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: Jun 27, 2025

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

Multi-View Gait Analysis by Temporal Geometric Features of Human Body Parts.

Thanyamon Pattanapisont1,2, Kazunori Kotani1, Prarinya Siritanawan1

  • 1School of Information Science, Japan Advanced Institute of Science and Technology, Nomi 923-1211, Japan.

Journal of Imaging
|April 26, 2024
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

Pore growth direction in anodic oxidation: insights from Ga anodization.

Nanotechnology·2026
Same author

A scenario-driven simulation approach to sustainable hospital resource management: aging society, pandemic preparedness and referral enhancement.

BMC health services research·2025
Same author

Workplace sustainability: energy-saving behaviors in office environments of Thailand.

Frontiers in psychology·2025
Same author

A Highly Robust Encoder-Decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images.

Journal of imaging·2025
Same author

Negative frequency-dependent selection through variations in seedling fitness due to genetic differentiation of parents' pair in a tropical rainforest tree, <i>Rubroshorea curtisii</i> (Dipterocarpaceae).

Frontiers in genetics·2025
Same author

Spatiotemporal association between monthly PM2.5 levels and cardiorespiratory mortality in Thailand (2015-2019).

International journal of environmental health research·2025
This summary is machine-generated.

This study uses vision-based pose estimation for gait analysis to identify individuals. Integrating multi-camera data with a majority voting algorithm significantly improved person identification accuracy by about 30%.

Area of Science:

  • Computer Vision
  • Biometrics
  • Human Motion Analysis

Background:

  • Gait analysis, the study of walking patterns, is a key biometric for person identification.
  • Vision-based human pose estimation has emerged as a powerful tool for extracting detailed gait features.
  • Existing methods require robust feature extraction and effective fusion strategies for accurate gait recognition.

Purpose of the Study:

  • To develop and evaluate a vision-based system for accurate person identification using gait analysis.
  • To investigate the impact of different body part features (whole, upper, lower) on gait recognition performance.
  • To enhance gait analysis for potential applications in clinical, psychological, and emotional assessments.

Main Methods:

  • Utilized vision-based human pose estimation to extract joint angles from multi-view gait databases (CASIA-B, OUMVLP-Pose).
Keywords:
correlation featuredynamic time warpingmulti-view gait analysisvoting algorithm

More Related Videos

Lower Limb Biomechanical Analysis of Healthy Participants
06:36

Lower Limb Biomechanical Analysis of Healthy Participants

Published on: April 15, 2020

9.1K
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

Related Experiment Videos

Last Updated: Jun 27, 2025

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
Lower Limb Biomechanical Analysis of Healthy Participants
06:36

Lower Limb Biomechanical Analysis of Healthy Participants

Published on: April 15, 2020

9.1K
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
  • Employed Dynamic Time Warping (DTW) for calculating minimum distance in person identity matching.
  • Implemented a majority voting algorithm to fuse matching results from multiple camera views, improving accuracy.

    • Main Results:

    • Separated features into whole, upper, and lower body components to assess their individual contributions to gait analysis.
    • Demonstrated that integrating multi-camera data via majority voting enhanced person identification accuracy.
    • Achieved an approximate 30% improvement in accuracy compared to single-camera or non-fused matching methods.

    Conclusions:

    • Vision-based pose estimation combined with DTW and majority voting offers a highly effective approach for gait-based person identification.
    • Feature analysis indicates that different body segments contribute uniquely to gait recognition, offering avenues for further optimization.
    • The proposed method shows promise for expanding gait analysis beyond identification to other behavioral and health-related tasks.