Physically based dynamic models are able to describe variable shapes without prior training. Their behaviour to find an object is intuitive, which facilitates corrections of false results. Expressing shape variation as physical feature, however, may be difficult because the physics of the model has little to do with the shape variation of instances of a class of objects. We present a dynamic model, which automatically adapts model parameters based on results of previous segmentations. The model was applied to artificial data and to images of leaves. Results show that the adapted model finds the correct shape more accurate than a model with preset parameters. Investigation of the parameterisation from adaptation also showed that they may be interpreted in terms of the semantics of the shape class represented.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A weight-adaptive dynamic model for shape segmentation


    Beteiligte:
    Toennies, K.D. (Autor:in) / Benedix, P. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    249141 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Weight-Adaptive Dynamic Model for Shape Segmentation

    Toennies, K. D. / Benedix, P. | British Library Conference Proceedings | 2005


    Spatial-Temporal Dynamic Segmentation Model

    Wu, H. / Liu, Z. / Zhang, S. et al. | British Library Conference Proceedings | 2010


    Shape-Based Mutual Segmentation

    Riklin-Raviv, T. / Sochen, N. / Kiryati, N. | British Library Online Contents | 2008


    URS: A Light-Weight Segmentation Model for Train Wheelset Monitoring

    Guo, Xiaoxuan / Ji, Zhenyan / Feng, Qibo et al. | IEEE | 2023


    Compressible dynamic stall control using a shape adaptive airfoil

    Chandrasekhara, M. / Wilder, M. / Carr, L. | AIAA | 1999