With real time vessel surveillance data now becoming available at an increasing rate, there is a growing interest in applications that can forecast future vessel positions and routes, especially in congested and busy areas. Since vessels move in “free space”, a prerequisite to effectively forecasting vessels' future locations is accurately discovering representative tracks (common paths followed by several vessels). Towards this direction, this work introduces a novel data driven framework that is capable of detecting spatial representations of complete trajectories (from port to port) from massive Automatic Identification System (AIS) datasets. Along these lines, we present a novel approach for forecasting representative tracks from noisy and non-uniform datasets (number of points, sampling rates, coverage gaps etc.) at a global scale. Our technique models the entire space where the vessels traveled in the past, detecting the set of frequently followed locations. This gives our proposed method the ability to forecast the most likely movement from a given query location towards a destination port. Finally, we present extensive experiments with real-world data, so as to demonstrate the effectiveness of our proposed method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting representative trajectories from global AIS datasets


    Contributors:


    Publication date :

    2021-09-19


    Size :

    1499308 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Representative Small UAS Trajectories for Encounter Modeling

    Weinert, Andrew J. / Edwards, Matthew / Alvarez, Luis et al. | AIAA | 2020


    REPRESENTATIVE SMALL UAS TRAJECTORIES FOR ENCOUNTER MODELING

    Weinert, Andrew J. / Edwards, Matthew / Alvarez, Luis et al. | TIBKAT | 2020


    Generating Representative Small UAS Trajectories using Open Source Data

    Weinert, Andrew / Underhill, Ngaire | IEEE | 2018


    A Novel Scalable Framework to Reconstruct Vehicular Trajectories From Unreliable GPS Datasets

    Soares de Sousa, Roniel / Boukerche, Azzedine / Loureiro, Antonio A. F. | IEEE | 2023