• DocumentCode
    398536
  • Title

    Matching with epipolar gradient features and edge transfer

  • Author

    Vincent, Étienne ; Laganière, Robert

  • Author_Institution
    Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont., Canada
  • Volume
    1
  • fYear
    2003
  • fDate
    14-17 Sept. 2003
  • Abstract
    A method for quickly and reliably selecting and matching points from three views of a scene is presented. The points that are selected are based on the concept of epipolar gradients, and consist in stable and relevant image features. Then, the selected points are matched using edge transfer, resulting in a measure of consistency for point triplets and the edges on which they lie, with the camera system´s trinocular geometry. This matching scheme is invariant to image deformations due to changes in viewpoint.
  • Keywords
    cameras; edge detection; feature extraction; geometry; gradient methods; image matching; camera system trinocular geometry; edge transfer; epipolar gradient feature; image deformation; matching point selection; point triplet; Application software; Cameras; Computer vision; Detectors; Equations; Geometry; Information technology; Layout; Reliability engineering; Tensile stress;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
  • ISSN
    1522-4880
  • Print_ISBN
    0-7803-7750-8
  • Type

    conf

  • DOI
    10.1109/ICIP.2003.1246952
  • Filename
    1246952