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

Bayesian-competitive consistent labeling for people surveillance.

Simone Calderara1, Rita Cucchiara, Andrea Prati

  • 1Dipartimento di Ingegneria dell'Informazione, University of Modena and Reggio Emilia, Via Vignolese, 905, 41100 Modena-Italy. simone.calderara@unimore.it

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 18, 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

A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models.

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

The aporetic dialogs of Modena on gender differences: Is it all about testosterone? Episode III: Mathematics.

Andrology·2025
Same author

VATr++: Choose Your Words Wisely for Handwritten Text Generation.

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

Spotting <i>Culex pipiens</i> from satellite: modeling habitat suitability in central Italy using Sentinel-2 and deep learning techniques.

Frontiers in veterinary science·2024
Same author

A Graph-Based Multi-Scale Approach With Knowledge Distillation for WSI Classification.

IEEE transactions on medical imaging·2023
Same author

Class-Incremental Continual Learning Into the eXtended DER-Verse.

IEEE transactions on pattern analysis and machine intelligence·2023
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

This study introduces a robust method for consistent people labeling in multi-camera surveillance. The approach accurately tracks individuals and groups across overlapping camera views, enhancing surveillance systems.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Surveillance Systems

Background:

  • Multi-camera surveillance systems require accurate and consistent object labeling for effective monitoring.
  • Existing methods often struggle with segmentation errors and distinguishing individual people within groups.

Purpose of the Study:

  • To develop a novel and robust framework for consistent people labeling in multi-camera surveillance.
  • To create a scalable system applicable to any number of cameras with overlapping views.

Main Methods:

  • An off-line training process computes ground-plane homography and epipolar geometry.
  • Hypotheses for matching objects across cameras are generated and evaluated using prior and likelihood values.
  • A maximum-a-posteriori approach is used for final label assignment, incorporating forward and backward likelihood contributions.

Related Experiment Videos

Main Results:

  • The proposed approach demonstrates accuracy and robustness in handling segmentation errors.
  • The method effectively disambiguates groups of people merged into single objects.
  • Experimental results validate the system's performance in outdoor surveillance scenarios.

Conclusions:

  • The developed framework offers a significant advancement in consistent labeling for multi-camera people surveillance.
  • The approach is scalable and robust, outperforming existing homography-based methods.
  • This work provides a reliable solution for improving the accuracy of surveillance systems.