Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Assessing the Impact of Virtual Reality, Augmented Reality, and Video Games on Improving Post-Traumatic Stress Disorder Symptoms: A Systematic Review and Meta-Analysis.

Inquiry : a journal of medical care organization, provision and financing·2026
Same author

The Newer, the More Secure? Standards-Compliant Bluetooth Low Energy Man-in-the-Middle Attacks on Fitness Trackers.

Sensors (Basel, Switzerland)·2025
Same author

Generisch-Net: A Generic Deep Model for Analyzing Human Motion with Wearable Sensors in the Internet of Health Things.

Sensors (Basel, Switzerland)·2024
Same author

An Efficient 3D Human Pose Retrieval and Reconstruction from 2D Image-Based Landmarks.

Sensors (Basel, Switzerland)·2021
Same author

Keys for Action: An Efficient Keyframe-Based Approach for 3D Action Recognition Using a Deep Neural Network.

Sensors (Basel, Switzerland)·2020

Related Experiment Video

Updated: Aug 2, 2025

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K

An Effective and Efficient Approach for 3D Recovery of Human Motion Capture Data.

Hashim Yasin1, Saba Ghani1, Björn Krüger2

  • 1Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad 44000, Pakistan.

Sensors (Basel, Switzerland)
|April 13, 2023
PubMed
Summary

This study introduces a novel data-driven method to restore corrupted motion capture data using a GPU-accelerated knowledge base and nearest neighbor search. The approach effectively recovers 3D motion trajectories with minimal errors, outperforming existing methods.

Keywords:
3D recoveryGPUK-nearest neighborshuman motion capturekd-treemissing joints or markersoptimization

More Related Videos

Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion
09:32

Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion

Published on: April 11, 2018

9.8K
Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
08:45

Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

Published on: March 28, 2018

10.7K

Related Experiment Videos

Last Updated: Aug 2, 2025

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K
Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion
09:32

Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion

Published on: April 11, 2018

9.8K
Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
08:45

Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

Published on: March 28, 2018

10.7K

Area of Science:

  • Computer Vision
  • Biomechanical Engineering
  • Data Science

Background:

  • Motion capture data is crucial for animation, sports analysis, and robotics.
  • Missing or corrupted data presents a significant challenge in motion capture analysis.
  • Existing methods often lack efficiency or accuracy in data recovery.

Purpose of the Study:

  • To develop a novel data-driven approach for recovering missing or corrupted 3D motion capture data.
  • To leverage GPU parallel processing for efficient knowledge-base construction and data retrieval.
  • To enhance the accuracy and reliability of motion data reconstruction.

Main Methods:

  • Construction of a knowledge base with prior motion capture data.
  • Parallel GPU-based k-d tree for efficient nearest neighbor search.
  • Utilization of histograms and radix sort for data organization and retrieval.
  • An objective function with multiple error terms for robust 3D trajectory recovery.

Main Results:

  • Successful quantitative and qualitative evaluation on CMU and HDM05 datasets.
  • High recovery accuracy for actions like boxing, running, and acrobatics.
  • Slightly larger errors observed for kicking and jumping motions, but overall superior performance.
  • Outperforms state-of-the-art methods in most test cases with minimal user interaction.

Conclusions:

  • The proposed data-driven approach effectively recovers corrupted motion capture data.
  • GPU parallelization significantly enhances the efficiency of the recovery process.
  • The method demonstrates state-of-the-art performance and reliability across various motion sequences.