In this paper existing map matching algorithms are combined and modified such, that the resulting algorithm is suitable for the implementation on the graphics processing unit (GPU). The map matching algorithm implemented on GPU consists of a geometrical and topological processing step, which provides high accuracy with high efficiency at the same time. An important building block of the implementation is the parallelization of the R∗-tree search. An efficient implementation is achieved by high data parallelism and minimal divergence between execution blocks. The presented map matching algorithm performs better than available open source implementations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Boosting Performance of Map Matching Algorithms by Parallelization on Graphics Processors


    Contributors:


    Publication date :

    2017-06-01


    Size :

    730272 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MASSIVE PARALLELIZATION OF TRAJECTORY PROPAGATIONS USING GRAPHICS PROCESSING UNITS

    Renk, Florian / Geda, Márton / Schrammel, Fabian et al. | TIBKAT | 2021



    Parallelization of Particle Filter Based Localization and Map Matching Algorithms on Multicore/Manycore Architectures

    Par, K. / Tosun, O. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2011


    Using NVIDIA multicore graphics processors in image decoding

    Kozlov, I. M. | British Library Online Contents | 2014


    Realistic 3D Graphics Synthesis on Parallel Multi-Processors

    Huang, X. / Zheng, N. / Jia, T. et al | British Library Online Contents | 1996