In this paper a camera-based system for detection, tracking, and classification of U.S. speed signs is presented. The implemented application uses multiple connected stages and iteratively reduces the number of pixels to process for recognition. Possible sign locations are detected using a fast, shape-based interest operator. Remaining objects other than speed signs are discarded using a classifier similar to the Viola-Jones detector. Classification results from tracked candidates are utilized to improve recognition accuracy. On a standard PC the system reached a detection speed of 27fps with an accuracy of 98.8%. Including classification, speed sign recognition rates of 96.3% were achieved with a frame rate of approximately 11fps and one false alarm every 42s.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-time recognition of U.S. speed signs


    Contributors:


    Publication date :

    2008-06-01


    Size :

    1117170 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-Time Recognition of U.S. Speed Signs

    Keller, C.G. / Sprunk, C. / Bahlmann, C. et al. | British Library Conference Proceedings | 2008


    Real Time Road Signs Recognition

    Broggi, Alberto / Cerri, Pietro / Medici, Paolo et al. | IEEE | 2007


    Real Time Road Signs Recognition

    Broggi, A. / Cerri, P. / Medici, P. et al. | British Library Conference Proceedings | 2007


    An Efficient Real-Time Speed Limit Signs Recognition Based on Rotation Invariant Feature

    Liu, W. / Lv, J. / Gao, H. et al. | British Library Conference Proceedings | 2011


    Efficient recognition of speed limit signs

    Torresen, J. / Bakke, J.W. / Sekanina, L. | IEEE | 2004