This contribution proposes a method to generate object hypotheses from stereo obstacle detection and image motion. Our algorithm is a general approach since it does not require any a priori information about the shape of the observed objects but relies on the basic assumption that the objects are rigid. The algorithm has two processing stages: First, obstacles are detected using stereo vision. Second, each obstacle is segmented into clusters of consistent motion in 3D space. The clustering process explicitly accounts for measurement uncertainties of stereo disparity and 2d motion. Our system may serve as a general feature for higher-level object detection and classification.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fast Object Hypotheses Generation Using 3D Position and 3D Motion


    Contributors:
    Thao Dang, (author) / Hoffmann, C. (author)


    Publication date :

    2005-01-01


    Size :

    735163 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    About robust hypotheses generation and object validation in traffic scenes

    Schneider, Martin / Gayko, Jens / Goerick, Christian | IEEE | 2007


    About Robust Hypotheses Generation and Object Validation in Traffic Scenes

    Schneider, M. / Gayko, J. / Goerick, C. et al. | British Library Conference Proceedings | 2007


    OBJECT POSITION MEASUREMENT WITH AUTOMOTIVE CAMERA USING VEHICLE MOTION DATA

    BARAN MATTHEW | European Patent Office | 2016

    Free access

    Vulnerability classification of generic object hypotheses using a visual words approach

    Ruehle,J. / Arbitmann,M. / Denzler,J. et al. | Automotive engineering | 2014


    OBJECT POSITION MEASUREMENT WITH AUTOMOTIVE CAMERA USING VEHICLE MOTION DATA

    BARAN MATTHEW | European Patent Office | 2018

    Free access