Search research articles

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

Energy Expenditure During Walking With a Novel Treadmill Controller That Induces Gait Asymmetry.

bioRxiv : the preprint server for biology·2026

Same author

Changes in interlimb coordination induced by within-stride changes in treadmill speed.

Journal of neurophysiology·2026

Same author

Task demands shift motor learning from adaptation to feedback control in a naturalistic bimanual task.

bioRxiv : the preprint server for biology·2026

Same author

Quantifying Repetitive Hand Flapping Kinematics in Autistic and Non-Autistic Toddlers Using Video-Based Pose Estimation.

Developmental science·2026

Same author

Automatic learning mechanisms for flexible human locomotion.

eLife·2026

Same author

Self-Reported Acceptance of a Wearable Activity Monitor in Persons With Stroke: Usability Study.

JMIR cardio·2025

Same journal

Another 10 years of PLOS Computational Biology: A data-driven reflection on trends in genomics research.

PLoS computational biology·2026

Same journal

Mobility data resolution needed to inform predictive models of spatial epidemic spread from mobile phone data.

PLoS computational biology·2026

Same journal

DeepMethylation: A deep learning framework for tissue-specific DNA methylation prediction and functional variant annotation.

PLoS computational biology·2026

Same journal

Redefining and estimating the early-phase reproduction ratio for epidemic outbreaks in spatially structured populations.

PLoS computational biology·2026

Same journal

Optimized phenotype definitions boost GWAS power.

PLoS computational biology·2026

Same journal

Detection, communication, and individual identification with deep audio embeddings: A case study with North Atlantic right whales.

PLoS computational biology·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 8, 2025

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

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

Two-dimensional video-based analysis of human gait using pose estimation.

Jan Stenum^1,2, Cristina Rossi^1,3, Ryan T Roemmich^1,2

¹Center for Movement Studies, Kennedy Krieger Institute, Baltimore, Maryland, United States of America.

Plos Computational Biology

|April 23, 2021

Summary

This summary is machine-generated.

Markerless pose estimation using OpenPose offers a low-cost, accessible method for human gait analysis. This video-based approach accurately measures spatiotemporal and kinematic parameters, even on a stride-by-stride basis.

More Related Videos

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

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

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

Published on: March 4, 2018

Related Experiment Videos

Last Updated: Nov 8, 2025

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

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

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

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

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

Published on: March 4, 2018

Area of Science:

Biomechanics
Computer Vision
Human Movement Science

Background:

Traditional human gait analysis methods (e.g., 3D motion capture, wearables) are often costly, require specialized equipment, and are data-limited.
Advances in markerless pose estimation present an opportunity to utilize accessible 2D video for gait analysis.

Purpose of the Study:

To evaluate the accuracy of video-based pose estimation (OpenPose) for human gait analysis.
To compare spatiotemporal and sagittal kinematic gait parameters derived from OpenPose with 3D motion capture.
To introduce a freely available workflow for gait analysis from video.

Main Methods:

Compared OpenPose markerless pose estimation with 3D motion capture for overground walking in healthy adults.
Analyzed spatiotemporal parameters (step time, stance time, swing time, double support time, step length) and sagittal kinematic angles (hip, knee, ankle).
Calculated errors on a stride-by-stride basis and as individual participant mean values.

Main Results:

Mean absolute errors for temporal gait parameters were 0.02s (stride-by-stride) and 0.01s (participant mean).
Mean absolute errors for step lengths were 0.049m (stride-by-stride) and 0.018m (participant mean).
Mean absolute errors for sagittal hip, knee, and ankle angles were 4.0°, 5.6°, and 7.4°, respectively.

Conclusions:

Video-based pose estimation (OpenPose) provides a viable, accurate alternative for human gait analysis.
The developed workflow is accessible, requires minimal expertise, and can be applied to various gait parameters.
This approach has significant potential for clinical and research applications, democratizing gait analysis.