• DocumentCode
    3475956
  • Title

    Fast Mosaic of High-Resolution Multiple-View Images of Surfaces from Architectural and Heritage Structures

  • Author

    Song, Ran ; Szymanski, John

  • Author_Institution
    Univ. of York, York
  • fYear
    2007
  • fDate
    18-21 Aug. 2007
  • Firstpage
    2270
  • Lastpage
    2275
  • Abstract
    This paper presents an automatic and fast method for creating seamless mosaics from images captured by a special aerial imaging system when imaging architectural and heritage structures. The whole scheme was made following three principles: speediness, robustness and the adaptability to the aerial image acquisition system in our project. We first extract keypoints and match them using the newest SURF algorithm, which can generate large sets of corresponding points fast and robustly. Then, a simple least-squares algorithm can estimate the projective transform parameters. In addition, to increase the robustness, lens distortion correction and global optimization strategy are also adopted. Finally, the aligned set of registered images is processed by an image fusion technique to produce effectively seamless composite images.
  • Keywords
    architecture; image fusion; image matching; image registration; image resolution; image segmentation; least squares approximations; optimisation; SURF algorithm; aerial image acquisition system; architectural-heritage structure; global optimization strategy; high-resolution multiple-view image mosaic; image fusion technique; image matching; image registration; keypoint extraction; least-squares algorithm; lens distortion correction; Control systems; Digital cameras; High-resolution imaging; Image fusion; Lenses; Lighting control; Motion control; Radio control; Robustness; Virtual reality; Global Optimization; Image Fusion; Lens Distortion Correction; SURF;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automation and Logistics, 2007 IEEE International Conference on
  • Conference_Location
    Jinan
  • Print_ISBN
    978-1-4244-1531-1
  • Type

    conf

  • DOI
    10.1109/ICAL.2007.4338954
  • Filename
    4338954