Video summary of the first data set per person.

<div><p>Accurate and reliable skeletal motion tracking is essential for rehabilitation monitoring, enabling objective assessment of patient progress and facilitating telerehabilitation applications. Traditional marker-based motion capture systems, while highly accurate, are costly and im...

Full description

Saved in:
Bibliographic Details
Main Author: Vytautas Abromavičius (22008573) (author)
Other Authors: Ervinas Gisleris (22008576) (author), Kristina Daunoravičienė (18251583) (author), Jurgita Žižienė (22008579) (author), Artūras Serackis (20783472) (author), Rytis Maskeliūnas (10172664) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852017786478395392
author Vytautas Abromavičius (22008573)
author2 Ervinas Gisleris (22008576)
Kristina Daunoravičienė (18251583)
Jurgita Žižienė (22008579)
Artūras Serackis (20783472)
Rytis Maskeliūnas (10172664)
author2_role author
author
author
author
author
author_facet Vytautas Abromavičius (22008573)
Ervinas Gisleris (22008576)
Kristina Daunoravičienė (18251583)
Jurgita Žižienė (22008579)
Artūras Serackis (20783472)
Rytis Maskeliūnas (10172664)
author_role author
dc.creator.none.fl_str_mv Vytautas Abromavičius (22008573)
Ervinas Gisleris (22008576)
Kristina Daunoravičienė (18251583)
Jurgita Žižienė (22008579)
Artūras Serackis (20783472)
Rytis Maskeliūnas (10172664)
dc.date.none.fl_str_mv 2025-08-07T17:35:03Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0328969.t002
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Video_summary_of_the_first_data_set_per_person_/29854623
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
yet challenges remain
wrist joint (<
upper limb activities
refine depth coordinates
reducing error margins
proposed system combines
missing joint positions
kalman filtering framework
human pose estimation
facilitating telerehabilitation applications
experimental results demonstrate
enabling objective assessment
depth estimation errors
deep learning approaches
enhance temporal consistency
scenarios involving occlusions
remote patient monitoring
improving tracking precision
div >< p
single camera setups
rehabilitation monitoring
patient progress
integrates temporal
camera systems
whereas marker
traditional marker
time interpolation
study provides
study proposes
spatial synchronization
scalable solution
rehabilitation exercises
recent studies
p </
occlusion conditions
linear regression
home rehabilitation
frontal perspectives
allowing real
dc.title.none.fl_str_mv Video summary of the first data set per person.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>Accurate and reliable skeletal motion tracking is essential for rehabilitation monitoring, enabling objective assessment of patient progress and facilitating telerehabilitation applications. Traditional marker-based motion capture systems, while highly accurate, are costly and impractical for home rehabilitation, whereas marker-less methods often suffer from depth estimation errors and occlusions. Recent studies have explored various computer vision and deep learning approaches for human pose estimation, yet challenges remain in ensuring robust depth accuracy and tracking under occlusion conditions. This study proposes a three-dimensional human skeleton tracking system for upper limb activities that integrates temporal and spatial synchronization to improve depth estimation accuracy for rehabilitation exercises. The proposed system combines a 90° secondary camera to compensate for the depth prediction inaccuracies inherent in single-camera systems, reducing error margins by up to 0.4 m. In addition, a linear regression-based depth error correction model is implemented to refine depth coordinates, further improving tracking precision. The Kalman filtering framework is employed to enhance temporal consistency, allowing real-time interpolation of missing joint positions. Experimental results demonstrate that the proposed method significantly reduces depth estimation errors of the elbow and wrist joint (<i>p</i> < 0.001) compared to single camera setups, particularly in scenarios involving occlusions and non-frontal perspectives. This study provides a cost-effective and scalable solution for remote patient monitoring and motor function evaluation.</p></div>
eu_rights_str_mv openAccess
id Manara_036743746040407af0c9a061fd29cc6a
identifier_str_mv 10.1371/journal.pone.0328969.t002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29854623
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Video summary of the first data set per person.Vytautas Abromavičius (22008573)Ervinas Gisleris (22008576)Kristina Daunoravičienė (18251583)Jurgita Žižienė (22008579)Artūras Serackis (20783472)Rytis Maskeliūnas (10172664)BiotechnologySpace ScienceEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedyet challenges remainwrist joint (<upper limb activitiesrefine depth coordinatesreducing error marginsproposed system combinesmissing joint positionskalman filtering frameworkhuman pose estimationfacilitating telerehabilitation applicationsexperimental results demonstrateenabling objective assessmentdepth estimation errorsdeep learning approachesenhance temporal consistencyscenarios involving occlusionsremote patient monitoringimproving tracking precisiondiv >< psingle camera setupsrehabilitation monitoringpatient progressintegrates temporalcamera systemswhereas markertraditional markertime interpolationstudy providesstudy proposesspatial synchronizationscalable solutionrehabilitation exercisesrecent studiesp </occlusion conditionslinear regressionhome rehabilitationfrontal perspectivesallowing real<div><p>Accurate and reliable skeletal motion tracking is essential for rehabilitation monitoring, enabling objective assessment of patient progress and facilitating telerehabilitation applications. Traditional marker-based motion capture systems, while highly accurate, are costly and impractical for home rehabilitation, whereas marker-less methods often suffer from depth estimation errors and occlusions. Recent studies have explored various computer vision and deep learning approaches for human pose estimation, yet challenges remain in ensuring robust depth accuracy and tracking under occlusion conditions. This study proposes a three-dimensional human skeleton tracking system for upper limb activities that integrates temporal and spatial synchronization to improve depth estimation accuracy for rehabilitation exercises. The proposed system combines a 90° secondary camera to compensate for the depth prediction inaccuracies inherent in single-camera systems, reducing error margins by up to 0.4 m. In addition, a linear regression-based depth error correction model is implemented to refine depth coordinates, further improving tracking precision. The Kalman filtering framework is employed to enhance temporal consistency, allowing real-time interpolation of missing joint positions. Experimental results demonstrate that the proposed method significantly reduces depth estimation errors of the elbow and wrist joint (<i>p</i> < 0.001) compared to single camera setups, particularly in scenarios involving occlusions and non-frontal perspectives. This study provides a cost-effective and scalable solution for remote patient monitoring and motor function evaluation.</p></div>2025-08-07T17:35:03ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0328969.t002https://figshare.com/articles/dataset/Video_summary_of_the_first_data_set_per_person_/29854623CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/298546232025-08-07T17:35:03Z
spellingShingle Video summary of the first data set per person.
Vytautas Abromavičius (22008573)
Biotechnology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
yet challenges remain
wrist joint (<
upper limb activities
refine depth coordinates
reducing error margins
proposed system combines
missing joint positions
kalman filtering framework
human pose estimation
facilitating telerehabilitation applications
experimental results demonstrate
enabling objective assessment
depth estimation errors
deep learning approaches
enhance temporal consistency
scenarios involving occlusions
remote patient monitoring
improving tracking precision
div >< p
single camera setups
rehabilitation monitoring
patient progress
integrates temporal
camera systems
whereas marker
traditional marker
time interpolation
study provides
study proposes
spatial synchronization
scalable solution
rehabilitation exercises
recent studies
p </
occlusion conditions
linear regression
home rehabilitation
frontal perspectives
allowing real
status_str publishedVersion
title Video summary of the first data set per person.
title_full Video summary of the first data set per person.
title_fullStr Video summary of the first data set per person.
title_full_unstemmed Video summary of the first data set per person.
title_short Video summary of the first data set per person.
title_sort Video summary of the first data set per person.
topic Biotechnology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
yet challenges remain
wrist joint (<
upper limb activities
refine depth coordinates
reducing error margins
proposed system combines
missing joint positions
kalman filtering framework
human pose estimation
facilitating telerehabilitation applications
experimental results demonstrate
enabling objective assessment
depth estimation errors
deep learning approaches
enhance temporal consistency
scenarios involving occlusions
remote patient monitoring
improving tracking precision
div >< p
single camera setups
rehabilitation monitoring
patient progress
integrates temporal
camera systems
whereas marker
traditional marker
time interpolation
study provides
study proposes
spatial synchronization
scalable solution
rehabilitation exercises
recent studies
p </
occlusion conditions
linear regression
home rehabilitation
frontal perspectives
allowing real