• DocumentCode
    1617496
  • Title

    Fast registration of multispectral images using orthogonal transform features

  • Author

    Chandra, D. V Satish

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Kansas State Univ., Manhattan, KS, USA
  • fYear
    1992
  • Firstpage
    703
  • Abstract
    A method of accomplishing multiple image registration using rationalized Haar transform coefficient features is presented. The transform technique described possesses a fast computational algorithm which requires only additions and subtractions, making it attractive for real-time implementation. The registration accuracy, computational complexity and feasibility of real-time implementation of the transform method are compared to that of the commonly used correlation method
  • Keywords
    computational complexity; image processing; real-time systems; transforms; computational complexity; fast computational algorithm; multiple image registration; multispectral images; orthogonal transform features; rationalized Haar transform coefficient features; real-time implementation; registration accuracy; Clouds; Computational complexity; Correlation; Digital images; Image registration; Motion analysis; Motion detection; Multispectral imaging; Object detection; Target tracking;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 1992., Proceedings of the 35th Midwest Symposium on
  • Conference_Location
    Washington, DC
  • Print_ISBN
    0-7803-0510-8
  • Type

    conf

  • DOI
    10.1109/MWSCAS.1992.271151
  • Filename
    271151