• DocumentCode
    860262
  • Title

    Direct recovery of planar-parallax from multiple frames

  • Author

    Irani, Michal ; Anandan, P. ; Cohen, Meir

  • Author_Institution
    Dept. of Comput. Sci. & Appl. Math., Weizmann Inst. of Sci., Rehovot, Israel
  • Volume
    24
  • Issue
    11
  • fYear
    2002
  • fDate
    11/1/2002 12:00:00 AM
  • Firstpage
    1528
  • Lastpage
    1534
  • Abstract
    We present an algorithm that estimates dense planar-parallax motion from multiple uncalibrated views of a 3D scene. This generalizes the "plane+parallax" recovery methods to more than two frames. The parallax motion of pixels across multiple frames (relative to a planar surface) is related to the 3D scene structure and the camera epipoles. The parallax field, the epipoles, and the 3D scene structure are estimated directly from image brightness variations across multiple frames, without precomputing correspondences.
  • Keywords
    brightness; computer vision; motion estimation; 3D scene; camera epipoles; correspondence estimation; dense planar-parallax motion estimation; image brightness variations; multiple frames; multiple uncalibrated views; pixels; planar surface; structure from motion; Brightness; Calibration; Cameras; Geometry; Image motion analysis; Layout; Motion analysis; Motion estimation; Search problems; Shape;
  • fLanguage
    English
  • Journal_Title
    Pattern Analysis and Machine Intelligence, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0162-8828
  • Type

    jour

  • DOI
    10.1109/TPAMI.2002.1046174
  • Filename
    1046174