• DocumentCode
    1039904
  • Title

    DEKF system for crowding estimation by a multiple-model approach

  • Author

    Tesei, Anna

  • Volume
    30
  • Issue
    5
  • fYear
    1994
  • fDate
    3/3/1994 12:00:00 AM
  • Firstpage
    390
  • Lastpage
    391
  • Abstract
    A distributed extended Kalman filter (DEKF) network devoted to real-time crowding estimation for surveillance in complex scenes is presented. Estimation is carried out by extracting a set of significant features from sequences of images. Feature values are associated by virtual sensors with the estimated number of people using nonlinear models obtained in an off-line training phase. Different models are used, depending on the positions and dimensions of the crowded subareas detected in each image
  • Keywords
    Kalman filters; feature extraction; image sequences; DEKF system; complex scenes; crowded subareas; distributed extended Kalman filter; feature values; image sequences; multiple-model approach; nonlinear models; off-line training phase; real-time crowding estimation; significant features; surveillance; virtual sensors;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19940280
  • Filename
    273277