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 Experiment Video

Updated: Jul 15, 2025

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

Gait analysis comparison between manual marking, 2D pose estimation algorithms, and 3D marker-based system.

Dimitrios Menychtas1, Nikolaos Petrou1, Ioannis Kansizoglou2

  • 1Biomechanics Laboratory, Department of Physical Education and Sports Science, Democritus University of Thrace, Komotini, Greece.

Frontiers in Rehabilitation Sciences
|September 25, 2023
PubMed
Summary

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

Agreement Between Standing Eight-Point Multifrequency Bioelectrical Impedance Analysis and Dual-Energy X-Ray Absorptiometry for Body Composition Assessment in Apparently Healthy Greek Adults.

Healthcare (Basel, Switzerland)·2026
Same author

Physical Activity During Official Match Play in Female Masters Basketball Players: An Accelerometry-Based Study.

Sports (Basel, Switzerland)·2026
Same author

Injury Prediction and Risk Modelling in Team Sports Using Artificial Intelligence and Sensor-Based Monitoring: A Scoping Review.

Journal of functional morphology and kinesiology·2026
Same author

Impact of swimming intensity on spatiotemporal kinematics of lower-limb breaststroke actions in national-level male swimmers: A discrete variable and time-series analysis.

Journal of biomechanics·2026
Same author

Convolutional Neural Network for Specimen-Invariant Structural Health Monitoring of FRC Under Flexural Loading.

Sensors (Basel, Switzerland)·2026
Same author

Explainable Machine Learning Reveals Time-Dependent Cognitive Risk in Minor Neurocognitive Disorder: Implications for Health Promotion and Early Risk Stratification.

Biomedicines·2026

AI pose estimation shows promise for gait analysis but struggles with small joint movements. An AI tool allowing error correction could make advanced kinematic measurements accessible to health professionals.

Area of Science:

  • Biomechanics
  • Artificial Intelligence
  • Computer Vision

Background:

  • Automated pose estimation using AI and Computer Vision (CV) offers potential for kinematic measurements from 2D videos, reducing reliance on expensive equipment.
  • Despite advancements, AI pose estimation algorithms are not widely adopted by health professionals due to erratic outputs and difficult error correction.
  • Manual video annotation tools are still prevalent, though less efficient and cost-effective than potential automated solutions.

Purpose of the Study:

  • To evaluate the accuracy of AI pose estimation algorithms (OpenPose and Mediapipe) for analyzing the gait cycle in the elderly population.
  • To compare AI pose estimation against a marker-based 3D motion capture system (Vicon) and a manual biomechanics tool (Kinovea).
  • To identify specific limitations of AI pose estimation in capturing subtle joint kinematics.
Keywords:
2D pose estimationbiomechanicsbiomechanics video annotationjoint angle comparisonmotion analysis

More Related Videos

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K
Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.4K

Related Experiment Videos

Last Updated: Jul 15, 2025

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
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K
Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.4K

Main Methods:

  • Gait cycle analysis of elderly individuals on a split-belt treadmill.
  • Comparison of OpenPose (OP) and Mediapipe (MP) AI algorithms against Vicon 3D motion capture and Kinovea manual annotation.
  • Statistical analysis using Bland-Altman plots and Statistical Parametric Mapping (SPM) to detect significant differences.

Main Results:

  • AI pose estimation demonstrated comparable motion tracking to marker-based systems for overall gait.
  • AI algorithms struggled to accurately identify joints with small, critical motions, such as the ankle.
  • Misidentification of anatomical landmarks in small joints was observed, unlike in manual annotation methods.

Conclusions:

  • AI pose estimation shows potential for accessible gait analysis but requires improvement for precise small joint motion tracking.
  • Manual tools, while reliable for landmark identification, introduce user-dependent static offsets.
  • Developing an AI-powered annotation tool with user correction capabilities could bridge the gap, offering cost-effective and accurate kinematic measurements for health professionals.