In this paper a vision-based system for cyclist detection for highly automated vehicles is presented which utilize a deep convolutional neural network. Given the limited amount of LiDAR data for cyclists for the task of cyclist detection, a realistic synthetic data generation pipeline has been adopted in this work to overcome this problem by generate virtually unlimited number of synthetic training, testing and validation depth image datasets of cyclists. Then, using a holistic detection technique, any instances of cyclists can be localised in the generated synthetic depth images which can be shown as a down-sampled instances of 3D LiDAR data. The proposed technique in this paper, exploits the Faster Region-based Convolutional Network (Faster R-CNN) architecture for simultaneously detecting and localising any instances of cyclists in depth images. The trained Faster R-CNN models have been tested on the widely popular KITTI urban dataset and the results show that the proposed framework outperforms the classical HOG+SVM object localisation method with increased 21% in average precision. This shows the ability of the trained models using the proposed framework to generalise from synthetic training dataset to operate on live dataset.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Cyclist detection in LIDAR scans using faster R-CNN and synthetic depth images


    Beteiligte:
    Saleh, Khaled (Autor:in) / Hossny, Mohammed (Autor:in) / Hossny, Ahmed (Autor:in) / Nahavandi, Saeid (Autor:in)


    Erscheinungsdatum :

    2017-10-01


    Format / Umfang :

    887307 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Cyclist Intent Prediction using 3D LIDAR Sensors for Fully Automated Vehicles

    Saleh, K. / Abobakr, A. / Nahavandi, D. et al. | IEEE | 2019


    In Depth Interviews With Road Users in Cyclist Accidents

    Bernhoft, I. M. | British Library Conference Proceedings | 1999


    Situation of Cyclist Accidents and Vehicle-Cyclist Impact Tests

    Kubota, M. | British Library Online Contents | 1998


    Cyclist accessory system

    XIAOYANG ZHANG | Europäisches Patentamt | 2017

    Freier Zugriff

    Cyclist warning system

    GAVIN ROBERT THODAY / PAUL MAISEY | Europäisches Patentamt | 2017

    Freier Zugriff