Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hydrogen-Bond Network Collapse and Molecular Confinement in Ethanol-Water Mixtures at the Azeotrope.

The journal of physical chemistry letters·2026
Same author

High-impact physical activity participation and 12-month risk of joint replacement: a longitudinal mediation analysis of 17 661 patients with knee or hip osteoarthritis.

British journal of sports medicine·2026
Same author

[Metabolic engineering of <i>Escherichia coli</i> for l- threonine synthesis with glucose and formate as co-substrates].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026
Same author

[Metabolic engineering of <i>Corynebacterium glutamicum</i> for glutaric acid production].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026
Same author

GM-CSF and IL-1α secreted by cryopreserved porcine skin promote angiogenesis in burn wounds by activating the JAK2/STAT3 pathway.

American journal of translational research·2026
Same author

Programming the translational landscape for predictable gene expression.

Biotechnology advances·2026

Related Experiment Video

Updated: Jul 25, 2025

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.3K

Monocular 3D Human Pose Markerless Systems for Gait Assessment.

Xuqi Zhu1, Issam Boukhennoufa1, Bernard Liew2

  • 1School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK.

Bioengineering (Basel, Switzerland)
|June 28, 2023
PubMed
Summary

This study introduces a cost-effective markerless human pose technique for clinical gait analysis using a monocular camera. The method significantly improves pose estimation accuracy, offering a promising alternative to traditional marker-based systems.

Keywords:
Kalman filtercomputer visiondeep learninggait analysismarkerlessmonocular camera

More Related Videos

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.2K
Lower-Limb Biomechanical Characteristics Associated with Unplanned Gait Termination Under Different Walking Speeds
05:52

Lower-Limb Biomechanical Characteristics Associated with Unplanned Gait Termination Under Different Walking Speeds

Published on: August 25, 2020

4.6K

Related Experiment Videos

Last Updated: Jul 25, 2025

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.3K
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.2K
Lower-Limb Biomechanical Characteristics Associated with Unplanned Gait Termination Under Different Walking Speeds
05:52

Lower-Limb Biomechanical Characteristics Associated with Unplanned Gait Termination Under Different Walking Speeds

Published on: August 25, 2020

4.6K

Area of Science:

  • Biomechanics
  • Computer Vision
  • Healthcare Technology

Background:

  • Gait analysis is crucial in healthcare and sports science.
  • Conventional methods use expensive equipment and trained personnel.
  • Advancements in computer vision offer cost-effective solutions.

Purpose of the Study:

  • To develop a markerless human pose technique for clinical gait analysis.
  • To utilize consumer-grade monocular RGB cameras for 3D human pose estimation.
  • To provide an efficient and accessible alternative to traditional gait analysis.

Main Methods:

  • Developed a markerless human pose technique using a consumer monocular camera (800x600 pixels, 30 FPS).
  • Employed deep neural networks and computer vision for 3D human pose estimation.
  • Utilized a post-processing algorithm to refine pose detection from the BlazePose model.

Main Results:

  • The proposed algorithm improved BlazePose's prediction performance by 10.7% compared to gold-standard gait signals on the MoVi dataset.
  • Achieved an excellent correlation (r=0.99) between predicted T^2 scores and ground truth.
  • Demonstrated a regression line of y = 0.94x + 0.01, indicating high accuracy.

Conclusions:

  • The developed markerless technique shows potential as an alternative to conventional marker-based gait analysis.
  • This approach can assist in clinical gait assessment with improved cost-effectiveness and efficiency.
  • The high correlation with ground truth validates the accuracy and reliability of the proposed method.