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

Learning semantic scene models from observing activity in visual surveillance.

Dimitios Makris1, Tim Ellis

  • 1Kingston University, Kingston-upon-Thames, Surrey KT1 2EE, U.K. d.makris@kingston.ac.uk

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|June 24, 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

Planning and licensing for marine aquaculture.

Reviews in aquaculture·2024
Same author

Dying for change: A roadmap to refine the fish acute toxicity test after 40 years of applying a lethal endpoint.

Ecotoxicology and environmental safety·2021
Same author

Large Scale Internet-based Survey of Patients With a Myeloproliferative Neoplasm: Opinions and Experiences Regarding SARS-CoV-2 (COVID-19) Vaccination Strategies in 2021.

HemaSphere·2021
Same author

Clarification of early end-points for refinement of animal experiments, with specific reference to fish.

Laboratory animals·2021
Same author

Growth Mechanisms of Nano-to Micro-Sized Lead Sulfate Particles.

ACS omega·2021
Same author

Immunoassays are not immune to errors: Examples from two studies of steroid output from freshwater trout farms.

General and comparative endocrinology·2019
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study introduces an automated method to create activity-based scene models from video streams. These models enhance visual surveillance by interpreting moving objects and identifying key activity zones.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional scene modeling often relies on manual annotation or predefined rules, limiting adaptability to dynamic environments.
  • Interpreting complex activities from raw video data presents significant challenges in automated systems.

Purpose of the Study:

  • To develop an unsupervised approach for automatically learning activity-based semantic scene models from video data streams.
  • To enable the labeling of distinct regions within a scene based on identifiable activities (e.g., entry/exit zones, paths).
  • To demonstrate the utility of these learned models in supporting the interpretation of moving objects for visual surveillance.

Main Methods:

  • Proposed an activity-based semantic scene model framework.

Related Experiment Videos

  • Developed and applied several unsupervised learning methods to identify and label scene elements.
  • Evaluated the efficiency and effectiveness of the proposed unsupervised learning techniques.

    • Main Results:

    • Demonstrated the efficiency of the unsupervised methods in learning scene elements.
    • Successfully generated activity-based semantic scene models from video data.
    • Validated the model's capability to identify key activity zones like entry/exit points, junctions, and paths.

    Conclusions:

    • The proposed unsupervised methods efficiently learn activity-based semantic scene models from video data.
    • These learned models effectively support the interpretation of moving objects in visual surveillance.
    • This approach offers a scalable and adaptable solution for automated scene understanding.