We present a novel technique for localisation of scene elements through sparse stereovision, targeted at obstacle detection. Applications are autonomous driving or robotics. Given a sparse 3D map computed from low-cost features and with many matching errors, we present a technique that can achieve localisation in a real-time context of all potential obstacles in front of the camera pair. We use v-disparity histograms for identifying relevant depth values, and extract from the 3D map successive subsets of points that correspond to these depth values. We apply a clustering step that provides the corresponding elements localisation. These clusters are then used to build a set of potential obstacles, considered as high level primitives. Experimental results on real images are provided.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Obstacle detection using sparse stereovision and clustering techniques


    Contributors:


    Publication date :

    2012-06-01


    Size :

    1344460 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Obstacle Detection Using Sparse Stereovision and Clustering Techniques

    Kramm, S. / Bensrhair, A. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2012



    Obstacle Detection in Urban Traffic Using Stereovision

    Huang, Y. / IEEE | British Library Conference Proceedings | 2005


    Long Range Obstacle Detection Using Laser Scanner and Stereovision

    Perrollaz, M. / Labayrade, R. / Royere, C. et al. | IEEE | 2006


    Long Range Obstacle Detection Using Laser Scanner and Stereovision

    Perrollaz, M. / Labayrade, R. / Royere, C. et al. | British Library Conference Proceedings | 2006