In this contribution the authors present a probabilistic fusion framework using the Joint Integrated Probabilistic Data Association (JIPDA) algorithm for the sensor independent measurement fusion. The application of the framework in an automotive multi-target multi-sensor environment by fusing laser scanner and video will be shown. The existing JIPDA algorithm was extended to allow for the association of multiple measurements to the same object, which reduces the effects of splitted segments in the data preprocessing step of high-resolution sensors like laser scanners. Extensions are shown to speed up the JIPDA algorithm which lead to real-time performance with fragmented data. The algorithms were evaluated using real-world data in a research vehicle.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    A probabilistic sensor-independent fusion framework for automotive driver assistance systems


    Additional title:

    Eine wahrscheinlichkeitsgestütze, von Sensoren unabhängige Sensorfusionsplattform für Fahrerassistenzsysteme


    Contributors:


    Publication date :

    2009


    Size :

    6 Seiten, 5 Bilder, 8 Quellen


    Type of media :

    Conference paper


    Type of material :

    Storage medium


    Language :

    English




    A probabilistic sensor-independent fusion framework for automotive driver assistance systems

    Munz,M. / Maehlisch,M. / Dietmayer,K. et al. | Automotive engineering | 2009


    A sensor independent probabilistic fusion system for driver assistance systems

    Munz, Michael / Dietmayer, Klaus C. J. / Mahlisch, Mirko | IEEE | 2009


    Sensor Fusion for Driver-Assistance-Systems

    Vukotich, A. / Kirchner, A. / VDI | British Library Conference Proceedings | 2001


    Automotive driver assistance systems

    Scoltock,J. | Automotive engineering | 2010


    Probabilistic modeling of sensor properties in generic fusion systems for modern driver assistance systems

    Munz, Michael / Mählisch, Mirko / Dickmann, Jürgen et al. | IEEE | 2010