Detailed environment perception is a crucial component of automated vehicles. However, to deal with the amount of perceived information, we also require segmentation strategies. Based on a grid map environment representation, well-suited for sensor fusion, free-space estimation and machine learning, we detect and classify objects using deep convolutional neural networks. As input for our networks we use a multi-layer grid map efficiently encoding 3D range sensor information. The inference output consists of a list of rotated bounding boxes with associated semantic classes. We conduct extensive ablation studies, highlight important design considerations when using grid maps and evaluate our models on the KITTI Bird's Eye View benchmark. Qualitative and quantitative benchmark results show that we achieve robust detection and state of the art accuracy solely using top-view grid maps from range sensor data.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks


    Contributors:


    Publication date :

    2018-11-01


    Size :

    1837792 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

    Engel, Nico / Hoermann, Stefan / Henzler, Philipp et al. | IEEE | 2018


    Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation

    Hoermann, Stefan / Henzler, Philipp / Bach, Martin et al. | IEEE | 2018


    Fully convolutional neural networks for dynamic object detection in grid maps

    Piewak, Florian / Rehfeld, Timo / Weber, Michael et al. | IEEE | 2017


    Obstacle Detection Based on Occupancy Grid Maps Using Stereovision System

    Kohara, Kenji / Suganuma, Naoki / Negishi, Tatsuyuki et al. | Springer Verlag | 2010