We present a video event mining framework that consists of comprehensive set of tools for event detection, annotation, content browsing and a video analysis database. Central to our framework is the video analysis database and the VideoViews database browser that supports both top-down and bottom-up analysis of the video data. to support event mining. We present two methods for video event detection, namely an expert system (CLIPS) rules based approach and a 2-level Hidden Markov Model built upon split and merge behaviors. We devised interfaces for these event detection methods to be operated on the video data in the database for training and detection. We embed scene, object and event data into the video stream as metadata. VideoViews provides interfaces to event detection and video annotation tools. Our video analysis database description scheme represents the structure of the video data from video clips to scenes, objects and their tracks as well as the semantics from simple behaviors to more complex events that may take place over multiple video scenes and/or clips. This framework and the combination of tools enable the users to visualize the raw video data and the processed video information from a number of perspectives facilitating efficient video event mining.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Video Event Detection and Mining Framework


    Beteiligte:
    Guler, Sadiye (Autor:in) / Liang, Winnie H. (Autor:in) / Pushee, Ian A. (Autor:in)


    Erscheinungsdatum :

    2003-06-01


    Format / Umfang :

    520861 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Traffic event video detection system

    HE SONGSONG / TAO JIANWEN / DAN YUFANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    VIDEO EVENT DETECTION AND NOTIFICATION

    CAO SONG / DUAN GENQUAN / CARTER DAVID | Europäisches Patentamt | 2017

    Freier Zugriff

    A multimedia data mining framework: mining information from traffic video sequences

    Chen, Shu-Ching / Shyu, Mei-Ling / Zhang, Chengcui et al. | Tema Archiv | 2002


    Volumetric Features for Video Event Detection

    Ke, Y. / Sukthankar, R. / Hebert, M. | British Library Online Contents | 2010