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

Incremental model-based estimation using geometric constraints.

Cristian Sminchisescu1, Dimitris Metaxas, Sven Dickinson

  • 1Artificial Intelligence Laboratory, Department of Computer Science, University of Toronto, 6 King's College Road, Pratt Building, Rm. 276, Toronto, Ontario, Canada, M5S 3G4. crismin@cs.toronto.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|May 7, 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

Analysis of cardiac dynamic global function.

JRSM cardiovascular disease·2026
Same author

MADCrowner: Margin Aware Dental Crown design with template deformation and refinement.

Medical image analysis·2026
Same author

Reconstructing Three-Dimensional Models of Interacting Humans.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Probabilistic Directed Distance Fields for Ray-Based Shape Representations.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2025
Same author

Editorial for Special Issue on Foundation Models for Medical Image Analysis.

Medical image analysis·2024
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

This study introduces a novel framework for object shape estimation and tracking using monocular image sequences. It enhances accuracy by incrementally integrating detected geometric primitives into the model.

Area of Science:

  • Computer Vision
  • Robotics
  • 3D Reconstruction

Background:

  • Traditional methods often rely on pre-defined shape models (e.g., splines, superquadrics) limiting adaptability.
  • Decoupling structure recovery from motion tracking reduces robustness and scope in existing frameworks.
  • A fixed shape representation restricts the ability to incrementally adapt to complex object geometries.

Purpose of the Study:

  • To develop a model-based framework for incremental and adaptive object shape estimation and tracking.
  • To enable automatic detection and integration of low-level geometric primitives for enhanced model building.
  • To improve tracking accuracy by incorporating newly recovered features into state estimation.

Main Methods:

  • A novel model-based framework integrating low-level geometric primitives (lines) incrementally into object shape estimation.

Related Experiment Videos

  • Utilizes trinocular constraints between geometric primitives for consistency testing and new structure identification.
  • Employs a unified state estimation that includes newly recovered features to improve tracking accuracy.

    • Main Results:

    • Demonstrated successful incremental integration of geometric primitives, expanding model scope beyond initial representations.
    • Achieved improved tracking accuracy by incorporating dynamically detected features into the state estimation process.
    • Validated the framework's robustness on two distinct image-based tracking domains with complex 3D structures and motion.

    Conclusions:

    • The proposed framework offers a step towards automatic model building for object shape estimation and tracking.
    • It reduces reliance on strong prior shape representations and a large number of initial features.
    • This approach enhances both the scope and robustness of object tracking in monocular image sequences.