• DocumentCode
    2608695
  • Title

    Monitoring of natural scenes for feature extraction and tracking an independent component analysis (ICA) approach

  • Author

    Durham, Jayson ; Torrez, William

  • Author_Institution
    Signal Exploration & Inf. Manage. Div., Space & Naval Warfare Syst. Center, San Diego, CA, USA
  • fYear
    2004
  • fDate
    14-16 July 2004
  • Firstpage
    2
  • Lastpage
    3
  • Abstract
    An independent component analysis (ICA) approach to monitoring of natural scenes empirically generates robust image features for localization and tracking of potentially-occluded targets. The ICA-based empirical model utilizes statistical techniques that assist analysts in characterizing the underlying criteria that enables such feature extraction. Thus, this approach provides a basis for analyzing how the empirically generated feature localization and tracking models and related algorithms to perform their function.
  • Keywords
    blind source separation; feature extraction; feedforward neural nets; independent component analysis; multilayer perceptrons; natural scenes; tracking; blind signal separation; feature extraction; independent component analysis; multilayer feedforward neural networks; natural scenes monitoring; signal decomposition; statistical technique; tracking model; Distribution functions; Feature extraction; Independent component analysis; Information management; Layout; Monitoring; Neural networks; Neurons; Smoothing methods; Target tracking;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence for Measurement Systems and Applications, 2004. CIMSA. 2004 IEEE International Conference on
  • Print_ISBN
    0-7803-8341-9
  • Type

    conf

  • DOI
    10.1109/CIMSA.2004.1397217
  • Filename
    1397217