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

Corrigendum to "Automatic liver Couinaud segmentation from computed tomography scans with a gradient-enhanced hierarchical cascade deep learning network" [Current Problems in Surgery 75 (2026) 101957].

Current problems in surgery·2026

Same author

Deep Learning-Based Liver Tumor Segmentation from Computed Tomography Scans with a Gradient-Enhanced Network.

Diagnostics (Basel, Switzerland)·2026

Same author

Automatic liver Couinaud segmentation from computed tomography scans with a gradient-enhanced hierarchical cascade deep learning network.

Current problems in surgery·2026

Same author

The effects of body mass index on foot shape among U.S. children.

Applied ergonomics·2026

Same author

Where healing begins: The role of positive childhood experiences (PCEs) in recovery from anxiety and depression among adolescents.

Journal of affective disorders·2026

Same author

Longitudinal Relationships Among Post-Traumatic Stress Disorder Symptoms, Non-Suicidal Self-Injury Severity, and Suicidality in Korean Adolescents: A Cross-Lagged Panel Analysis.

Omega·2025

Search research articles

Related Experiment Video

Updated: Jul 4, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Optimising computer vision-based ergonomic assessments: sensitivity to camera position and monocular 3D pose model.

Aditya Subramani Murugan¹, Gijeong Noh^1,2, Hayoung Jung³

¹Department of Mechanical, Automotive, and Materials Engineering, University of Windsor, Ontario, Canada.

|January 31, 2024

Summary

For precise ergonomic evaluations, a side camera position is optimal. VideoPose3D (VP3D_FB) proved most effective among tested computer vision algorithms for posture analysis.

Keywords:

3D pose model Ergonomic assessment RULA computer vision

More Related Videos

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

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

Related Experiment Videos

Last Updated: Jul 4, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

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

Area of Science:

Computer Vision
Ergonomics
Biomechanics

Background:

Automated posture analysis using computer vision enhances ergonomic evaluations.
The optimal algorithm and camera setup for accurate ergonomic assessments remain unclear.

Purpose of the Study:

Identify the best camera position and monocular 3D pose model for precise ergonomic evaluations.
Compare the performance of four leading computer vision algorithms: Mediapipe BlazePose, VideoPose3D, 3D-pose-baseline, and PSTMO.

Main Methods:

Evaluated four computer vision algorithms for 3D human pose estimation.
Assessed algorithm performance across static, dynamic, and combined tasks.
Determined optimal camera positioning (e.g., side view) for ergonomic assessments.

Main Results:

The side camera position consistently yielded the lowest Mean Absolute Error (MAE) across all task types.
VideoPose3D (VP3D_FB) demonstrated superior accuracy and reliability compared to other evaluated models.
Side camera positioning is recommended for dependable ergonomic evaluations.

Conclusions:

A side camera perspective combined with the VideoPose3D algorithm offers the most accurate and efficient approach for computer vision-based ergonomic assessments.
This combination enhances the precision of posture analysis in occupational settings.