In this paper, we propose to fuse the LIDAR and monocular image in the framework of conditional random field to detect the road robustly in challenging scenarios. LIDAR points are aligned with pixels in image by cross calibration. Then boosted decision tree based classifiers are trained for image and point cloud respectively. The scores of the two kinds of classifiers are treated as the unary potentials of the corresponding pixel nodes of the random field. The fused conditional random field can be solved efficiently with graph cut. Extensive experiments tested on KITTI-Road benchmark show that our method reaches the state-of-the-art.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CRF based road detection with multi-sensor fusion


    Contributors:
    Xiao, Liang (author) / Dai, Bin (author) / Liu, Daxue (author) / Hu, Tingbo (author) / Wu, Tao (author)


    Publication date :

    2015-06-01


    Size :

    587381 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Road surface condition detection with multi-scale fusion

    TONG WEI / ZHAO QINGRONG / LITKOUHI BAKHTIAR B et al. | European Patent Office | 2018

    Free access

    ROAD SURFACE CONDITION DETECTION WITH MULTI-SCALE FUSION

    TONG WEI / ZHAO QINGRONG / LITKOUHI BAKHTIAR B et al. | European Patent Office | 2017

    Free access

    Multi-sensor fusion method for road condition measurement

    PENG SHASHA / WANG HONGGANG / CHENG HUASHAN et al. | European Patent Office | 2021

    Free access

    AEB control method based on multi-sensor road adhesion coefficient fusion

    ZHU BING / ZHAO NANNAN / XUE JINGWEI et al. | European Patent Office | 2024

    Free access

    FUSION-BASED WET ROAD SURFACE DETECTION

    ZHAO QINGRONG / LITKOUHI BAKHTIAR B / ZHANG QI et al. | European Patent Office | 2018

    Free access