Abstract We address the problem of recognition of natural motions such as water, smoke and wind-blown vegetation. Such dynamic scenes exhibit characteristic stochastic motions, and we ask whether the scene contents can be recognized using motion information alone. Previous work on this problem has considered only the case where the texture samples have sufficient overlap to allow registration, so that the visual content of the scene is very similar between examples. In this paper we investigate the recognition of entirely non-overlapping views of the same underlying motion, specifically excluding appearance-based cues. We describe the scenes with time-series models—specifically multivariate autoregressive (AR) models—so the recognition problem becomes one of measuring distances between AR models. We show that existing techniques, when applied to non-overlapping sequences, have significantly lower performance than on static-camera data. We propose several new schemes, and show that some outperform the existing methods.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Shift-Invariant Dynamic Texture Recognition


    Beteiligte:


    Erscheinungsdatum :

    2006-01-01


    Format / Umfang :

    14 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Shift-Invariant Dynamic Texture Recognition

    Woolfe, F. / Fitzgibbon, A. | British Library Conference Proceedings | 2006


    The Illumination-Invariant Recognition of Texture in Color Texture

    Healey, G. / Wang, L. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995


    Dynamic Texture Recognition

    Saisan, P. / Doretto, G. / Wu, Y. N. et al. | British Library Conference Proceedings | 2001


    Dynamic texture recognition

    Saisan, P. / Doretto, G. / Ying Nian Wu, et al. | IEEE | 2001


    Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

    Lazebnik, S. / Schmid, C. / Ponce, J. et al. | British Library Conference Proceedings | 2003