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

Nonstationary color tracking for vision-based human-computer interaction.

Ying Wu1, T S Huang

  • 1Dept. of Electr. Eng. and Comput. Sci., Northwestern Univ., Evanston, IL, USA.

IEEE Transactions on Neural Networks
|February 5, 2008
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

Self-assembled antibacterial coating by N-halamine polyelectrolytes on a cellulose substrate.

Journal of materials chemistry. B·2020
Same author

Growth and Survival of Salmonella montevideo on Tomatoes and Disinfection with Chlorinated Water.

Journal of food protection·2019
Same author

Production of Kojic Acid by Aspergillus candidus in Three Culture Media.

Journal of food protection·2019
Same author

Characterization and Mechanism for the Protection of Photolytic Decomposition of N-Halamine Siloxane Coatings by Titanium Dioxide.

ACS applied materials & interfaces·2016
Same author

Humic substances shorten human plasma prothrombin time.

Environmental geochemistry and health·2013
Same author

Tissue distribution of absorbed humic acids.

Environmental geochemistry and health·2013
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces adaptive color models for robust human tracking in videos. The Structure Adaptive Self-Organizing Map (SASOM) neural network effectively handles changing lighting and diverse skin tones for real-time face and hand localization.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Human-Computer Interaction

Background:

  • Skin color is a key feature for tracking human body parts in video.
  • Traditional color-based tracking struggles with changing lighting and individual skin tone variations.
  • Existing adaptive color models require further research for improved performance.

Purpose of the Study:

  • To investigate color-based image segmentation and nonstationary color tracking.
  • To propose and evaluate novel adaptive color models for robust target localization.
  • To develop algorithms for real-time face and hand tracking in dynamic environments.

Main Methods:

  • Proposed the Structure Adaptive Self-Organizing Map (SASOM) neural network as a new color model.
  • Formulated nonstationary color tracking as a model transduction problem.

Related Experiment Videos

  • Developed SASOM transduction and discriminant Expectation-Maximization (EM) algorithms for adaptive color classification.

    • Main Results:

    • SASOM demonstrated powerful capabilities for efficient image segmentation.
    • The proposed transduction algorithms successfully adapted to nonstationary color distributions.
    • Experiments showed effective real-time face and hand localization despite tracking challenges.

    Conclusions:

    • Adaptive color models are crucial for reliable vision-based human tracking.
    • SASOM and transduction methods offer a robust solution for nonstationary color tracking.
    • The developed system enables effective vision-based human-computer interaction.