• DocumentCode
    3014818
  • Title

    Robust image registration for multi-frame mobile applications

  • Author

    Tico, Marius ; Pulli, Kari

  • Author_Institution
    Nokia Res. Center, Palo Alto, CA, USA
  • fYear
    2010
  • fDate
    7-10 Nov. 2010
  • Firstpage
    860
  • Lastpage
    864
  • Abstract
    We present an approach to global image registration that allows a robust and efficient image alignment, required in various mobile imaging applications (e.g. multi-frame image enhancement, high dynamic range imaging, panoramic image stitching). The proposed method follows a coarse to fine strategy, adopting different registration techniques at coarse and fine resolution levels. Coarse levels are registered using an image-based approach, whereas fine levels are registered based on salient features detected in the two images. The method is robust to blur and noise image degradations, as well as to illumination changes. In addition, due to low computational complexity, the proposed method is included in several mobile imaging applications that are briefly summarized in the paper.
  • Keywords
    computational complexity; image registration; image resolution; mobile radio; object detection; coarse levels; computational complexity; feature detection; mobile imaging applications; noise image degradations; robust image registration; Cameras; Image registration; Image resolution; Noise; Pixel; Robustness;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signals, Systems and Computers (ASILOMAR), 2010 Conference Record of the Forty Fourth Asilomar Conference on
  • Conference_Location
    Pacific Grove, CA
  • ISSN
    1058-6393
  • Print_ISBN
    978-1-4244-9722-5
  • Type

    conf

  • DOI
    10.1109/ACSSC.2010.5757689
  • Filename
    5757689