume-title: Proceedings of the European Conference on Computer Vision (ECCV) ident: B19 article-title: Point-to-point regression pointnet for 3d hand pose estimation contributor: fullname: Ge – volume: 18 start-page: 3872 ident: B30 article-title: 3dairsig: a framework for enabling in-air signatures using a multi-modal depth sensor publication-title: Sensors doi: 10.3390/s18113872 contributor: fullname: Malik – volume: 140 start-page: 865 year: 2017 ident: B9 article-title: Hand and wrist anatomy and biomechanics: a comprehensive guide publication-title: Plast Reconstr. Surg doi: 10.1097/PRS.0000000000003745 contributor: fullname: Chim – volume: 2013 start-page: 910961 year: 2013 ident: B5 article-title: Constraint study for a hand exoskeleton: human hand kinematics and dynamics publication-title: J. Rob doi: 10.1155/2013/910961 contributor: fullname: Chen Chen – start-page: 824 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2015 ident: B49 article-title: Cascaded hand pose regression contributor: fullname: Sun – volume: 2 start-page: 92 year: 2021 ident: B23 article-title: Corrective filter based on kinematics of human hand for pose estimation publication-title: Front. Virt. Reality doi: 10.3389/frvir.2021.663618 contributor: fullname: Isaac – volume: 37 start-page: 1 year: 2021 ident: B28 article-title: 3d hand reconstruction from a single image based on biomechanical constraints publication-title: Vis. Comput doi: 10.1007/s00371-021-02250-y contributor: fullname: Li – start-page: 8417 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ident: B17 article-title: Hand pointnet: 3d hand pose estimation using point sets contributor: fullname: Ge |
SSID | ssj0002505112 |
Score | 2.235666 |
Snippet | Hand pose estimation in 3D from depth images is a highly complex task. Current state-of-the-art 3D hand pose estimators focus only on the accuracy of the model... |
SourceID | doaj pubmedcentral proquest crossref pubmed |
SourceType | Open Website Open Access Repository Aggregation Database Index Database |
StartPage | 759255 |
SubjectTerms | 3D hand pose estimation anatomically correct tracking Artificial Intelligence biomechanical constraints depth based hand tracking single shot corrective CNN |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7iyYvvx_oighcPdZukadqjri6LwiKosLeQpikuLF1Z68F_70yyXXZF8OK1aenwTZL5PpKZIeRSoOSSPImkMTZKmBNRUTgXKTzms0oZbvwt32E6eE0eRnK01OoL74SF8sABuC4EuKSqkKcbmVTMGA7fp7IsSiMzlQVqxOSSmMI9GAM7MIlwLgkqLO9WMzMGOcj5tZI5x8y-pTjky_X_xjF_XpVcij39bbI5J430Jhi7Q9ZcvUu22oYMdL4-98jjMwSiiaPPb9OG9rDvht_NaG84pEBO6U0NEtvXB5h8teNU3NGBqUv6NP1w9B5WfEhm3Cev_fuX3iCad0uILAThJnICQos0lqWY3-5EKkqmLLe5A1ECyMVpbNIkq2zBVGlKV0qbSxHnACu2fSnEAVmvp7U7IrQEXmUym2axKhJTAUdhsXBWVI6nDmJ8h1y12On3UBRDg5hAnDXirBFnHXDukFsEd_EelrP2D8DJeu5k_ZeTO-SidY2G6Y9nGqZ2088PzWH_wBKFDIw6DK5a_MqX_s943iFqxYkrtqyO1OM3X2I7Axmq4vz4P4w_IRuIh8-DZ6dkvZl9ujNgMk1x7iftN8iQ8Ag priority: 102 providerName: Directory of Open Access Journals |
Title | Single Shot Corrective CNN for Anatomically Correct 3D Hand Pose Estimation |
URI | https://www.ncbi.nlm.nih.gov/pubmed/35265829 https://search.proquest.com/docview/2638014318 https://pubmed.ncbi.nlm.nih.gov/PMC8899709 https://doaj.org/article/4314ff4562a54f1aa27a265dbda5878a |
Volume | 5 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PT9swFH4qHCYubMCAsoGMxGWHtHEcx8mx66gqJiokhsTNenEcqFQSVMph_z3PTtLRaadd40R5eu_Z7_vk9wPgQjjKJaM4kIgmiLkVQZ5bGyh3zWeUwgh9lu8smd7FV_fyvgeyq4XxSfsmnw-qxdOgmj_63MrnJzPs8sSGN9fjlEiCCrPhFmwpId5RdHf8uphOIKK5kiQClg3LJc6JCUbRQMmMIPQOfPBd4VOPK_9EI9-0_19I8--EyXcRaPIJdlvoyEaNiHvQs9U-fOzGMrB2lx7Az1sKRwvLbh_rFRu76Rv-TGPj2YwRRGWjioi27xKw-N2tM_GDTbEq2E39Ytkl7fumpPEz3E0uf42nQTszITAUileBFRRgJBqeuCp3KxJRcGUik1miJnFJBDDEJE5Lk3NVYGELaTIpwgwJuWUJz8UhbFd1ZY-BFYSuMDVJGqo8xpKQCg-FNaK0UWIp0vfhW6c7_dy0xtBEKZzKtVO5dirXjcr78N0pd_2ea2rtH9TLB92aVhOWicvSUTKSpuSIEblKIou8QJmqFPtw3plG0yZwNxtY2fr1RUd0irhGhZyEOmpMtf5VZ-o-qA0jbsiyuUJ-5xttt3528t9ffoEdpwRfAs-_wvZq-WpPCcSs8jNP_s-8674BWqTxlg |
link.rule.ids | 230,315,733,786,790,870,891,2115,27957,27958,53827,53829 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Nb9QwEB2VIkEvlG-WTyNx4ZBsbMdxcixLq4W2q0ptUW-W7Th0xTapttkD_HrGTlK6FRe4xokyybNn3pNnxgAfuJdcgqWR0NpGKXU8Msa5SPptPiulZjpk-c6y6Wn69UycbYAYamFC0r4187heXMT1_DzkVl5e2PGQJzY-OpzkKBJkUozvwF1cr0zeEOneAfuojjSi25RECVaMq6WeoxZkLJaiQBK9BfdCX_g8MMs_8Si07f8b17ydMnkjBu1tw7fB-i715Ee8ak1sf91q7PjPn_cQHvSslOx0w49gw9WPYXs48YH0DuAJ7B9jpFs4cnzetGTiD_YI7pJMZjOC7Jfs1KjhQwOCxc9hnPDPZKrrkhw1V47sokvpqiWfwune7slkGvXHMUQWo3wbOY6xS2hLM19A73jGSyots4VD1ZNWqC0TnaV5ZQ2VpS5dKWwheFJoJIVFRg1_Bpt1U7sXQEokbjq3WZ5Ik-oKSRBNuLO8cixzSCJG8HEARV12XTcUqhWPpfJYKo-l6rAcwSeP2vV9vl92uNAsv6v-tyqkSWlVebWH1lRUa4azMBOlKbXIZa5H8H7AXOH68psmunbN6koxdFC-ByJFo553c-D6VcMcGoFcmx1rtqyPIOahh3eP8cv_fvId3J-eHB6ogy-z_Vew5X9IqLSnr2GzXa7cG-RKrXkbVsZvZ7ASug |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9wwEB21VEJcCv2iS6F1pV56yKfjODnShdW2tKuVKBLqxbIdp6y6JKsle6C_vmMngV3UE9c4UWw_e-Y9eTwD8IlaycXixGNSai-JDPWUMsbj9phPcy5j6aJ8J-n4Ivl2yS7XSn25oH2tZn41v_ar2ZWLrVxc66CPEwumP4YZigQe5sGiKIOn8Az3bJyvCXVrhK1nRyrRHkyiDMuDcilnqAfj2OcsRyK9A9suN3zm2OW9T3Kp-__HNx-GTa75odEu_OpH0Iaf_PFXjfL13wfJHR81xD143rFTcty-8gKemOol7PaVH0hnCF7B2Tl6vLkh51d1Q4a2wIczm2Q4mRBkweS4Qi3vEhHMb_t2Qk_IWFYFmdY3hpyiaWlvTb6Gi9Hpz-HY68oyeBq9feMZij6MSR2l9iK9oSktIq5jnRtUP0mJGjOUaZKVWkW8kIUpmM4ZDXOJ5DBPI0XfwFZVV-YtkAIJnMx0moVcJbJEMhSF1Ghamjg1SCYG8LkHRiza7BsCVYvFU1g8hcVTtHgO4ItF7u49mzfbPaiXv0U3tQLpUlKWVvVhb8pIyhhXY8oKVUiW8UwO4GOPu8B9Zg9PZGXq1Y2I0VDZXIgRdmq_XQd3v-rX0QD4xgrZ6MtmC-Lucnl3OB88-ssPsD09GYnvXydn72DHzoe7cB8dwlazXJkjpEyNeu82xz8NtBU6 |
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=Single+Shot+Corrective+CNN+for+Anatomically+Correct+3D+Hand+Pose+Estimation&rft.jtitle=Frontiers+in+artificial+intelligence&rft.au=Isaac%2C+Joseph+H+R&rft.au=Manivannan%2C+Muniyandi&rft.au=Ravindran%2C+Balaraman&rft.date=2022-02-21&rft.eissn=2624-8212&rft.volume=5&rft.spage=759255&rft.epage=759255&rft_id=info:doi/10.3389%2Ffrai.2022.759255&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2624-8212&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2624-8212&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2624-8212&client=summon |