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

Registration using natural features for augmented reality systems.

M L Yuan1, S K Ong, A Y C Nee

  • 1Department of Mechanical Engineering, National University of Singapore. mpeyml@nus.edu.sg

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

[Expression of CREPT in vascular endothelial cells and its angiogenic mechanism in glioma].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2026
Same author

[Analysis on the effect of iodine staining endoscopy in screening for early esophageal cancer].

Zhonghua yi xue za zhi·2025
Same author

Complexity and weak integration promote the diversity of reef fish oral jaws.

Communications biology·2024
Same author

[Application of interventional respiratory techniques in the treatment of pulmonary bullae:an update].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2024
Same author

[SENP1 induced protein deSUMO modification increased the chemotherapy sensitivity of endometrial cancer side population cells].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2022
Same author

SIRT3 Promotes the Development of Esophageal Squamous Cell Carcinoma by Regulating Hexokinase 2 through the AKT Signaling Pathway.

Bulletin of experimental biology and medicine·2022
Same journal

Two-phase Impulse Fluid on Particle Flow Map.

IEEE transactions on visualization and computer graphics·2026
Same journal

FGO-SLAM++: Real-time Geometry-Aware Gaussian SLAM with Continuous Opacity Field.

IEEE transactions on visualization and computer graphics·2026
Same journal

Blue Noise Dithering for Reservoir-based Spatio-temporal Importance Resampling.

IEEE transactions on visualization and computer graphics·2026
Same journal

ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

MesoSplats: Texture Synthesis with Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

IEEE transactions on visualization and computer graphics·2026
See all related articles

A novel augmented reality (AR) registration method uses natural features and projective reconstruction for accurate virtual object superimposition. This simple yet robust technique enhances AR system stability and performance in various environments.

Area of Science:

  • Computer Vision
  • Augmented Reality
  • Geometric Reconstruction

Background:

  • Accurate registration is a critical challenge in augmented reality (AR) systems.
  • Existing methods often rely on predefined markers, limiting their applicability.
  • Natural feature-based approaches offer a promising alternative for markerless AR.

Purpose of the Study:

  • To propose a simple and robust registration method for augmented reality using natural features.
  • To leverage projective reconstruction techniques for accurate virtual object superimposition.
  • To enhance the stability and reliability of AR registration in diverse conditions.

Main Methods:

  • A two-step process involving embedding and rendering for virtual object superimposition.
  • Utilizing the Kanade-Lucas-Tomasi (KLT) feature tracker to identify natural feature correspondences in live video.

Related Experiment Videos

  • Employing projective reconstruction to estimate registration matrices and a robust projective matrix estimation method with Levenberg-Marquardt (LM) optimization.

    • Main Results:

    • The method achieves accurate registration without requiring predefined fiducials or markers.
    • Robustness is demonstrated with effectiveness even with occluded areas and potential outliers during tracking.
    • The technique ensures stable results and effective virtual object superimposition in both indoor and outdoor AR applications.

    Conclusions:

    • The proposed natural feature-based registration method offers a simple, robust, and effective solution for AR systems.
    • It overcomes limitations of marker-based approaches, enabling markerless registration.
    • The method's stability and ability to handle occlusion make it suitable for real-world AR applications.