This work proposes a novel classifier-fusion scheme using learning algorithms, i.e. syntactic models, instead of the usual Bayesian or heuristic rules. Moreover, this paper complements the previous comparative studies on DaimlerChrysler Automotive Dataset, offering a set of complementary experiments using feature extractor and classifier combinations. The experimental results provide evidence of the effectiveness of our methods regarding false positive rate, AUC, and accuracy, which reached 96.67%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Trainable classifier-fusion schemes: An application to pedestrian detection


    Contributors:


    Publication date :

    2009-10-01


    Size :

    402725 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Trainable N-tuple Pattern classifier and its Application for Monitoring Fish Underwater

    Chan, D. / Tillett, R. D. / Hockaday, S. et al. | British Library Conference Proceedings | 1999


    A Cascaded Classifier for Pedestrian Detection

    Xu, Y. W. / Cao, X. B. / Qiao, H. et al. | British Library Conference Proceedings | 2006


    A Cascaded Classifier for Pedestrian Detection

    Xu, Y.W. / Cao, X.B. / Qiao, H. et al. | IEEE | 2006


    740-014: Pedestrian Detection using HOGVA Feature and Local Pedestrian Classifier

    Kasai, H. / Onoguchi, K. / International Association of Science and Technology for Development | British Library Conference Proceedings | 2011


    A Trainable System for Object Detection

    Papageorgiou, C. / Poggio, T. | British Library Online Contents | 2000