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 Experiment Video

Updated: May 9, 2026

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

Model-based reinforcement of Kinect depth data for human motion capture applications.

Luis Vicente Calderita1, Juan Pedro Bandera, Pablo Bustos

  • 1Polythecnic School of Cáceres, University of Extremadura, Cáceres 10003, Spain. lvcalderita@unex.es

Sensors (Basel, Switzerland)
|July 13, 2013
PubMed
Summary

New motion capture systems offer real-time human pose tracking. This study introduces a model-based generator to improve pose validity by enforcing constraints and filtering noise, enhancing OpenNI tracker performance efficiently.

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

Motor Competence Profiles in Greek Primary School Children: A Cross-Sectional Multilevel Analysis of Skill-Specific and Contextual Variability.

Children (Basel, Switzerland)·2026
Same author

Optimal sigmoid function models for analysis of transspinal evoked potential recruitment curves recorded from different muscles.

PloS one·2025
Same author

Interactions between arm and leg neuronal circuits following paired cervical and lumbosacral transspinal stimulation in healthy humans.

Experimental brain research·2024
Same author

Enhancing Robotic Perception through Synchronized Simulation and Physical Common-Sense Reasoning.

Sensors (Basel, Switzerland)·2024
Same author

Tapping into the human spinal locomotor centres with transspinal stimulation.

Scientific reports·2024
Same author

Soleus H-reflex amplitude modulation during walking remains physiological during transspinal stimulation in humans.

Experimental brain research·2024

Area of Science:

  • Computer Vision
  • Human-Computer Interaction
  • Robotics

Background:

  • Advancements in depth sensors and open-source frameworks like OpenNI enable non-invasive, real-time human motion capture.
  • Current systems often lack robust evaluation of the captured human pose's validity.
  • There is a need for improved accuracy and reliability in markerless motion tracking systems.

Purpose of the Study:

  • To enhance the accuracy and validity of human poses captured by markerless motion systems.
  • To develop a system that complements existing human trackers, like OpenNI, by enforcing kinematic constraints.
  • To reduce sensor noise and eliminate unrealistic poses in real-time motion capture.

Main Methods:

  • Integration of a model-based pose generator with the OpenNI human tracker.

Related Experiment Videos

Last Updated: May 9, 2026

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

  • Implementation of a kinematics-based filter to enforce joint constraints and body proportions.
  • Utilizing a PrimeSense depth sensor for data acquisition.
  • Learning the performer's body dimensions for personalized tracking.

    • Main Results:

    • The proposed system significantly improves the quality of human poses compared to using OpenNI alone.
    • Effectively enforces kinematic constraints, leading to more natural and valid poses.
    • Successfully filters sensor noise and eliminates erroneous or odd poses.
    • Achieves these improvements with minimal computational overhead.

    Conclusions:

    • The developed model-based pose generator effectively enhances markerless human motion capture systems.
    • The system provides a computationally efficient solution for improving pose validity and reliability.
    • This approach offers a practical method for more accurate real-time human pose estimation.