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

Search research articles

Related Experiment Video

Updated: Jan 18, 2026

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

Development of Marker-Based Motion Capture Using RGB Cameras: A Neural Network Approach for Spherical Marker

¹Faculty of Human Health, Kurume University, 1635 Miichou, Kurume 839-0851, Fukuoka, Japan.

Sensors (Basel, Switzerland)

|September 13, 2025

Summary

This study introduces a cost-effective marker-based motion capture system using RGB cameras and a neural network (NN) model. The system accurately estimates marker coordinates, offering a viable alternative to expensive infrared systems for motion analysis.

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

Wand-Based Calibration Accuracy for Unsynchronized Multicamera Systems Without Timestamps.

Sensors (Basel, Switzerland)·2026

Same author

The Location of the Center of Pressure on the Starting Block Is Related to Sprint Start Performance.

Frontiers in sports and active living·2020

Same author

Improvement in sprint start performance by modulating an initial loading location on the starting blocks.

Journal of sports sciences·2020

Same author

Calculation of the centre of pressure on the athletic starting block.

Sports biomechanics·2019

Same author

Comparación de la efectividad de ranibizumab intravítreo para el tratamiento del edema macular diabético en ojos vitrectomizados y no vitrectomizados.

Ophthalmologica. Journal international d'ophtalmologie. International journal of ophthalmology. Zeitschrift fur Augenheilkunde·2017

Same author

Comparison of the Effectiveness of Intravitreal Ranibizumab for Diabetic Macular Edema in Vitrectomized and Nonvitrectomized Eyes.

Ophthalmologica. Journal international d'ophtalmologie. International journal of ophthalmology. Zeitschrift fur Augenheilkunde·2016

Area of Science:

Biomechanics
Computer Vision
Machine Learning

Background:

Marker-based motion capture systems, typically using infrared cameras (IR MoCaps), are crucial in biomechanical research but are often prohibitively expensive.
High costs limit the widespread implementation of advanced motion capture technologies in many research institutions.

Purpose of the Study:

To develop a cost-effective marker-based motion capture system utilizing RGB cameras.
To create a neural network (NN) model for accurately estimating the digitized coordinates of spherical markers.

Main Methods:

A neural network model was trained using virtual markers inserted into RGB images from non-marker trials.
Eight RGB cameras recorded 13 participants walking, with and without markers on 25 body landmarks.

Keywords:

YOLO human motion measurement object detection

More Related Videos

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Jan 18, 2026

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

The NN model detected spherical markers, and their 3D coordinates were reconstructed and compared to a gold standard.

Main Results:

The developed NN model demonstrated proficiency in detecting spherical markers from RGB camera footage.
The reconstructed 3D marker coordinates achieved a mean resultant error of 2.2 mm when compared to the gold standard.
The system achieved automatic marker reconstruction comparable to traditional IR MoCap systems.

Conclusions:

The proposed method offers a lower-cost, fully automatic marker reconstruction solution for motion analysis.
This approach provides a viable and accurate alternative to expensive IR MoCap systems.
The technology holds significant potential for broader application in various fields of motion analysis.