• DocumentCode
    3097925
  • Title

    A Multiview Approach to Robust Detection in the Presence of Cast Shadows

  • Author

    Xu, Ming ; Ren, Jie ; Chen, Dongyong ; Smith, Jeremy S. ; Liu, Zhechi

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Xi´´an Jiaotong-Liverpool Univ., Suzhou, China
  • fYear
    2011
  • fDate
    12-15 Aug. 2011
  • Firstpage
    494
  • Lastpage
    499
  • Abstract
    This paper presents an object detection algorithm using multiple cameras, which is robust in the presence of cast shadows. The information fusion is based on homography mapping of the foreground regions to a top view image. The homography is based on multiple planar planes parallel to the ground plane. Two novel approaches to estimating such homography have been proposed. The results on an open video dataset are demonstrated.
  • Keywords
    image fusion; object detection; cast shadows; foreground regions; homography mapping; information fusion; multiple cameras; multiview approach; object detection; robust detection; top view image; Approximation methods; Cameras; Estimation; Head; Object detection; Robustness; Transmission line matrix methods; detection; homography; motion analysis; video surveillance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image and Graphics (ICIG), 2011 Sixth International Conference on
  • Conference_Location
    Hefei, Anhui
  • Print_ISBN
    978-1-4577-1560-0
  • Electronic_ISBN
    978-0-7695-4541-7
  • Type

    conf

  • DOI
    10.1109/ICIG.2011.180
  • Filename
    6005850