Vessel traffic flow detection is an important and challenging research field and has been broadly investigated in the past. Researchers have done an extensive work, and various devices have been developed to extract vessel traffic information, such as Vessel Traffic Service System (VTS), Automatic Identification System (AIS), and intelligent visual surveillance system. In this paper, a novel detection method is proposed based on Kalman filter to extract vessel traffic flow from optical imagery. The proposed algorithm includes two stages: moving vessel detection and dynamic vessel tracking. Vessel detection is a key step and the concept of tracking vessel is built upon the vessel-segmentation method. According to the segmented vessel shape, a three-step predict method is proposed based on Kalman filter to track each vessel. The proposed method has been tested on a number of monocular vessel traffic flow image sequences. The experimental results show that the algorithm is effective and robust.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vessel Traffic Flow Detection and Tracking in River


    Beteiligte:
    Xie, Lei (Autor:in) / Chu, Xiumin (Autor:in) / Huang, Ming (Autor:in) / Yan, Zhongzhen (Autor:in)

    Kongress:

    First International Conference on Transportation Information and Safety (ICTIS) ; 2011 ; Wuhan, China


    Erschienen in:

    ICTIS 2011 ; 1788-1797


    Erscheinungsdatum :

    2011-06-16




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch