• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Institut de Biomécanique Humaine Georges Charpak (IBHGC)
  • View Item
  • Home
  • Institut de Biomécanique Humaine Georges Charpak (IBHGC)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

A novel dataset and deep learning-based approach for marker-less motion capture during gait

Article dans une revue avec comité de lecture
Author
VAFADAR, Saman
ccSKALLI, Wafa
1001024 Laboratoire de biomécanique [LBM]
BONNET-LEBRUN, Aurore
KHALIFÉ, Marc
300119 Hôpital Européen Georges Pompidou [APHP] [HEGP]
RENAUDIN, Mathis
HAMZA, Amine
ccGAJNY, Laurent
1001017 Institut de Biomécanique Humaine Georges Charpak [IBHGC]

URI
http://hdl.handle.net/10985/20156
DOI
10.1016/j.gaitpost.2021.03.003
Date
2021
Journal
Gait and Posture

Abstract

Background: The deep learning-based human pose estimation methods, which can estimate joint centers position, have achieved promising results on the publicly available human pose datasets (e.g., Human3.6 M). However, these datasets may be less efficient for gait study, particularly for clinical applications, because of the limited number of subjects, their homogeneity (all asymptomatic adults), and the errors introduced by marker placement on subjects’ regular clothing. Research question: How a new human pose dataset, adapted for gait study, could contribute to the advancement and evaluation of marker-less motion capture systems? Methods: A marker-less system, based on deep learning-based pose estimation methods, was proposed. A new dataset (ENSAM dataset) was collected. Twenty-two asymptomatic adults, one adult with scoliosis, one adult with spondylolisthesis, and seven children with bone disease performed ten walking trials, while being recorded both by the proposed marker-less system and a reference system – combining a marker-based motion capture system and a medical imaging system (EOS). The dataset was split into training and test sets. The pose estimation method, already trained on the Human3.6 M dataset, was evaluated on the ENSAM test set, then reevaluated after further training on the ENSAM training set. The joints coordinates were evaluated, using Bland-Altman bias and 95 % confidence interval, and joint position error (the Euclidean distance between the estimated joint centers and the corresponding reference values). Results: The Bland-Altman 95 % confidence intervals were substantially improved after finetuning the pose estimation method on the ENSAM training set (e.g., from 106.9 mm to 17.4 mm for the hip joint). With the new dataset and approach, the mean joint position error varied from 6.2 mm for ankles to 21.1 mm for shoulders. Significance: The proposed marker-less system achieved promising results in terms of joint position errors. Future studies are necessary to assess the system in terms of gait parameters.

Files in this item

Name:
IBHGC_GAIPOS_VAFADAR_2021.pdf
Size:
751.9Kb
Format:
PDF
Embargoed until:
2022-05-01
View/Open

Collections

  • Institut de Biomécanique Humaine Georges Charpak (IBHGC)

Related items

Showing items related by title, author, creator and subject.

  • Assessment of a novel deep learning-based marker-less motion capture system for gait study 
    Article dans une revue avec comité de lecture
    VAFADAR, Saman; ccSKALLI, Wafa; BONNET-LEBRUN, Aurore; ASSI, Ayman; ccGAJNY, Laurent (Elsevier BV, 2022-05)
    Background. Marker-less systems based on digital video cameras and deep learning for gait analysis could have a deep impact in clinical routine. A recently developed system has shown promising results in terms of joint ...
  • Fast quasi-automated 3D reconstruction of lower limbs from low dose biplanar radiographs using statistical shape models and contour matching 
    Article dans une revue avec comité de lecture
    GIRINON, François; BAYOUD, Wael; LAHKAR, Bhrigu; BONNET-LEBRUN, Aurore; LAZENNEC, Jean-Yves; ccSKALLI, Wafa; ccROUCH, Philippe; ccGAJNY, Laurent (Elsevier BV, 2022-03)
    Three-dimensional bone reconstructions from medical imaging are essential for biomechanical modelling and are growing tools in clinics. Several methods of lower limbs reconstruction from biplanar radiographs have ...
  • Full-body Postural Alignment Analysis Through Barycentremetry 
    Article dans une revue avec comité de lecture
    KHALIFE, Marc; ccVERGARI, Claudio; ASSI, Ayman; ccGUIGUI, Pierre; ccATTALI, Valerie; VALENTIN, Rémi; VAFADAR, Saman; FERRERO, Emmanuelle; ccSKALLI, Wafa (Wolters Kluwer Health Inc., 2024-04)
    Study design: Multicentric retrospective. Objective: The study of center of mass (COM) locations (i.e. barycentremetry) can help us understand postural alignment. ...
  • Quantitative analysis of lower limb and pelvic deformities in children with X-linked hypophosphatemic rickets 
    Article dans une revue avec comité de lecture
    ccBONNET-LEBRUN, Aurore; ccLINGLART, Agnès; DE TIENDA, Marine; OUCHRIF, Younes; BERKENOU, Jugurtha; ASSI, Ayman; WICART, Philippe; ccSKALLI, Wafa (Elsevier BV, 2021-12)
    Introduction X-linked hypophosphatemia (XLH) rickets mainly causes leg deformities in children that can get worse as they grow. We hypothesized that quantifying the bone parameters will help to document and monitor these ...
  • Combined gait analysis and radiologic examination in children with X-linked hypophosphatemia 
    Article dans une revue avec comité de lecture
    ccBONNET-LEBRUN, Aurore; ccLINGLART, Agnès; ccDE TIENDA, Marine; NGUYEN KHAC, Virginie; ccOUCHRIF, Younes; BERKENOU, Jugurtha; ccPILLET, Helene; ASSI, Ayman; WICART, Philippe; ccSKALLI, Wafa (Elsevier Ltd, 2023-04)
    Background: X-linked hypophosphataemia causes bone deformities and gait abnormalities that tend to worsen with age in the absence of appropriate treatment. However, doctors do not currently use quantitative tools to ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales