• DocumentCode
    3276064
  • Title

    Shadow Removal via Flash/Noflash Illumination

  • Author

    Lu, Cheng ; Drew, Mark S. ; Finlayson, Graham D.

  • Author_Institution
    Sch. of Comput. Sci., Simon Fraser Univ., Vancouver, BC
  • fYear
    2006
  • fDate
    3-6 Oct. 2006
  • Firstpage
    198
  • Lastpage
    201
  • Abstract
    Shadows bedevil multimedia applications, e.g. seeing into shadow regions in surveillance video. Model-based and non-model based, statistical methods, spatial, temporal, and invariant-based methods have been devised for combatting the shadow problem. Here we take a different approach, by attenuating the shadow by utilizing a second image under another illuminant to remove the effect of shadow-edges from an edge map of each frame. As a precursor step, we examine flash/noflash still image pairs. A flash image provides lessened shadows, but other shadows are produced. We can produce a flash-only (no ambient) image by subtracting the two images, but several artifacts remain. Instead, we have used the pure-flash image to detect the ambient shadows [ICME06]. However that method may fail when there are flash-shadows or specularities in the copy region. Here we manipulate the gradient field using a smoothing step including the directionality of edges near the shadow boundary, with improved results
  • Keywords
    edge detection; gradient methods; statistical analysis; copy region; flash illumination; flash-only image; invariant-based method; pure-flash image; shadows bedevil multimedia application; smoothing step; spatial-temporal method; statistical method; Cameras; Image edge detection; Lighting; Merging; Pixel; Poisson equations; Shape; Smoothing methods; Statistical analysis; Surveillance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multimedia Signal Processing, 2006 IEEE 8th Workshop on
  • Conference_Location
    Victoria, BC
  • Print_ISBN
    0-7803-9751-7
  • Electronic_ISBN
    0-7803-9752-5
  • Type

    conf

  • DOI
    10.1109/MMSP.2006.285296
  • Filename
    4064546