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

In Situ Growth of Stable (DPPM)<sub>2</sub>Cu<sub>4</sub>I<sub>4</sub>@TPU Flexible Scintillator Films.

Sensors (Basel, Switzerland)·2026
Same author

Predicting disease relapse in plaque psoriasis patients treated with secukinumab: A multicenter retrospective cohort study.

Chinese medical journal·2026
Same author

Amino acid substitutions at the G118 hotspot in dihydroorotate dehydrogenase confer olorofim resistance in <i>Aspergillus flavus</i>.

Microbiology spectrum·2026
Same author

Metabolic reprogramming landscape orchestrating chlamydospore formation in <i>Volvariella volvacea</i>.

Frontiers in microbiology·2026
Same author

Prevalence of sarcopenia in patients with rheumatoid arthritis: a cross-sectional study.

RMD open·2026
Same author

Dynamic shifts in cutaneous bacterial and fungal communities throughout human aging: a pilot study.

BMC microbiology·2026

Related Experiment Video

Updated: Jun 13, 2025

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.7K

MFCF-Gait: Small Silhouette-Sensitive Gait Recognition Algorithm Based on Multi-Scale Feature Cross-Fusion.

Chenyang Song1,2, Lijun Yun1,2, Ruoyu Li1,2

  • 1College of Information, Yunnan Normal University, Kunming 650500, China.

Sensors (Basel, Switzerland)
|September 14, 2024
PubMed
Summary

This study introduces a new gait recognition system (MFCF-Gait) that improves accuracy for smaller silhouette images using super-resolution and multi-scale feature fusion. Enhanced performance was demonstrated on the CASIA-B dataset.

Keywords:
deep learningfeature fusiongaitgait recognitionsuper-resolution

More Related Videos

Automated Gait Analysis in Mice with Chronic Constriction Injury
06:49

Automated Gait Analysis in Mice with Chronic Constriction Injury

Published on: October 17, 2017

10.1K
Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits
06:25

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

8.4K

Related Experiment Videos

Last Updated: Jun 13, 2025

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.7K
Automated Gait Analysis in Mice with Chronic Constriction Injury
06:49

Automated Gait Analysis in Mice with Chronic Constriction Injury

Published on: October 17, 2017

10.1K
Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits
06:25

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

8.4K

Area of Science:

  • Computer Vision
  • Biometrics
  • Pattern Recognition

Background:

  • Gait recognition commonly uses 64x64 pixel gait silhouette images.
  • Smaller input images lead to information loss and reduced accuracy.
  • Existing methods struggle with variable input resolutions.

Purpose of the Study:

  • To develop a robust gait recognition system for varying silhouette image sizes.
  • To enhance recognition accuracy for low-resolution gait data.
  • To address the limitations of fixed-size input in current gait recognition models.

Main Methods:

  • Proposed Multi-scale Feature Cross-Fusion Gait (MFCF-Gait) system.
  • Utilized super-resolution algorithms for input data preprocessing.
  • Introduced a multi-scale feature cross-fusion network architecture.

Main Results:

  • Significant accuracy improvements on the CASIA-B dataset for smaller images (32x32).
  • Achieved 94.23% (NM), 87.68% (BG), and 71.57% (CL) accuracy on 32x32 images.
  • Maintained high accuracy on standard 64x64 images (96.49% NM, 91.42% BG, 78.24% CL).

Conclusions:

  • MFCF-Gait effectively handles variations in gait silhouette image resolution.
  • Super-resolution and multi-scale fusion are crucial for recognizing smaller gait patterns.
  • The proposed system offers a promising solution for real-world gait recognition challenges.