Advanced technologies for monitoring and predicting pedestrian behaviors in public areas have gradually spread to ensure safe and efficient mobility in modern societies. Recently, the Covid-19 pandemic has further highlighted the potential of crowd analysis and monitoring tools, especially in gathering places where a minimum spacing has to be guaranteed, such as in transportation terminals.In this paper, starting from data acquired by a video recording system located outside the Milano Centrale railway station (Italy), several analyses have been conducted in order to investigate macroscopic parameters of pedestrian dynamics (i.e. densities, speeds and main walking directions), as well as testing strengths and weaknesses of Computer Vision algorithms for pedestrian detection. Results demonstrated that the precision of the system is reliable, as most of the people were “partially’’ tracked and the analysis of the macroscopic parameters are useful to identify effective intervention strategies in emergency and crowded situations. The analyses also deliver first insights for the development of a decision support system aimed at managing and supervising pedestrian dynamics.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pedestrian analysis for crowd monitoring: the Milan case study (Italy)


    Beteiligte:


    Erscheinungsdatum :

    14.06.2023


    Format / Umfang :

    806123 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    New street cars in Milan, Italy

    Hug, A.M. | Engineering Index Backfile | 1940


    Modeling Pedestrian Group Behavior in Crowd Evacuations

    Xiangli, Ying / Xu, Jie | Springer Verlag | 2024


    Mobility as a Service (MaaS) bundle uptake: a case study in Milan, Italy

    Fulvio Silvestri / Federico Silvestri / Pierluigi Coppola | DOAJ | 2025

    Freier Zugriff

    Identifying Latent Classes of Pedestrian Crowd Evacuees

    Haghani, Milad / Sarvi, Majid | Transportation Research Record | 2016