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 Videos

Real-time markerless tracking for augmented reality: the virtual visual servoing framework.

Andrew I Comport1, Eric Marchand, Muriel Pressigout

  • 1IRISA-INRIA Rennes, France. Andrew.Comport@sophia.inria.fr

IEEE Transactions on Visualization and Computer Graphics
|June 30, 2006
PubMed
Summary

This study introduces a real-time 3D model-based tracking algorithm for augmented reality (AR) systems. The novel approach enhances accuracy and reduces latency for robust object pose estimation in challenging visual conditions.

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

Optimizing COPD Care in Belgium: A Multidisciplinary Expert Consensus on Cardiopulmonary Risk Management.

International journal of chronic obstructive pulmonary disease·2026
Same author

Assessing Geriatric Competencies in Residents: Validating the 5Ms Dimensions.

Journal of graduate medical education·2025
Same author

Transcatheter mitral valve repair with MitraClip® enabling single lung transplantation: A case report.

Heliyon·2025
Same author

Optimizing ozone treatment for pathogen removal and disinfection by-product control for potable reuse at pilot-scale.

Chemosphere·2024
Same author

Visuo-Haptic Rendering of the Hand during 3D Manipulation in Augmented Reality.

IEEE transactions on haptics·2024
Same author

[The forced oscillation technique in the functional evaluation of COPD dyspnea].

Revue des maladies respiratoires·2022

Area of Science:

  • Computer Vision
  • Augmented Reality
  • Robotics

Background:

  • Real-time tracking is crucial for augmented reality (AR) applications.
  • Existing trackers often face challenges with accuracy, latency, and cost.
  • Monocular vision systems require efficient pose estimation for virtual object integration.

Purpose of the Study:

  • To propose a real-time, robust, and efficient 3D model-based tracking algorithm for monocular vision systems.
  • To address the need for high accuracy and low latency in AR tracking.
  • To extend the method for 3D model-free augmented reality scenarios.

Main Methods:

  • Nonlinear pose estimation using a virtual visual servoing approach.
  • Derivation of point-to-curves interaction matrices for 3D geometrical primitives (lines, circles, cylinders, spheres).

Related Experiment Videos

  • Integration of a local moving edges tracker and an M-estimator with iteratively reweighted least squares for robustness.

    • Main Results:

    • The algorithm achieves real-time object pose estimation for virtual object projection.
    • Demonstrated robustness to occlusion, illumination changes, and mistracking in complex outdoor sequences.
    • Successful extension to 3D model-free augmented reality problems.

    Conclusions:

    • The proposed tracking algorithm offers a robust and efficient solution for real-time AR.
    • The method provides accurate pose estimation essential for seamless virtual object integration.
    • Validated performance in challenging real-world conditions, including outdoor environments.