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

Coupled parametric active contours.

Christophe Zimmer1, J C Olivo-Marin

  • 1Quantitative Image Analysis Group, Institut Pasteur, Paris, France. czimmer@pasteur.fr

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 16, 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

Deep learning-based detection of murine congenital heart defects from µCT scans.

Communications biology·2025
Same author

Uniform dynamics of cohesin-mediated loop extrusion in living human cells.

Nature genetics·2025
Same author

Multiscale visualization of nucleolar chromatin in yeast Saccharomyces cerevisiae.

Journal of structural biology·2025
Same author

Extracting circumstances of Covid-19 transmission from free text with large language models.

Nature communications·2025
Same author

A constricted mitochondrial morphology formed during respiration.

Nature communications·2025
Same author

A relay race of ESCRT-III paralogs drives cell division in a hyperthermophilic archaeon.

mBio·2024
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a new active contour method to track touching objects, preventing segmentation failures. The coupled contours maintain object identity during contact, improving tracking accuracy.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Geometry

Background:

  • Tracking non-occluding objects that touch is challenging for existing methods.
  • Parametric and single level set methods often fail when objects make transient contact.

Purpose of the Study:

  • To develop an advanced active contour model for robust object tracking during contact.
  • To address the limitations of current methods in handling merging or overlapping objects.

Main Methods:

  • An extension of parametric active contours is proposed.
  • A cost functional is minimized simultaneously for all contours.
  • A penalty for contour overlaps is incorporated to enforce topological constraints.

Main Results:

Related Experiment Videos

  • The coupled active contour model successfully tracks non-occluding objects during transient contact.
  • Object identity is preserved throughout contact and separation events.
  • The method overcomes limitations of previous parametric and level set approaches.

Conclusions:

  • The proposed coupled active contour method provides a robust solution for tracking objects with temporary contact.
  • This technique enhances segmentation and tracking accuracy by respecting object topological constraints.