A multi-sensor obstacle detection system for the use on railway tracks was specified, implemented and tested. The applied look-ahead sensors are: Video cameras (optical passive) and LIDAR (optical active). The objects delivered by the sensors were fused, classified and their description is sent to the central vehicle unit. It has been shown that the fusion of active and passive optical sensors and a railway track data base lead to very robust system performance. The overall detection performance has shown to be comparable to that of a human driver. We have successfully demonstrated a multi-sensor obstacle detection system prototype having an up to 400 m look-ahead range under typical operating conditions. The prototype was tried out on a test vehicle (Train Control TestCar) driving up to 120 km/h over long distances across Germany. Future steps are the optimization, miniaturization and the integration of the active and passive sensor components of the obstacle detection system. The computational optimization of the object detection algorithms is another important step in order to reduce necessary computing resources.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-sensor obstacle detection on railway tracks


    Contributors:
    Mockel, S. (author) / Scherer, F. (author) / Schuster, P.F. (author)


    Publication date :

    2003-01-01


    Size :

    443868 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-sensor obstacle detection on railway tracks

    Mockel, S. / Scherer, F. / Schuster, P.F. | Tema Archive | 2003


    Local and Global Information in Obstacle Detection on Railway Tracks

    Brucker, Matthias / Cramariuc, Andrei / von Einem, Cornelius et al. | ArXiv | 2023

    Free access

    Machine Learning based Obstacle Detection for Avoiding Accidents on Railway Tracks

    Prakash, R.Meena / Vimala, M. / Keerthana, S. et al. | IEEE | 2023



    Long range obstacle detection on automated railroad tracks

    Scherer, F. / Schuster, P. / Möckel, S. | Tema Archive | 2003