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: Mar 6, 2026

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.5K

Feature-based three-dimensional registration for repetitive geometry in machine vision.

Yuanzheng Gong1, Eric J Seibel1

  • 1Mechanical Engineering Department, University of Washington, Seattle, Washington, USA, 98195.

Journal of Information Technology & Software Engineering
|March 14, 2017
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

CoreView imaging on needle: Rapid core-needle biopsy imaging for point-of-care breast cancer diagnosis.

Global translational medicine·2026
Same author

Complementary fluorescence and photoacoustic imaging of tozuleristide in muscle tissue in vitro- toward optically-guided solid tumor surgery: feasibility studies.

Scientific reports·2026
Same author

Vision-Guided Surgical Navigation Using Computer Vision for Dynamic Intraoperative Imaging Updates.

International forum of allergy & rhinology·2025
Same author

High-Fidelity 3D Reconstruction for Accurate Anatomical Measurements in Endoscopic Sinus Surgery.

Proceedings of SPIE--the International Society for Optical Engineering·2025
Same author

Inverse-designed large field-of-view polychromatic metalens for tri-color scanning fiber endoscopy.

Communications engineering·2025
Same author

Neural Radiance Fields (NeRF) for 3D Reconstruction of Monocular Endoscopic Video in Sinus Surgery.

Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery·2025
See all related articles

This study introduces a new feature-based 3D registration algorithm to align 3D point clouds, improving accuracy and efficiency for objects with repetitive geometries, unlike traditional Iterative Closest Point (ICP) methods.

Area of Science:

  • Computer Vision
  • Robotics
  • 3D Reconstruction

Background:

  • 3D registration aligns multiple 3D point clouds for complete scene reconstruction.
  • Iterative Closest Point (ICP) is a common but flawed registration method, especially for repetitive geometries.
  • Vision-based 3D reconstruction often suffers from depth uncertainty due to small camera baselines.

Purpose of the Study:

  • To develop a robust feature-based 3D registration algorithm for vision-based 3D reconstruction.
  • To overcome the limitations of ICP algorithms in handling repetitive geometric structures.
  • To address depth uncertainty issues in 3D reconstruction.

Main Methods:

  • A novel feature-based 3D registration algorithm utilizing object texture and image feature robustness.
Keywords:
3D reconstruction3D registrationIterative Closest Point (ICP)machine vision

More Related Videos

Quantitative Assessment Protocol for Facial Soft Tissue Volumetric Changes with Stereophotogrammetry
06:26

Quantitative Assessment Protocol for Facial Soft Tissue Volumetric Changes with Stereophotogrammetry

Published on: December 9, 2025

226
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

15.1K

Related Experiment Videos

Last Updated: Mar 6, 2026

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.5K
Quantitative Assessment Protocol for Facial Soft Tissue Volumetric Changes with Stereophotogrammetry
06:26

Quantitative Assessment Protocol for Facial Soft Tissue Volumetric Changes with Stereophotogrammetry

Published on: December 9, 2025

226
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

15.1K
  • Retrieval of 3D correspondences to solve for rigid transformation between point clouds.
  • Comparative analysis against various ICP algorithms.

    • Main Results:

    • The proposed algorithm demonstrates superior accuracy, efficiency, and robustness compared to ICP methods for repetitive geometries.
    • Successful alignment of 3D point clouds generated from vision-based 3D reconstruction.
    • Effective mitigation of depth uncertainty caused by limited camera baselines.

    Conclusions:

    • The feature-based approach offers a significant advancement in 3D registration for complex scenes.
    • This method enhances the reliability of 3D reconstruction from visual data.
    • The algorithm provides a robust solution for challenging registration scenarios in machine vision.