Jove
Visualize
Contact Us

Related Experiment Videos

Infrared target detection with probability density functions of wavelet transform subbands.

Firooz A Sadjadi1

  • 1Lockheed Martin, 3400 Highcrest Road, Saint Anthony, Minnesota 55418-0000, USA. sadja001@tc.umn.edu

Applied Optics
|January 23, 2004
PubMed
Summary

This study introduces a new wavelet texture algorithm for image segmentation. It effectively segments targets from background clutter using probability density functions and clustering, enabling performance prediction and optimization for infrared imagery.

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

Automated exploitation of sky polarization imagery.

Applied optics·2018
Same author

Invariants of polarization transformations.

Applied optics·2007
Same author

Passive three-dimensional imaging using polarimetric diversity.

Optics letters·2007
Same author

Adaptive polarimetric sensing for optimum radar signature classification using a genetic search algorithm.

Applied optics·2006
Same author

Target-adaptive polarimetric synthetic aperture radar target discrimination using maximum average correlation height filters.

Applied optics·2006
Same author

Polarimetric laser radar target classification.

Optics letters·2005
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

Area of Science:

  • Image processing and computer vision
  • Signal processing
  • Pattern recognition

Background:

  • Automated target recognition (ATR) systems require robust segmentation algorithms.
  • Infrared (IR) imagery presents unique challenges due to thermal signatures and background clutter.
  • Wavelet-based texture analysis offers a powerful approach for feature extraction in complex scenes.

Purpose of the Study:

  • To develop and evaluate a novel wavelet multiresolution texture-based algorithm for target segmentation in infrared imagery.
  • To establish predictive performance models for the developed algorithm under various conditions.
  • To enable optimization of algorithm parameters for improved detection probability and reduced false alarms.

Main Methods:

  • Image decomposition using wavelet multiresolution analysis.

Related Experiment Videos

  • Probability density function (PDF) estimation and moment calculation from subbands.
  • Clustering algorithm for segmenting targets from background clutter.
  • Experimental evaluation on real infrared imagery with varying parameters and scene conditions.

    • Main Results:

    • The algorithm successfully segments targets from background clutter using PDF moments.
    • Multidimensional predictive analytic performance models were developed.
    • Models relate detection probability to false alarm rate, target characteristics, and scene metrics.
    • Performance prediction and optimization capabilities were demonstrated.

    Conclusions:

    • The developed wavelet texture algorithm provides effective target segmentation in infrared imagery.
    • The predictive performance models allow for accurate performance estimation and parameter optimization.
    • This approach enhances the robustness and efficiency of automated target recognition systems.