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 4, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

A Wearable Motion Capture Dataset for Gait Analysis Using IMUs and Shank-Mounted Egocentric Cameras.

Md Sanzid Bin Hossain1,2, Sy Nguyen3, Joseph Dranetz3

  • 1University of Central Florida, Department of Clinical Science, Orlando, 32816, US.

Scientific Data
|July 2, 2026
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

Multi-parameter prediction of extubation failure using spontaneous breathing trial and post-spontaneous breathing trial rest period data.

Digital health·2026
Same author

Impact of Dysplasia on Inverted Papilloma Recurrence: A Systematic Review and Meta-Analysis.

International forum of allergy & rhinology·2026
Same author

Perturbation of genes linked to common schizophrenia risk variants identifies cilia programs.

bioRxiv : the preprint server for biology·2026
Same author

Pharmacological Management of Peptic Ulcer Bleeding.

The Korean journal of helicobacter and upper gastrointestinal research·2026
Same author

A mixed methods evaluation of a six-year primary care community safety net-academic partnership model.

Academic medicine : journal of the Association of American Medical Colleges·2026
Same author

Integrated Hydrochemical and isotopic fingerprints of groundwater evolution, water quality, and health risk in Northwest Bangladesh.

The Science of the total environment·2026

This study introduces a novel multimodal dataset for human walking analysis, combining wearable sensor data with precise motion capture. This resource aids machine learning and biomechanics research in understanding gait dynamics.

Area of Science:

  • Biomechanics
  • Machine Learning
  • Wearable Technology

Background:

  • Walking kinematics are crucial for assessing motor function and rehabilitation.
  • Machine learning and wearable sensors are advancing gait analysis.
  • Existing datasets lack multimodal wearable data across diverse walking conditions.

Purpose of the Study:

  • To introduce a comprehensive multimodal dataset for human walking kinematics.
  • To facilitate research in biomechanics and machine learning applications for gait analysis.
  • To provide synchronized wearable sensor and ground-truth kinematic data.

Main Methods:

  • Collected 14 walking trials from 10 healthy participants across various speeds and locomotion modes (overground, treadmill, slope, stairs).
  • Acquired synchronized data from inertial measurement units (IMUs), shank-mounted egocentric video, and optical motion capture.

Related Experiment Videos

Last Updated: Jul 4, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

  • Utilized musculoskeletal modeling to derive ground-truth joint kinematics.

    • Main Results:

    • The dataset includes 327 minutes of synchronized IMU signals, motion capture data, and joint angles.
    • Features 588k egocentric video frames per foot with Histogram of Optical Flow (HOF) features.
    • Represents the first dataset with multimodal wearable IMU and video data alongside ground-truth kinematics for diverse walking tasks.

    Conclusions:

    • This novel dataset significantly advances human gait analysis capabilities.
    • It supports a wide range of applications in biomechanics and machine learning research.
    • Enables development and validation of advanced gait assessment and rehabilitation tools.