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

Dense motion estimation using regularization constraints on local parametric models.

Ioannis Patras1, Marcel Worring, Rein van den Boomgaard

  • 1Intelligent Sensory Information Systems Group, Computer Science Institute, University of Amsterdam, The Netherlands. I.Patras@ewi.tudelft.nl

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|November 16, 2004
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

Interpol review of detection of AI-generated image and video deepfakes, 2022-2025.

Forensic science international. Synergy·2026
Same author

Evaluating <sup>18</sup>F-FDG PET-CT for Regional Lymph Node Assessment in Advanced Upper Tract Urothelial Carcinoma.

European urology open science·2026
Same author

Low risk of ipsilateral recurrence after distal ureterectomy for upper tract urothelial carcinoma.

Scandinavian journal of urology·2026
Same author

Survival patterns after perioperative treatment escalation and cystectomy for synchronous oligometastatic bladder cancer (M1a/M1b) - a population-based series.

Scandinavian journal of urology·2025
Same author

[Doctor and algorithm].

Nederlands tijdschrift voor geneeskunde·2025
Same author

Machine learning approaches for fine-grained symptom estimation in schizophrenia: A comprehensive review.

Artificial intelligence in medicine·2025
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a novel dense optical flow estimation method using patch-based motion modeling with inter-patch regularization. The approach accurately handles motion discontinuities and large displacements, yielding precise piecewise-smooth motion fields.

Area of Science:

  • Computer Vision
  • Image Processing
  • Motion Estimation

Background:

  • Dense optical flow estimation is crucial for analyzing motion in image sequences.
  • Existing methods struggle with motion discontinuities and large displacements.
  • Patch-based approaches require robust regularization for accurate parameter estimation.

Purpose of the Study:

  • To develop a novel dense optical flow estimation method.
  • To improve accuracy in handling motion discontinuities and large displacements.
  • To introduce regularization constraints between neighboring patch model parameters.

Main Methods:

  • Parametrizing motion fields within image patches using models of varying orders.
  • Introducing novel regularization constraints between model parameters of adjacent patches.

Related Experiment Videos

  • Employing robust functions for regularization to preserve motion discontinuities.
  • Utilizing a three-frame approach with a direction field to balance constraints.
  • Solving the optimization problem via an iterative deterministic relaxation method.

    • Main Results:

    • The proposed method successfully estimates dense optical flow.
    • It effectively handles large magnitude motions and motion discontinuities.
    • The method produces accurate piecewise-smooth motion fields.
    • Inter-patch regularization provides necessary constraints for small or poorly constrained patches.

    Conclusions:

    • The novel regularization approach enhances dense optical flow estimation accuracy.
    • The method demonstrates robustness in challenging motion scenarios.
    • Accurate and piecewise-smooth motion fields are achieved, suitable for various applications.