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 26, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Fast scene recognition and camera relocalisation for wide area augmented reality systems.

Tao Guan1, Liya Duan, Yongjian Chen

  • 1School of Computer Science & Technology, Huazhong University of Science and Technology, No.1037 Luoyu Road, Wuhan 430074, China. qd_gt@126.com

Sensors (Basel, Switzerland)
|January 6, 2012
PubMed
Summary

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

RNF125 inhibits EMT and glycolysis in breast cancer by suppressing HDAC1-mediated histone deacetylation of PGM5.

Epigenomics·2026
Same author

The global patent landscape of bispecific antibodies: technological innovations and therapeutic applications.

Nature biotechnology·2026
Same author

Generative Artificial Intelligence and Large Language Models in Clinical Oncology.

MedComm·2026
Same author

Assessment of disease severity in systemic sclerosis-associated interstitial lung disease using a modified lung ultrasound score: correlation with pulmonary function, HRCT, and clinical scores, and evaluation of diagnostic efficacy.

Clinical rheumatology·2026
Same author

Soluble dietary fiber from Piper sarmentosum Roxb. leaves modulates gut microbiota-derived cis-11-eicosenoic acid to regulate lipid metabolism.

International journal of biological macromolecules·2026
Same author

[Clinical Value of Detecting <i>MYD88 L265P</i> Mutation in the Plasma of Patients with Treatment-Naive Diffuse Large B-Cell Lymphoma via Droplet Digital PCR].

Zhongguo shi yan xue ye xue za zhi·2026

This study enhances augmented reality systems by improving online scene learning with adaptive random trees and speeding up camera relocalisation using an enhanced PROSAC algorithm. These advancements enable more accurate and efficient real-time tracking in large-scale environments.

Area of Science:

  • Computer Vision
  • Augmented Reality
  • Robotics

Background:

  • Wide area augmented reality (AR) systems face performance limitations due to challenges in online scene learning and camera relocalisation.
  • Accurate and efficient scene understanding and camera positioning are critical for seamless AR experiences.

Purpose of the Study:

  • To address the limitations in online scene learning and fast camera relocalisation for wide area AR systems.
  • To develop algorithms that improve accuracy and reduce computational complexity in AR tracking.

Main Methods:

  • Implemented adaptive random trees for accurate online scene learning, particularly effective in large-scale workspaces.
  • Utilized an enhanced PROSAC algorithm for fast camera relocalisation, significantly reducing computational complexity.
Keywords:
adaptive random treesaugmented realityregistrationscene recognitionwide-area

Related Experiment Videos

Last Updated: May 26, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

  • Employed a parallel-computing scheme with a multithreaded architecture to separate camera tracking, scene mapping, scene learning, and relocalisation into distinct threads.

    • Main Results:

    • Achieved higher recognition rates compared to traditional methods for online scene learning.
    • Demonstrated a significant reduction in computational complexity for camera relocalisation.
    • Enabled real-time tracking performance and the capability to track multiple maps simultaneously.

    Conclusions:

    • The proposed adaptive random trees and enhanced PROSAC algorithm effectively improve online scene learning and camera relocalisation in AR systems.
    • The multithreaded implementation ensures real-time performance and robust tracking in complex, large-scale environments.
    • The developed methods offer a viable solution for enhancing the performance of wide area augmented reality applications.