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

Figure-ground segmentation from occlusion.

Pedro M Q Aguiar1, José M F Moura

  • 1Institute for Systems and Robotics, Instituto Superior Técnico, 1049-001 Lisboa, Portugal. aguiar@isr.ist.utl.pt

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|August 27, 2005
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

Reconstruction of Lamb wave dispersion curves by sparse representation with continuity constraints.

The Journal of the Acoustical Society of America·2017
Same author

Geodesic distance on a Grassmannian for monitoring the progression of Alzheimer's disease.

NeuroImage·2016
Same author

Data-driven and calibration-free Lamb wave source localization with sparse sensor arrays.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2015
Same author

An efficient method to detect periodic behavior in botnet traffic by analyzing control plane traffic.

Journal of advanced research·2015
Same author

Dispersion curve recovery with orthogonal matching pursuit.

The Journal of the Acoustical Society of America·2015
Same author

Data-driven matched field processing for Lamb wave structural health monitoring.

The Journal of the Acoustical Society of America·2014
Same journal

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation.

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

This study introduces a simple algorithm for segmenting moving objects in videos, even in challenging low-texture scenes. The method directly infers object templates, improving computational efficiency and performance for layered video representations.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Layered video representations are gaining popularity.
  • Automating these representations requires effective moving object segmentation.
  • Existing methods struggle with low-textured regions or are computationally intensive.

Purpose of the Study:

  • To present a computationally simple algorithm for segmenting moving objects.
  • To address limitations of current methods in low-texture/low-contrast scenes.
  • To develop a method that infers object templates directly from image intensities.

Main Methods:

  • Infers moving object templates directly from image intensity values, bypassing motion field computation.
  • Models object rigidity and background occlusion.

Related Experiment Videos

  • Formulates segmentation as penalized likelihood cost function minimization.
  • Employs an alternating minimization algorithm with closed-form solutions and relaxation.

    • Main Results:

    • Successfully segments moving objects in low-texture/low-contrast scenes.
    • Demonstrates good performance compared to existing methods.
    • Estimates object motion, templates, and pixel intensity levels efficiently.

    Conclusions:

    • The proposed algorithm offers a computationally simple and effective solution for moving object segmentation.
    • It overcomes limitations of traditional methods in challenging visual conditions.
    • The direct template inference approach is robust and efficient for layered video generation.