Maritime data, such as Automatic Identification System (AIS)-based, are characterized as high volume and complex. Utilizing these data and discovering potential value is challenging for the maritime domain. This paper provides a framework for visual analysis of ship trajectory data. This framework first performs a wrangling process to get clean data. Then the density of ships over the map is estimated by the kernel density estimator (KDE). Furthermore, an interactive 3D model is carried out based on the estimated density for further analysis. We applied the framework to analyze the shipping traffic in the Qiongzhou Strait of China. The results prove that our framework can efficiently depict the ship’s trajectory and regional ship operation and analyze the ship’s behavior in a local area. We assert our work can fruitfully support further analysis and prediction of the ship’s movement mode and detection of abnormal behavior.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Visual Analysis of Ship Trajectories Based on Kernel Density Estimation


    Contributors:
    Shi, Juhong (author) / Pan, Yushan (author) / Xiang, Yang (author) / Liu, Xinpeng (author) / Wang, Yihong (author) / Ji, Chengtao (author)


    Publication date :

    2023-05-12


    Size :

    6822820 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Generating lane level road data from vehicle trajectories using Kernel Density Estimation

    Uduwaragoda, E.R.I.A.C.M. / Perera, A.S. / Dias, S.A.D. | IEEE | 2013



    Knowledge-based clustering of ship trajectories using density-based approach

    Liu, Bo / de Souza, Erico N. / Matwin, Stan et al. | IEEE | 2014


    Trajectory learning and analysis based on kernel density estimation

    Zhou, Jianying / Wang, Kunfeng / Tang, Shuming et al. | IEEE | 2009