In this paper we present an example-based approach to learn a given class of complex shapes, and recognize instances of that shape with outliers. The system consists of a two-layer custom-designed neural network. We apply this approach to the recognition of pedestrians carrying objects from a single camera. The system is able to capture and model an ample range of pedestrian shapes at varying poses and camera orientations, and achieves a 90% correct recognition rate.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Modelling pedestrian shapes for outlier detection: a neural net based approach


    Beteiligte:
    Nanda, H. (Autor:in) / Benabdelkedar, C. (Autor:in) / Davis, L. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    384668 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Stereo- and Neural Network-Based Pedestrian Detection

    Zhao, L. / Thorpe, C. E. | British Library Online Contents | 2000


    Pedestrian modelling

    Daamen, W. / Association for European Transport | British Library Conference Proceedings | 2009


    Cluster-Based Flight Trajectory Outlier Detection

    Mikol Forney / Banavar Sridhar / Kenneth Freeman | NTRS


    Pedestrian Detection with Convolutional Neural Networks

    Szarvas, M. / Yoshizawa, A. / Yamamoto, M. et al. | British Library Conference Proceedings | 2005