We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model's structure to analytically average over many parameters. Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available. We also extend this hierarchical framework to scenes containing multiple objects.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning hierarchical models of scenes, objects, and parts


    Beteiligte:
    Sudderth, E.B. (Autor:in) / Torralba, A. (Autor:in) / Freeman, W.T. (Autor:in) / Willsky, A.S. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    1954268 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learning Hierarchical Models of Scenes, Objects, and Parts

    Sudderth, E. / Torralba, A. / Freeman, W. et al. | British Library Conference Proceedings | 2005


    Describing Visual Scenes Using Transformed Objects and Parts

    Sudderth, E. B. / Torralba, A. / Freeman, W. T. et al. | British Library Online Contents | 2008


    Guest Editorial: Scenes, Images and Objects

    Labrosse, F. d. / Zwiggelaar, R. / Liu, Y. et al. | British Library Online Contents | 2012


    Objects layout graph for 3D complex scenes

    Adan, A. / Merchan, P. / Salamanca, S. et al. | IEEE | 2005


    Objects Layout Graph for 3d Complex Scenes

    Adan, A. / Merchan, P. / Salamanca, S. et al. | British Library Conference Proceedings | 2005