Search research articles

Search research articles

Related Experiment Video

Updated: Dec 27, 2025

Physical Activity Measurement in Children Accepting Table Tennis Training

Physical Activity Measurement in Children Accepting Table Tennis Training

Published on: July 27, 2022

Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera.

Aston K McCullough^1,2, Melanie Rodriguez¹, Carol Ewing Garber¹

¹Department of Biobehavioral Sciences, Teachers College, Columbia University, New York, NY 10027, USA.

Sensors (Basel, Switzerland)

|February 26, 2020

Summary

This summary is machine-generated.

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

The Components of Physical Fitness in Adults: A Roundtable Statement by the American College of Sports Medicine.

Medicine and science in sports and exercise·2026

Same author

Microneedling for Cutaneous Manifestations of Autoimmune Disease: A Scoping Review.

Cureus·2026

Same author

NG2-targeting macrophages inhibit 3D invasion of patient-derived glioblastoma spheroids.

bioRxiv : the preprint server for biology·2026

Same author

The Lifetime Dance Exposure Questionnaire for Professional Training: Survey Development and Reliability Study.

Interactive journal of medical research·2026

Same author

Skin Blood Flowmotion in Various Disease States: A Scoping Review.

Cureus·2026

Same author

Targeting HIF-2α in renal cell carcinoma: Expanding upon belzutifan.

Cancer·2026

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

Three-dimensional video and computer vision accurately estimate physical activity (PA) intensities in young children. This technology reliably measures sedentary, light, and moderate-to-vigorous PA levels during indoor play.

Area of Science:

Pediatrics
Biomedical Engineering
Kinesiology

Background:

Accurate measurement of physical activity (PA) in young children is crucial for understanding health behaviors.
Traditional methods for assessing PA intensity can be burdensome or impractical for this age group.
Novel technologies like 3D video and computer vision offer potential for objective and unobtrusive PA assessment.

Purpose of the Study:

To evaluate the feasibility and validity of using 3D video data and computer vision to estimate physical activity intensities in children aged 2-5 years.
To compare computer vision-derived PA intensity data with direct observation as a ground truth.
To determine the classification accuracy of a computer vision algorithm for different PA intensities.

Main Methods:

Keywords:

algorithms computer vision systems machine learning play

More Related Videos

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

Published on: February 12, 2018

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

Related Experiment Videos

Last Updated: Dec 27, 2025

Physical Activity Measurement in Children Accepting Table Tennis Training

Physical Activity Measurement in Children Accepting Table Tennis Training

Published on: July 27, 2022

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

Published on: February 12, 2018

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

Children (n=10, aged 2-5 years) participated in 20-minute semi-structured indoor play sessions.

Physical activity was recorded using a 3D camera.

3D video data were processed using computer vision to derive triaxial accelerations, and analyzed using a Classification and Regression Tree (CART) algorithm. Direct observation served as the ground truth.

Main Results:

The CART algorithm demonstrated high accuracy in classifying PA intensity: sedentary (AUC=0.89), light PA (AUC=0.87), and moderate-to-vigorous PA (AUC=0.92).
No significant differences were found between directly observed and computer vision-estimated proportions of time spent in each PA intensity (p > 0.05).
The study confirmed the feasibility of using 3D video and computer vision for PA intensity estimation.

Conclusions:

A computer vision algorithm utilizing 3D camera data is a valid and feasible method for estimating physical activity intensities in young children during indoor play.
This technology can accurately quantify the proportion of time children spend in sedentary, light, and moderate-to-vigorous physical activity.
This approach offers a promising tool for objective and detailed assessment of children's physical activity in research and clinical settings.