Cargando…

Towards Single Camera Human 3D-Kinematics

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos....

Descripción completa

Detalles Bibliográficos
Autores principales: Bittner, Marian, Yang, Wei-Tse, Zhang, Xucong, Seth, Ajay, van Gemert, Jan, van der Helm, Frans C. T.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9823525/
https://www.ncbi.nlm.nih.gov/pubmed/36616937
http://dx.doi.org/10.3390/s23010341
_version_ 1784866181200478208
author Bittner, Marian
Yang, Wei-Tse
Zhang, Xucong
Seth, Ajay
van Gemert, Jan
van der Helm, Frans C. T.
author_facet Bittner, Marian
Yang, Wei-Tse
Zhang, Xucong
Seth, Ajay
van Gemert, Jan
van der Helm, Frans C. T.
author_sort Bittner, Marian
collection PubMed
description Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos. Most current techniques work in a multi-step approach by first detecting the pose of the body and then fitting a musculoskeletal model to the data for accurate kinematic estimation. Errors in training data of the pose detection algorithms, model scaling, as well the requirement of multiple cameras limit the use of these techniques in a clinical setting. Our goal is to pave the way toward fast, easily applicable and accurate 3D kinematic estimation. To this end, we propose a novel approach for direct 3D human kinematic estimation D3KE from videos using deep neural networks. Our experiments demonstrate that the proposed end-to-end training is robust and outperforms 2D and 3D markerless motion capture based kinematic estimation pipelines in terms of joint angles error by a large margin (35% from 5.44 to 3.54 degrees). We show that D3KE is superior to the multi-step approach and can run at video framerate speeds. This technology shows the potential for clinical analysis from mobile devices in the future.
format Online
Article
Text
id pubmed-9823525
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98235252023-01-08 Towards Single Camera Human 3D-Kinematics Bittner, Marian Yang, Wei-Tse Zhang, Xucong Seth, Ajay van Gemert, Jan van der Helm, Frans C. T. Sensors (Basel) Article Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos. Most current techniques work in a multi-step approach by first detecting the pose of the body and then fitting a musculoskeletal model to the data for accurate kinematic estimation. Errors in training data of the pose detection algorithms, model scaling, as well the requirement of multiple cameras limit the use of these techniques in a clinical setting. Our goal is to pave the way toward fast, easily applicable and accurate 3D kinematic estimation. To this end, we propose a novel approach for direct 3D human kinematic estimation D3KE from videos using deep neural networks. Our experiments demonstrate that the proposed end-to-end training is robust and outperforms 2D and 3D markerless motion capture based kinematic estimation pipelines in terms of joint angles error by a large margin (35% from 5.44 to 3.54 degrees). We show that D3KE is superior to the multi-step approach and can run at video framerate speeds. This technology shows the potential for clinical analysis from mobile devices in the future. MDPI 2022-12-28 /pmc/articles/PMC9823525/ /pubmed/36616937 http://dx.doi.org/10.3390/s23010341 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Bittner, Marian
Yang, Wei-Tse
Zhang, Xucong
Seth, Ajay
van Gemert, Jan
van der Helm, Frans C. T.
Towards Single Camera Human 3D-Kinematics
title Towards Single Camera Human 3D-Kinematics
title_full Towards Single Camera Human 3D-Kinematics
title_fullStr Towards Single Camera Human 3D-Kinematics
title_full_unstemmed Towards Single Camera Human 3D-Kinematics
title_short Towards Single Camera Human 3D-Kinematics
title_sort towards single camera human 3d-kinematics
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9823525/
https://www.ncbi.nlm.nih.gov/pubmed/36616937
http://dx.doi.org/10.3390/s23010341
work_keys_str_mv AT bittnermarian towardssinglecamerahuman3dkinematics
AT yangweitse towardssinglecamerahuman3dkinematics
AT zhangxucong towardssinglecamerahuman3dkinematics
AT sethajay towardssinglecamerahuman3dkinematics
AT vangemertjan towardssinglecamerahuman3dkinematics
AT vanderhelmfransct towardssinglecamerahuman3dkinematics