This paper shows that the pose clustering method of object recognition can be decomposed into small sub-problems without loss of accuracy. Randomization can then be used to limit the number of sub-problems that need to be examined to achieve accurate recognition. These techniques are used to decrease the computational complexity of pose clustering. The clustering step is formulated as an efficient tree search of the pose space. This method requires little memory since not many poses are clustered at a time. Analysis shows that pose clustering is not inherently more sensitive to noise than other methods of generating hypotheses. Finally, experiments on real and synthetic data are presented.<>


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Time and space efficient pose clustering


    Beteiligte:
    Olson (Autor:in)


    Erscheinungsdatum :

    01.01.1994


    Format / Umfang :

    799858 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Time and Space Efficient Pose Clustering

    Olson, C. F. / Institute of Electrical and Electronics Engineers; Computer Society | British Library Conference Proceedings | 1994


    Efficient Pose Clustering Using a Randomized Algorithm

    Olson, C. F. | British Library Online Contents | 1997


    Pose Clustering From Stereo Data

    Hillenbrand, Ulrich | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2008

    Freier Zugriff

    Object Location by Parallel Pose Clustering

    Austin, W. J. / Wallace, A. M. | British Library Online Contents | 1998


    Simple yet efficient real-time pose-based action recognition

    Ludl, Dennis / Gulde, Thomas / Curio, Cristobal | IEEE | 2019