In this work, we focus on an improvement of a road obstacle recognition system using SVM based classifiers combination. The improvement relies on the use of Dempster-Shafer theory (DST) to combine in a finer way the outputs of SVM classifiers. The SVM classifiers were trained on different local and global features based on Speeded Up Robust Features (SURF) extracted from both visible and far-infrared images. A two-stage recognition method is also proposed to reduce the complexity of the overall system. The experiments are conducted on a set of images where obstacles occur at different scales, shapes and in difficult recognition situations. They show significant improvements while using DST combination compared to the classical combination strategies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evidential combination of SVM road obstacle classifiers in visible and far infrared images


    Contributors:
    Besbes, B. (author) / Ammar, S. (author) / Kessentini, Y. (author) / Rogozan, A. (author) / Bensrhair, A. (author)


    Publication date :

    2011-06-01


    Size :

    239883 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evidential Combination of SVM Road Obstacle Classifiers in Visible and Far Infrared Images

    Besbes, B. / Ammar, S. / kessentini, y. et al. | British Library Conference Proceedings | 2011



    Obstacle recognition using multiple kernel in visible and infrared images

    Apatean, Anca / Rogozan, Alexandrina / Bensrhair, Abdelaziz | IEEE | 2009


    Obstacle Recognition Using Multiple Kernel in Visible and Infrared Images

    Apatean, A. / Rogozan, A. / Bensrhair, A. | British Library Conference Proceedings | 2009


    FUSION OF FAR INFRARED AND VISIBLE IMAGES IN ENHANCED OBSTACLE DETECTION IN AUTOMOTIVE APPLICATIONS

    STEIN GIDEON / SHASHUA AMNON / GDALYAHU YORAM | European Patent Office | 2016

    Free access