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

A Bayesian, exemplar-based approach to hierarchical shape matching.

Dariu M Gavrila1

  • 1Machine Perception Department of DainlerChrysler R&D, Ulm, Germany. dariu.gavrila@DainlerChrysler.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 15, 2007
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

EuroCity Persons 2.0: A Large and Diverse Dataset of Persons in Traffic.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Semantic Scene Completion Using Local Deep Implicit Functions on LiDAR Data.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks.

IEEE transactions on pattern analysis and machine intelligence·2016
Same author

A multilevel Mixture-of-Experts framework for pedestrian classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2011
Same author

Monocular pedestrian detection: survey and experiments.

IEEE transactions on pattern analysis and machine intelligence·2009
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 new probabilistic method for shape matching using a template tree. This approach significantly speeds up real-time pedestrian detection by efficiently eliminating unlikely matches.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Hierarchical, exemplar-based shape matching often requires feature correspondence.
  • Existing methods can be computationally intensive for real-time applications.

Purpose of the Study:

  • To develop a novel probabilistic approach for hierarchical, exemplar-based shape matching.
  • To improve efficiency and accuracy in shape matching tasks, particularly for real-time applications like pedestrian detection.

Main Methods:

  • Utilized a template tree generated via bottom-up clustering and stochastic optimization.
  • Implemented a simultaneous coarse-to-fine matching strategy over the template tree and transformation parameters.
  • Developed a Bayesian model to estimate a posteriori object class probability, incorporating object scale and saliency.

Related Experiment Videos

Main Results:

  • The probabilistic approach demonstrated significant speed-up compared to a nonprobabilistic variant.
  • The Bayesian model effectively pruned unpromising search paths in the template tree.
  • Successful application in real-time pedestrian detection from a moving vehicle.

Conclusions:

  • The proposed probabilistic, hierarchical, exemplar-based shape matching offers an efficient and principled method.
  • The Bayesian model enhances threshold setting and search space pruning.
  • This approach shows strong potential for real-time computer vision tasks.