Search research 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

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

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026

Same author

[Functional characteristics of the SACE_2701-2702 transport system in <i>Saccharopolyspora erythraea</i> and its impact on erythromycin biosynthesis].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026

Same author

Prenatal exposure to mixed toxic metals and childhood blood pressure: the mediating role of amino acid and carnitine metabolism.

Environmental pollution (Barking, Essex : 1987)·2026

Same author

SA-RAG: Structured and adaptive retrieval-augmented generation for multi-hop question answering.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Diterpene Synthases as Gatekeepers of Bioactive Diterpenoids: A Resource for Discovery and Engineering toward Efficient Synthesis.

ACS synthetic biology·2026

Same author

Tensor decomposition of transportation temporal and spatial big data: A brief review.

Fundamental research·2026

Search research articles

Related Experiment Video

Updated: Nov 19, 2025

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

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

Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks.

Yanxiang Wang, Xian Zhang, Yiran Shen

IEEE Transactions on Pattern Analysis and Machine Intelligence

|January 27, 2021

Summary

This summary is machine-generated.

Event cameras offer advantages for vision tasks but produce event-streams. This study proposes graph and image-like representations for event-based gait recognition, finding image-like methods superior with limited data.

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 19, 2025

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

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

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Computer Vision
Biometrics
Machine Learning

Background:

Dynamic vision sensors (event cameras) offer advantages like low power and high temporal resolution over traditional RGB sensors.
Event cameras generate asynchronous event-streams, posing challenges for conventional computer vision algorithms.
Effective representation of event-streams is crucial for leveraging deep learning in event-based vision tasks.

Purpose of the Study:

To investigate suitable representations for event-streams in event-based human gait identification.
To propose and evaluate novel deep learning approaches for gait recognition using event-camera data.
To compare the performance of graph-based and image-like representations for event-based gait recognition.

Main Methods:

Developed two event-based gait recognition approaches: EV-Gait-3DGraph using graph representations and Graph Convolutional Networks (GCN), and EV-Gait-IMG using image-like representations and Convolutional Neural Networks (CNN).
Created two event-based gait datasets: one from real-world experiments and another by converting the CASIA-B RGB gait dataset.
Evaluated the proposed methods on the collected datasets.

Main Results:

EV-Gait-3DGraph demonstrated significantly higher recognition accuracy with sufficient training data compared to other methods.
EV-Gait-IMG exhibited faster convergence during training and achieved good accuracy with limited training samples (less than ten).
The study highlights a trade-off between accuracy and data requirements for different representations.

Conclusions:

Graph and image-like representations offer distinct advantages for event-based gait recognition using deep learning.
Image-like representations are preferable for gait recognition when training data is scarce due to faster convergence and good performance.
The proposed methods advance the application of event cameras in biometric identification tasks.