• DocumentCode
    2869447
  • Title

    Landmark identification based on projective and permutation invariant vectors

  • Author

    Colios, Christos I. ; Trahanias, Panos E.

  • Author_Institution
    Inst. of Comput. Sci., Foundation for Res. Technol., Hellas, Greece
  • Volume
    4
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    128
  • Abstract
    We address the issue of environment representation for navigational tasks by using reference scene patterns, the so-called landmarks, to adequately describe the robot´s workspace. Mathematical tools from projective geometry are employed for landmark identification. A complete framework is presented for landmark extraction and recognition based on projective and point-permutation invariant vectors
  • Keywords
    image recognition; mobile robots; path planning; robot vision; environment representation; landmark extraction; landmark identification; landmark recognition; navigational tasks; permutation invariant vectors; projective geometry; projective invariant vectors; reference scene patterns; Cognitive robotics; Computational geometry; Computer science; Contracts; Detectors; Indoor environments; Layout; Navigation; Robustness; Virtual colonoscopy;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2000. Proceedings. 15th International Conference on
  • Conference_Location
    Barcelona
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-0750-6
  • Type

    conf

  • DOI
    10.1109/ICPR.2000.902880
  • Filename
    902880