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

Distinct Metabolic Fates of 6PPD and 6PPD-Q in Rice under Root and Foliar Exposure Pathways.

Journal of agricultural and food chemistry·2026

Same author

Assessing the Risk of Frequent Premature Ventricular Contractions in Patients with Ischemic Cardiomyopathy: Development and Validation of a Nomogram Model.

Journal of imaging informatics in medicine·2026

Same author

Systematic analysis of the mitophagy scoring system in the prognosis and immunotherapy of HCC patients.

Discover oncology·2026

Same author

Case Report: Upadacitinib treatment for Behçet's syndrome with intestinal damage.

Frontiers in medicine·2026

Same author

Case Report: A case of Fournier's gangrene of the scrotum.

Frontiers in medicine·2026

Same author

Development of immune-derived molecular markers for coronary heart disease via multimachine learning.

iScience·2026

Search research articles

Related Experiment Video

Updated: Jun 13, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Spatial and temporal attention embedded spatial temporal graph convolutional networks for skeleton based gait

Jianjun Yan¹, Weixiang Xiong¹, Li Jin²

¹Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, Shanghai 200237, China.

|September 16, 2024

Summary

This study introduces a novel skeleton-based gait recognition method using spatial-temporal graph convolutional networks and inertial measurement units (IMUs). The approach achieves high accuracy for exoskeleton robot control.

Keywords:

computer science engineering mechanics

More Related Videos

Clinical Assessment of Spatiotemporal Gait Parameters in Patients and Older Adults

Clinical Assessment of Spatiotemporal Gait Parameters in Patients and Older Adults

Published on: November 7, 2014

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Related Experiment Videos

Last Updated: Jun 13, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Clinical Assessment of Spatiotemporal Gait Parameters in Patients and Older Adults

Clinical Assessment of Spatiotemporal Gait Parameters in Patients and Older Adults

Published on: November 7, 2014

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Area of Science:

Robotics
Biomechanical Engineering
Computer Vision

Background:

Current Inertial Measurement Unit (IMU)-based gait recognition methods for exoskeleton robots lack comprehensive analysis of human spatial structure and joint interconnections.
Existing methods often rely solely on inertial data, limiting their ability to capture the full complexity of human gait dynamics.

Purpose of the Study:

To develop an advanced skeleton-based gait recognition system for enhanced exoskeleton robot control.
To improve the accuracy and robustness of gait recognition by integrating spatial-temporal information with IMU data.

Main Methods:

A novel approach utilizing spatial-temporal graph convolutional networks (ST-GCNs) with spatial and temporal attention mechanisms was proposed.
A human forward kinematics solver was employed to construct dynamic human skeleton models.
A temporal attention module was integrated to emphasize critical gait cycle time frames.

Main Results:

The proposed method achieved an average accuracy of approximately 99% in user experiments, outperforming existing algorithms.
The integration of skeleton data with IMU data through ST-GCNs significantly improved gait recognition performance.
The spatial and temporal attention mechanisms effectively captured salient features within the gait cycle.

Conclusions:

The developed skeleton-based gait recognition approach offers a significant advancement for real-time exoskeleton robot control.
This method provides a robust and highly accurate solution for recognizing human gaits, paving the way for more intuitive human-robot interaction.
The findings offer valuable insights for future research in wearable robotics and human motion analysis.