• DocumentCode
    263785
  • Title

    Fusion of three techniques for person detection in real time

  • Author

    Boukamcha, Hamdi ; Mohamed, Amr

  • Author_Institution
    EME Lab., Univ. of Monastir, Monastir, Tunisia
  • fYear
    2014
  • fDate
    17-19 Jan. 2014
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    The present paper is a new technique for the detection of persons, with combination of the three approaches (Adaptive Gaussian Mixture, Objects Classification, and Stereo Vision) with the integration of the multithreaded architecture. The study and validation at high-level of these descriptors was used to determinate the advantages and drawbacks of each approach. Several tests were made to evaluate the precision, execution time, complexity and sensitivity to different situations.
  • Keywords
    Gaussian processes; image classification; mixture models; multi-threading; object detection; stereo image processing; adaptive Gaussian mixture; multithreaded architecture; objects classification; person detection; real time; stereo vision; technique fusion; Cameras; Classification algorithms; Instruction sets; Mobile communication; Stereo vision; Streaming media; Three-dimensional displays; Multi-threading; Person Detection; Stereo Vision; background-difference; classification;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Applications and Information Systems (WCCAIS), 2014 World Congress on
  • Conference_Location
    Hammamet
  • Print_ISBN
    978-1-4799-3350-1
  • Type

    conf

  • DOI
    10.1109/WCCAIS.2014.6916573
  • Filename
    6916573