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: Jul 4, 2026

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

Point matching under large image deformations and illumination changes.

Bogdan Georgescu1, Peter Meer

  • 1Computer Science Department, Rutgers University, 94 Brett Road, Piscataway, NJ 08854-8058, USA. georgesc@caip.rutgers.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 27, 2008
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

Organ masks applied in feature space improve weakly supervised scan-level CT classification.

Scientific reports·2026
Same author

Predictors of Pathological Complete Response and Patient-Reported Outcomes During Neoadjuvant Chemotherapy in Early Breast Cancer: A Single-Center Retrospective Cohort Study.

Cureus·2026
Same author

PatchCLIP enables region specific contrastive health record and image joint training with patch embedding loss.

Scientific reports·2026
Same author

Deep learning-based pulmonary nodule risk assessment outperforms established malignancy risk scores in lung cancer screening.

Radiology advances·2026
Same author

The Performance of Protein Meal from <i>Hermetia illucens</i> Larvae in Hetero-Clarias Hybrid Farming.

Insects·2025
Same author

miRNA and Its Implications in the Treatment Resistance in Breast Cancer-Narrative Review of What Do We Know So Far.

Non-coding RNA·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 novel method for image correspondence using differential techniques and robust M-estimation. It achieves subpixel accuracy under significant distortions, improving object tracking.

Area of Science:

  • Computer Vision
  • Image Processing
  • Geometric Transformations

Background:

  • The general point correspondence problem is crucial for image analysis.
  • Existing methods like optical flow or color distribution matching have limitations.
  • Homography is a common transformation model for image patches.

Purpose of the Study:

  • To propose a robust solution for general point correspondence under homography.
  • To integrate optical flow and local color distribution matching.
  • To achieve subpixel matching accuracy under large projective distortions.

Main Methods:

  • Utilizing first-order differential techniques within a robust M-estimation framework.
  • Computing local color distributions using spatially oriented kernels in a 5D joint space.

More Related Videos

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

Related Experiment Videos

Last Updated: Jul 4, 2026

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

  • Employing a Gaussian pyramid for multi-resolution estimation, starting at the third level.
  • Incorporating illumination change compensation.

    • Main Results:

    • Achieved subpixel matching accuracy under significant projective distortions.
    • Demonstrated performance exceeding individual optical flow or color matching methods.
    • Successfully applied the correspondence algorithm to oriented object tracking.

    Conclusions:

    • The integrated approach offers a robust solution for point correspondence.
    • The method significantly enhances accuracy and robustness compared to existing techniques.
    • This algorithm has practical applications in computer vision tasks like object tracking.