This contribution presents a robust pedestrian detection system at night that fuses a camera sensor and a scanning radar sensor on feature level. Each sensor defines an overdetermined set of features to be selected and parameterized using the supervised training algorithm AdaBoost. This technique assures an optimal selection and weighting of the features from both sensors depending on their discriminative power for the classification task. In the radar plane a new complex signal filter has been derived which describes a local similarity measure of velocity differences. In order to achieve realtime capability multiple classifiers are combined using a cascade.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Camera and imaging radar feature level sensorfusion for night vision pedestrian recognition


    Contributors:


    Publication date :

    2009-06-01


    Size :

    1926645 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Camera and Imaging Radar Feature Level Sensorfusion for Night Vision Pedestrian Recognition

    Serfling, M. / Loehlein, O. / Schweiger, R. et al. | British Library Conference Proceedings | 2009


    SENSORFUSION

    SITHIRAVEL RAJIV / LAPORTE DAVID / CAREY KYLE J | European Patent Office | 2020

    Free access

    SENSORFUSION

    BANERJEE GAURAB / NAGASAMY VIJAY | European Patent Office | 2023

    Free access

    ADAPTIVE SENSORFUSION

    SOLTANI BOZCHALOOI IMAN / ASSADIAN FRANCIS / SCARIA LISA | European Patent Office | 2021

    Free access