3D Tracking of Human Motion Using Visual Skeletonization and Stereoscopic Vision.
artificial intelligence
computer vision
gait analysis
markerless motion capture
movement measurement
Journal
Frontiers in bioengineering and biotechnology
ISSN: 2296-4185
Titre abrégé: Front Bioeng Biotechnol
Pays: Switzerland
ID NLM: 101632513
Informations de publication
Date de publication:
2020
2020
Historique:
received:
31
10
2019
accepted:
24
02
2020
entrez:
21
3
2020
pubmed:
21
3
2020
medline:
21
3
2020
Statut:
epublish
Résumé
The design of markerless systems to reconstruct human motion in a timely, unobtrusive and externally valid manner is still an open challenge. Artificial intelligence algorithms based on automatic landmarks identification on video images opened to a new approach, potentially e-viable with low-cost hardware. OpenPose is a library that t using a two-branch convolutional neural network allows for the recognition of skeletons in the scene. Although OpenPose-based solutions are spreading, their metrological performances relative to video setup are still largely unexplored. This paper aimed at validating a two-cameras OpenPose-based markerless system for gait analysis, considering its accuracy relative to three factors: cameras' relative distance, gait direction and video resolution. Two volunteers performed a walking test within a gait analysis laboratory. A marker-based optical motion capture system was taken as a reference. Procedures involved: calibration of the stereoscopic system; acquisition of video recordings, simultaneously with the reference marker-based system; video processing within OpenPose to extract the subject's skeleton; videos synchronization; triangulation of the skeletons in the two videos to obtain the 3D coordinates of the joints. Two set of parameters were considered for the accuracy assessment: errors in trajectory reconstruction and error in selected gait space-temporal parameters (step length, swing and stance time). The lowest error in trajectories (~20 mm) was obtained with cameras 1.8 m apart, highest resolution and straight gait, and the highest (~60 mm) with the 1.0 m, low resolution and diagonal gait configuration. The OpenPose-based system tended to underestimate step length of about 1.5 cm, while no systematic biases were found for swing/stance time. Step length significantly changed according to gait direction (
Identifiants
pubmed: 32195243
doi: 10.3389/fbioe.2020.00181
pmc: PMC7066370
doi:
Types de publication
Journal Article
Langues
eng
Pagination
181Informations de copyright
Copyright © 2020 Zago, Luzzago, Marangoni, De Cecco, Tarabini and Galli.
Références
IEEE Trans Pattern Anal Mach Intell. 2019 Jul 17;:
pubmed: 31331883
J Electromyogr Kinesiol. 2017 Aug;35:69-75
pubmed: 28601565
J Biomech. 1995 Oct;28(10):1257-61
pubmed: 8550644
J Biomech. 2018 Apr 27;72:268-273
pubmed: 29567306
Sports Med Open. 2018 Jun 5;4(1):24
pubmed: 29869300
J Neuroeng Rehabil. 2006 Mar 15;3:6
pubmed: 16539701
Gait Posture. 2005 Feb;21(2):186-96
pubmed: 15639398
J Biomech. 2018 Apr 11;71:281-285
pubmed: 29475751
Comput Methods Biomech Biomed Engin. 2018 Feb;21(2):113-128
pubmed: 29374973
Comput Methods Programs Biomed. 2016 Mar;125:37-45
pubmed: 26792173
Eur Rev Aging Phys Act. 2017 Nov 15;14:19
pubmed: 29177018
Gait Posture. 2019 Feb;68:193-200
pubmed: 30500731
Gait Posture. 2019 Jul;72:46-50
pubmed: 31136942
Clin Rehabil. 2017 Jan;31(1):23-33
pubmed: 26658333