Object detection is challenging partly due to the limited discriminative power of local feature descriptors. We propose a two-step algorithm. First, a feature together with its spatial neighbors forms a flexible feature template. Two feature templates can be compared more informatively than two individual features without knowing the 3D object model. A large portion of false matches can be excluded after the first step. In a second global matching step, object detection is formulated as a graph-matching problem. A model graph is constructed by applying Delaunay triangulation on the surviving features. The best matching graph in an input image is computed by finding the maximum a posterior (MAP) estimate of a binary Markov random field with triangular maximal clique. The optimization is solved by the max-product algorithm (a.k.a. belief propagation). Experiments on both rigid and nonrigid objects demonstrate the generality and efficacy of the proposed methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object detection using 2D spatial ordering constraints


    Beteiligte:
    Yan Li, (Autor:in) / Tsin, Y. (Autor:in) / Genc, Y. (Autor:in) / Kanade, T. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    42545 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Object detection using 2D spatial ordering constraints

    Li, Y. / Tsin, Y. / Genc, Y. et al. | IEEE | 2005


    PARTIALLY OCCLUDED OBJECT DETECTION USING CONTEXT AND DEPTH ORDERING

    AYVACI ALPER / HEISELE BERND / ZHENG JINGJING | Europäisches Patentamt | 2017

    Freier Zugriff

    Monocular Motion Detection Using Spatial Constraints in a Unified Manner

    Klappstein, J. / Stein, F. / Franke, U. | British Library Conference Proceedings | 2006


    Monocular Motion Detection Using Spatial Constraints in a Unified Manner

    Klappstein, J. / Stein, F. / Franke, U. | IEEE | 2006