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

Occlusion-aware optical flow estimation.

Serdar Ince1, Janusz Konrad

  • 1Department of Electrical and Computer Engineering, Boston University, Boston, MA 02115, USA. ince@alum.bu.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|July 18, 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

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia.

Machine learning in clinical neuroimaging : 7th international workshop, MLCN 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 10, 2024, proceedings. MLCN (Workshop) (7th : 2024 : Marrakesh, Morocco)·2026
Same author

Cell classification with phase-imaging meta-sensors.

Optics letters·2024
Same author

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia.

ArXiv·2024
Same author

MIO-TCD: A new benchmark dataset for vehicle classification and localization.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018
Same author

Concussion, microvascular injury, and early tauopathy in young athletes after impact head injury and an impact concussion mouse model.

Brain : a journal of neurology·2018
Same author

Dictionary-based image reconstruction for superresolution in integrated circuit imaging.

Optics express·2015
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
Same journal

GoP-based Quality Enhancement on Video Compression.

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

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

This study introduces a new method for estimating optical flow in images, even in occluded areas. The approach jointly computes flow and detects occlusions, improving accuracy for computer vision tasks.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Photography

Background:

  • Optical flow estimation is crucial for understanding motion in image sequences.
  • Occlusion areas pose a significant challenge, as direct flow estimation is impossible.
  • Existing methods often involve separate steps for flow estimation and occlusion handling, limiting interaction.

Purpose of the Study:

  • To develop a novel variational formulation for joint optical flow estimation and occlusion detection.
  • To enable interaction between optical flow and occlusion estimates for improved accuracy.
  • To enhance optical flow extrapolation in occluded regions using image gradients.

Main Methods:

  • A variational formulation is proposed to simultaneously compute optical flow and detect occlusions.

Related Experiment Videos

  • Anisotropic diffusion is employed for optical flow extrapolation in occluded areas.
  • The method leverages underlying image gradients to preserve structural information and discontinuities.

    • Main Results:

    • The proposed method demonstrates significant qualitative and quantitative improvements in optical flow field accuracy.
    • Joint computation allows for more reliable occlusion detection and flow extrapolation compared to traditional methods.
    • Preservation of optical flow discontinuities is achieved through gradient-based anisotropic diffusion.

    Conclusions:

    • The variational approach offers a more integrated and effective solution for optical flow estimation in the presence of occlusions.
    • This method advances the state-of-the-art in computer vision by providing more robust motion analysis.
    • The technique has potential applications in various fields requiring accurate motion tracking from image data.