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

Maximum-likelihood registration of range images with missing data.

Gregory C Sharp1, Sang W Lee, David K Wehe

  • 1Department of Radiation Oncology, Massachusetts General Hospital, Boston, MA 02114, USA. gcsharp@partners.org

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 15, 2007
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

Safety and effectiveness of the Colovac anastomosis protection device compared with diverting ileostomy after low anterior resection: protocol for an international, multicentre, prospective, non-randomised comparative study (SAFE-3).

BMJ open gastroenterology·2026
Same author

Femoral Derotational Osteotomy for Idiopathic Excessive Femoral Anteversion: A Comparison of Surgical Techniques.

Journal of pediatric orthopedics·2026
Same author

PRISM: An open-source framework for regularized material decomposition on a novel kV dual-layer imager.

Medical physics·2026
Same author

Corrigendum to "Clinical target volumes for glioma - Automated delineation to improve neuroanatomic consistency" [Phys. Imaging Radiat. Oncol. 36 (2025) 100865].

Physics and imaging in radiation oncology·2026
Same author

Real-time bowel perfusion monitoring with FUJIFILM ELUXEO® VISION endoscopic imaging system in colorectal surgery.

Surgical endoscopy·2025
Same author

Probabilistic clinical target definition with nearest neighbor correlation.

Physics in medicine and biology·2025
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a new method for registering range images with missing data, improving accuracy by using ray casting to form correspondences and statistical properties to classify point matches.

Area of Science:

  • Computer Vision
  • Robotics
  • 3D Reconstruction

Background:

  • Missing data in range images is a significant challenge for 3D scene registration.
  • Common causes include occlusions, sensor limitations, and shadows, leading to registration failures.
  • Existing registration methods struggle with unmatched or missing data points.

Purpose of the Study:

  • To develop a robust maximum likelihood method for registering range images containing missing or unmatched data.
  • To improve the accuracy and reliability of 3D scene registration in the presence of data gaps.
  • To classify points based on visibility properties for more accurate matching.

Main Methods:

  • A maximum likelihood approach is proposed for registration.
  • Ray casting is employed to establish correspondences between valid and missing points.

Related Experiment Videos

  • Points are classified by visibility properties (occlusions, field of view, shadows).
  • Statistical sensor properties (noise, outliers) are used to determine match likelihood.

    • Main Results:

    • The method successfully registers complex scenes with significant missing data.
    • High rates of convergence were demonstrated in experimental evaluations.
    • Improved accuracy in handling occlusions, field of view limitations, and shadows.

    Conclusions:

    • The proposed maximum likelihood method effectively addresses the challenge of missing data in range image registration.
    • The technique enhances the robustness of 3D reconstruction and scene analysis.
    • This approach offers a significant advancement for applications relying on accurate 3D data alignment.