• DocumentCode
    3466673
  • Title

    Defect detection on rail surfaces by a vision based system

  • Author

    Deutschl, E. ; Gasser, C. ; Niel, A. ; Werschonig, J.

  • Author_Institution
    Inst. of Digital Image Process., Joanneum Res., Graz, Austria
  • fYear
    2004
  • fDate
    14-17 June 2004
  • Firstpage
    507
  • Lastpage
    511
  • Abstract
    A new vision based inspection technique for rail surface defects is presented. It replaces visual checks with an automatic inspection system. Colour line-scan cameras and a special image acquisition method- the so called spectral image differencing procedure (SIDP- allow the automatic detection of defects on rail surfaces, like flakes, cracks, grooves or break-offs by means of image processing. The system is already used by a rail manufacturer as inline system, but may also be used on testing vehicles. Practice shows that it produces reliable results even for heavily scaled surfaces, which usually pose serious problems to optical inspection systems due to their irregular texture.
  • Keywords
    automatic optical inspection; computer vision; image texture; rail traffic; railways; automatic detection; automatic inspection system; colour line scan cameras; image acquisition method; image processing; irregular texture; optical inspection systems; rail manufacturer; rail surface defect detection; rail traffic; spectral image differencing procedure; testing vehicles; vision based inspection technique; vision based system; Cameras; Color; Image processing; Inspection; Machine vision; Manufacturing; Rails; Surface cracks; System testing; Vehicles;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Vehicles Symposium, 2004 IEEE
  • Print_ISBN
    0-7803-8310-9
  • Type

    conf

  • DOI
    10.1109/IVS.2004.1336435
  • Filename
    1336435