• DocumentCode
    594840
  • Title

    Camera-less articulated trajectory reconstruction

  • Author

    Yingying Zhu ; Valmadre, J. ; Lucey, Simon

  • Author_Institution
    Univ. of Queensland, Brisbane, QLD, Australia
  • fYear
    2012
  • fDate
    11-15 Nov. 2012
  • Firstpage
    841
  • Lastpage
    844
  • Abstract
    In this paper, we address the problem of reconstructing 3D trajectories given only 2D point projection trajectories of an articulated structure. Hitherto, most applications of articulated trajectory reconstruction require: (i) relative lengths, and (ii) camera motion. We propose a novel extension that allows us to in many circumstances circumvent these limitations. Of particular note is our characterisation theoretically and demonstration empirically how agnostic one be to camera motion when using a DCT basis. Practical reconstructions of non-human articulated structures are depicted (e.g. koala, sea snake, tasmanian tiger) where articulated lengths and camera motion are unknown.
  • Keywords
    discrete cosine transforms; image reconstruction; 2D point projection trajectories; 3D trajectory reconstruction; DCT; articulated lengths; camera motion; camera-less articulated trajectory reconstruction; discrete cosine transform; nonhuman articulated structures; Cameras; Discrete cosine transforms; Equations; Estimation; Humans; Image reconstruction; Trajectory;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2012 21st International Conference on
  • Conference_Location
    Tsukuba
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4673-2216-4
  • Type

    conf

  • Filename
    6460265