This paper presents an application of the optical character recognition, the interpretation of traffic signs from digital video images. Individual sign objects are segmented and normalized using image processing and coding approaches. An OCR-module based on probabilistic neural network and fuzzy logic is developed for isolation recognition. The extracted and identified sign objects are automatically converted to CAD form. A rule-based interpretation system is proposed and implemented for understanding traffic signs. An experiment was conducted on 97 highway signs and successful recognition and interpretation results are achieved. Such a system is required to assist drivers and for guidance and control of autonomous vehicles on highways.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Interpretation of traffic signs from digital video images


    Additional title:

    Die Interpretation von Verkehrszeichen aus digitalen Videobildern


    Contributors:
    Liu, Z. (author) / Benning, W. (author)


    Publication date :

    1998


    Size :

    4 Seiten, 3 Bilder, 6 Quellen



    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Recognition of supplementary signs for correct interpretation of traffic signs

    Puthon, Anne-Sophie / Moutarde, Fabien / Nashashibi, Fawzi | IEEE | 2013


    RECOGNITION OF SUPPLEMENTARY SIGNS FOR CORRECT INTERPRETATION OF TRAFFIC SIGNS

    Puthon, A. / Moutarde, F. / Nashashibi, F. et al. | British Library Conference Proceedings | 2013


    Recognition of supplementary signs for correct interpretation of traffic signs

    Puthon, Anne-Sophie / Moutarde, Fabien / Nashashibi, Fawzi | IEEE | 2013


    STUDENTS' INTERPRETATION OF TRAFFIC SIGNS IN LANGSA

    Bayos erwana syahroni | BASE | 2019

    Free access

    Traffic Safety Evaluation of Video Advertising Signs

    National Research Council (U.S.) | British Library Conference Proceedings | 2005