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

Errors-in-variables modeling in optical flow estimation.

L Ng1, V Solo

  • 1Dept. of Electron., Macquarie Univ., Sydney, NSW, Australia. lng@insightful.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 8, 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

Anaesthesia for paediatric liver transplantation.

BJA education·2026
Same author

Anastomotic Failure Is Not Affected by Anastomotic Technique in Minimally Invasive Two-Stage Oesophagectomy.

ANZ journal of surgery·2026
Same author

Upper Limit on the Photoproduction Cross Section of the Spin-Exotic π_{1}(1600).

Physical review letters·2025
Same author

Visual supplementation is an effective tool in cataract surgery counselling by eye-care practitioners.

Journal francais d'ophtalmologie·2024
Same author

Serum microRNA test to identify individuals with high risk of colorectal cancer: abridged secondary publication.

Hong Kong medical journal = Xianggang yi xue za zhi·2023
Same author

A comparison of the kinematics and kinetics of barefoot and shod running in children with cerebral palsy.

Gait & posture·2022
Same journal

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

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

BayeTopo: Bayesian-based Topology-guided Learning for Vascular Imaging Segmentation.

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

This study introduces a novel optical flow estimation method (EIVM) to address errors-in-variables (EIV) in spatial derivatives. EIVM improves accuracy by incorporating a general EIV model and a data-driven approach for neighborhood size selection.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Gradient-based optical flow methods often neglect spatial derivative errors, leading to an errors-in-variables (EIV) problem.
  • Finite difference methods introduce correlated errors between pixels, complicating standard EIV solutions like Total Least Squares (TLS).
  • Existing TLS methods are flawed as they assume independence of errors in neighboring pixels, which is not the case in optical flow.

Purpose of the Study:

  • To formulate a new optical flow estimation method (EIVM) that accurately addresses the EIV problem.
  • To incorporate a general EIV model into optical flow estimation using Sprent's procedure.
  • To develop a data-driven method for selecting the neighborhood size based on Stein's unbiased risk estimators (SURE).

Main Methods:

Related Experiment Videos

  • Developed the Errors-In-Variables Method (EIVM) based on Sprent's (1966) procedure for optical flow estimation.
  • Utilized a neighborhood size as a smoothing parameter within the EIVM objective function.
  • Implemented a data-driven approach using Stein's unbiased risk estimators (SURE) for optimal neighborhood size selection.

Main Results:

  • EIVM properly treats the EIV problem in optical flow estimation, unlike previous methods.
  • The neighborhood size in EIVM has a more complex effect on smoothing due to data-driven weights.
  • The proposed SURE-based method provides an objective criterion for selecting the neighborhood size.

Conclusions:

  • The EIVM offers a more robust approach to optical flow estimation by explicitly handling errors-in-variables.
  • The adaptive neighborhood size selection enhances the performance and applicability of the EIVM.
  • This work advances gradient-based optical flow techniques by providing a principled way to manage derivative errors.