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

Optical flow estimation and moving object segmentation based on median radial basis function network.

A G Borş1, I Pitas

  • 1Department of Informatics, University of Thessaloniki, Thessaloniki, Greece. adrian@zeus.csd.auth.gr

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

Introduction.

Optics express·2009
Same author

Image watermarking using block site selection and DCT domain constraints.

Optics express·2009
Same author

Morphological iterative closest point algorithm.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Object classification in 3-D images using alpha-trimmed mean radial basis function network.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Fuzzy scalar and vector median filters based on fuzzy distances.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

A generalized fuzzy mathematical morphology and its application in robust 2-D and 3-D object representation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same journal

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

This study introduces a novel pattern recognition scheme for simultaneous optical flow estimation and segmentation. It effectively identifies moving objects in image sequences using a median radial basis function neural network.

Area of Science:

  • Computer Vision
  • Pattern Recognition
  • Machine Learning

Background:

  • Simultaneous optical flow estimation and segmentation are crucial for analyzing dynamic scenes.
  • Existing methods face challenges in accurately decomposing complex moving scenes.

Purpose of the Study:

  • To develop a robust pattern recognition scheme for simultaneous optical flow estimation and segmentation.
  • To identify and segment individual moving objects within image sequences based on motion characteristics.

Main Methods:

  • Decomposition of moving scenes into distinct motion-based regions.
  • Utilizing feature vectors of still image and motion information as inputs.
  • Employing a median radial basis function (MRBF) neural network classifier.
  • Defining an error criterion function based on probability estimation theory as the cost function.

Related Experiment Videos

  • Estimating basis function parameters using marginal median and median absolute deviations (MAD) estimators.

    • Main Results:

    • Successful decomposition of scenes into motion-defined regions, with each class representing a moving object.
    • Effective activation of basis functions by specific image regions.
    • Merging of image regions by output units to accurately identify moving objects.

    Conclusions:

    • The proposed MRBF neural network-based pattern recognition scheme enables effective simultaneous optical flow estimation and segmentation.
    • The method accurately identifies and segments moving objects by leveraging motion information and robust parameter estimation techniques.