Conventional trajectory-based vehicular traffic analysis approaches work well in simple environments such as a single crossing but they do not scale to more structurally complex environments such as networks of interconnected crossings (e.g., urban road networks). Local trajectory models are necessary to cope with the multi-modality of such structures, which in turn introduces new challenges. These larger and more complex environments increase the occurrences of lack of motion and self-overlaps in observed trajectories which impose further challenges. In this paper we consider the problem of motion pattern recognition in the setting of sequential local motion pattern models. That is, classifying sub-trajectories from observed trajectories in accordance with which motion pattern that best explains it. We introduce a Gaussian process (GP) based modeling approach which outperforms the state-of-the-art GP based motion pattern approaches at this task. We investigate the impact of varying local model overlap and the length of the observed trajectory trace on the classification quality. We further show that introducing a pre-processing step filtering out stops from the training data significantly improves the classification performance. The approach is evaluated using real GPS position data from city buses driving in urban areas.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Gaussian Process Based Motion Pattern Recognition with Sequential Local Models


    Beteiligte:
    Tiger, Mattias (Autor:in) / Heintz, Fredrik (Autor:in)


    Erscheinungsdatum :

    01.06.2018


    Format / Umfang :

    1525777 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Ship control motion forecasting method and system based on local Gaussian process regression

    OUYANG ZILU / ZOU LU / LIU JINZHOU et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Time sequential nonlinear correlations for optical pattern recognition

    Garcia-Martinez, P. / Arsenault, H. H. / Ferreira, C. et al. | British Library Conference Proceedings | 2001



    Combining local-physical and global-statistical models for sequential deformable shape from motion

    Agudo Martínez, Antonio / Moreno-Noguer, Francesc | BASE | 2017

    Freier Zugriff

    Combining Local-Physical and Global-Statistical Models for Sequential Deformable Shape from Motion

    Agudo, A. / Moreno-Noguer, F. | British Library Online Contents | 2017