• DocumentCode
    384364
  • Title

    Auto-calibration via the absolute quadric and scene constraints

  • Author

    Heyden, A. ; Huynh, D.Q.

  • Author_Institution
    Sch. of Technol. & Soc., Malmo Univ., Sweden
  • Volume
    2
  • fYear
    2002
  • fDate
    2002
  • Firstpage
    631
  • Abstract
    A scheme is described for incorporation of scene constraints into the structure from motion problem. Specifically, the absolute quadric is recovered with constraints imposed by orthogonal scene planes. The scheme involves a number of steps. A projective reconstruction is first obtained, followed by a linear technique to form an initial estimate of the absolute quadric. A nonlinear iteration then refines this quadric and the camera intrinsic parameters to upgrade the projective reconstruction to Euclidean. Finally, a bundle adjustment algorithm optimizes the Euclidean reconstruction to give a statistically optimal result. This chain of algorithms is essentially the same as used in auto-calibration and the novelty of this paper is the inclusion of orthogonal scene plane constraints in each step. The algorithms involved are demonstrated on both simulated and real data showing the performance and usability of the proposed scheme.
  • Keywords
    computer vision; image motion analysis; image reconstruction; image sequences; matrix algebra; minimisation; natural scenes; video signal processing; Euclidean reconstruction; absolute quadric recovery; auto-calibration; bundle adjustment algorithm; camera intrinsic parameters; computer vision; linear technique; nonlinear iteration; orthogonal scene planes; projective reconstruction; real data; scene constraints; simulated data; statistically optimal result; structure from motion problem; video sequence; Australia; Calibration; Computer vision; Digital cameras; Equations; Image reconstruction; Information technology; Layout; Nonlinear distortion; Object detection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2002. Proceedings. 16th International Conference on
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-1695-X
  • Type

    conf

  • DOI
    10.1109/ICPR.2002.1048381
  • Filename
    1048381