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

Precision range image registration using a robust surface interpenetration measure and enhanced genetic algorithms.

Luciano Silva1, Olga R P Bellon, Kim L Boyer

  • 1Departamento de Informática, Universidade Federal do Paraná, Caixa Postal 19092, Curitiba, PR, Brazil 81531-980. luciano@inf.ufpr.br

IEEE Transactions on Pattern Analysis and Machine Intelligence
|May 7, 2005
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

Letter to the editor for the article "Does concordance between preoperatively measured prostate volume and enucleated weight predict outcomes in endoscopic enucleation of the prostate? Results from the REAP database".

World journal of urology·2024
Same author

Unsupervised Learning of Local Equivariant Descriptors for Point Clouds.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Clinical and radiographic features of pycnodysostosis: A case report.

Journal of clinical and experimental dentistry·2017
Same author

Dental Implant in the Canalis Sinuosus: A Case Report and Review of the Literature.

Case reports in dentistry·2017
Same author

Horizontally root fractured teeth with pulpal vitality - two case reports.

World journal of radiology·2017
Same author

A Rare Malignant Peripheral Nerve Sheath Tumor of the Maxilla Mimicking a Periapical Lesion.

Case reports in dentistry·2016

This study introduces a novel hybrid genetic algorithm (GA) and a quantitative surface interpenetration metric for robust range image registration. This approach overcomes limitations of traditional methods, enabling accurate alignment with low overlap and noise without prealignment.

Area of Science:

  • Computer Vision
  • Robotics
  • Computational Geometry

Background:

  • Range image registration is crucial for 3D reconstruction and object recognition.
  • Existing Iterative Closest Point (ICP) algorithms require prealignment and are sensitive to noise and low surface overlap.
  • Limitations of current methods hinder accurate registration in challenging real-world scenarios.

Purpose of the Study:

  • To develop a novel, robust range image registration method.
  • To overcome the limitations of prealignment dependency and outlier sensitivity in existing algorithms.
  • To enable accurate registration for range images with low overlap and significant noise.

Main Methods:

  • A hybrid genetic algorithm (GA) incorporating hill-climbing and parallel-migration for transformation space search.

Related Experiment Videos

  • A new, quantitative surface interpenetration metric for robust evaluation, replacing qualitative assessments.
  • The GA searches transformation spaces, eliminating the need for initial surface alignment.

    • Main Results:

    • The proposed GA technique demonstrates significantly faster convergence compared to previous GA methods.
    • The novel interpenetration metric provides more precise alignments than traditional metrics like mean squared error.
    • Experimental results validate the effectiveness of the hybrid GA and robust metric in challenging registration tasks.

    Conclusions:

    • The hybrid GA approach effectively registers range images with low overlap and without prealignment.
    • The quantitative interpenetration metric enhances robustness against noise and improves alignment accuracy.
    • This new method offers a significant advancement for range image registration in complex environments.