• DocumentCode
    2251335
  • Title

    Automatic information extraction of traffic panels based on computer vision

  • Author

    González, Á ; Bergasa, L.M. ; Gavilán, M. ; Sotelo, M.A. ; Herranz, F. ; Fernández, C.

  • Author_Institution
    Dept. de Electron., Univ. de Alcala, Alcala de Henares, Spain
  • fYear
    2009
  • fDate
    4-7 Oct. 2009
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    Computer vision systems used on road maintenance, either related to signs or to the road itself, are playing a major role in many countries because of the higher investment on public works of this kind. These systems are able to collect a wide range of information automatically and quickly, with the aim of improving road safety. In this context, the suitability of the information contained on the road signs located above the road, typically known as traffic panels, is vital for a correct and safe use by the road user. This paper describes an approach to the first steps of a developing system which will be able to make an inventory and to check the reliability of the information contained on the traffic panels, and whose final aim is to take part on an automatic visual inspection system of signs and panels.
  • Keywords
    Hough transforms; automatic optical inspection; computer vision; feature extraction; image segmentation; road safety; road traffic; traffic engineering computing; Hough transform; automatic information extraction; automatic visual inspection system; computer vision system; image segmentation; inventory system; public works investment; road maintenance; road safety; traffic panel; traffic sign; Cameras; Computer vision; Data mining; Inspection; Intelligent transportation systems; Roads; Vehicles; Video recording; Video sequences; Visualization; Hough transform; image segmentation; panel reorientation; traffic panels;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Transportation Systems, 2009. ITSC '09. 12th International IEEE Conference on
  • Conference_Location
    St. Louis, MO
  • Print_ISBN
    978-1-4244-5519-5
  • Electronic_ISBN
    978-1-4244-5520-1
  • Type

    conf

  • DOI
    10.1109/ITSC.2009.5309872
  • Filename
    5309872