Pedestrian recognition is one of the key technologies for advanced driver assistance systems and autonomous driving systems. The present paper proposes a fusion system for reliable pedestrian recognition using high-definition LIDAR and a vision sensor to achieve high performance under various conditions. Pedestrian candidates are extracted from two sensors in parallel by support vector machine-based classifiers. In particular, the region of interest in the image processing is set based on information about objects derived from the LIDAR processing in order to reduce false positives as well as the computational burden. All candidates are integrated by their likelihood, as calculated from their classification scores, using multiple thresholds according to the detection condition of the target in two sensors. A quantitative evaluation in a road environment confirms the effectiveness of the proposed system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Reliable pedestrian recognition combining high-definition LIDAR and vision data


    Contributors:


    Publication date :

    2012-09-01


    Size :

    548014 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Pedestrian Recognition Integrating High-definition LIDAR and Vision

    Kidono, K. / Naito, T. / Miura, J. | British Library Online Contents | 2012


    Pedestrian Recognition Using High-Definition LIDAR

    Kidono, K. / Miyasaka, T. / Watanabe, A. et al. | British Library Conference Proceedings | 2011


    Pedestrian recognition using high-definition LIDAR

    Kidono, K. / Miyasaka, T. / Watanabe, A. et al. | IEEE | 2011


    Pedestrian Detection Based on Integration of Vision and High-definition LIDAR

    Kidono, K. / Goto, K. / Naito, T. et al. | British Library Conference Proceedings | 2011


    Vision-based pedestrian detection -reliable pedestrian candidate detection by combining IPM and a 1D profile

    Ma, Guanglin / Park, Su-Birm / Muller-Schneiders, Stefan et al. | IEEE | 2007