• DocumentCode
    2607610
  • Title

    Moving cast shadows detection based on ratio edge

  • Author

    Zhang, Wei ; Fang, Xiang Zhong ; Yang, Xiaokang

  • Author_Institution
    Inst. of Image Commun. & Inf. Process., Shanghai Jiao Tong Univ.
  • Volume
    4
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    73
  • Lastpage
    76
  • Abstract
    In this paper we propose a novel method for moving cast shadows detection. Based on the analysis to the physical model of moving shadows, we prove that the ratio edge is illumination invariant. The distribution of the ratio edge is discussed and a significance test is performed to classify each image pixel into foreground object or moving shadow. Experimental results on typical scenes show that the proposed method can detect moving shadows robustly
  • Keywords
    image classification; object detection; foreground object; illumination invariant; image pixel classification; moving cast shadow detection; ratio edge distribution; Image communication; Image edge detection; Information processing; Layout; Light sources; Lighting; Performance evaluation; Pixel; Testing; Vehicles;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-2521-0
  • Type

    conf

  • DOI
    10.1109/ICPR.2006.818
  • Filename
    1699786