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: May 13, 2026

Video Movement Analysis Using Smartphones (ViMAS): A Pilot Study

Video Movement Analysis Using Smartphones (ViMAS): A Pilot Study

Published on: March 14, 2017

Machine learning classifiers for automatic classification of foot strike patterns from 2D video.

Torstein E Dæhlin¹, Caleb D Johnson², Stephen A Foulis²

¹School of Physical Therapy and Rehabilitation Sciences, University of South Florida, Tampa, FL, USA.

Sports Biomechanics

|May 12, 2026

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

Genetic Risk Scores are Related to Bone Microarchitecture in US Army Basic Training.

Journal of applied physiology (Bethesda, Md. : 1985)·2026

Same author

Core Content Related to Teaching Biomechanical Aspects of Human Movement for Physical Therapist Students: A Modified Delphi Study.

Journal, physical therapy education·2026

Same author

Sex- and site-specific associations between hemoglobin levels and cortical bone structure and microarchitecture in older adults.

Bone·2026

Same author

HR-pQCT skeletal phenotype clustering associated with muscle function in older men and women: The Study of Muscle, Mobility and Aging (SOMMA).

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2026

Same author

Inflammation and alterations in redox homeostasis precede and persist following musculoskeletal injury in US army trainees.

British journal of sports medicine·2026

Same author

Sex-Specific Associations of Radiographic Knee Osteoarthritis and Pain with Distal Tibia Bone Microarchitecture: the Study of Muscle, Mobility and Aging (SOMMA).

Calcified tissue international·2026

Same journal

The association between running velocity, cadence, and tibial acceleration in recreational runners in an outdoor environment.

Sports biomechanics·2026

Same journal

No extra sensors needed: estimating vertical ground reaction force using IMUs at the smartwatch and heartrate strap location.

Sports biomechanics·2026

Same journal

Validity of using a smartphone-based markerless motion capture system for quantitative analysis of human dynamic movements.

Sports biomechanics·2026

Same journal

Rugby tackle kinematics in adolescent players: effects of tackle height and shoulder side.

Sports biomechanics·2026

Same journal

Baseball has an elbow injury problem: biomechanics may have the solution.

Sports biomechanics·2026

Same journal

Synergy structure and distribution mechanism of joint moments in the landing leg during tennis pinpoint serve.

Sports biomechanics·2026

See all related articles

Machine learning accurately classifies running foot strike patterns (forefoot, midfoot, rearfoot) from video, outperforming traditional cut-point methods. This technology offers a practical tool for analyzing running biomechanics.

Area of Science:

Biomechanics
Machine Learning
Sports Science

Background:

Automatic classification of running foot strike patterns (forefoot, midfoot, rearfoot) using video data is challenging.
Existing cut-point methods have limitations in accuracy.

Purpose of the Study:

To evaluate machine learning classifiers for automatic foot strike pattern classification.
To compare the performance of machine learning models against established cut-point methods.

Main Methods:

Video data from 767 U.S. Army trainees running on a treadmill were analyzed.
DeepLabCut identified key foot landmarks to compute kinematic variables.
Three machine learning algorithms were trained and tested on the data.

Main Results:

Keywords:

2D video analysis Foot strike classification artificial intelligence running technique

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Related Experiment Videos

Last Updated: May 13, 2026

Video Movement Analysis Using Smartphones (ViMAS): A Pilot Study

Video Movement Analysis Using Smartphones (ViMAS): A Pilot Study

Published on: March 14, 2017

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

The best-performing machine learning classifier achieved a 70.0% F1 score.
Machine learning outperformed cut-point methods (66.7%, 68.9%, 53.0% F1 scores) in classification accuracy.
The classifier showed improved performance in identifying midfoot strikes.

Conclusions:

Machine learning algorithms demonstrate potential as accurate and practical tools for automatic foot strike pattern classification.
This approach may enhance the analysis of running biomechanics and injury prevention strategies.