A first step towards an understanding of the semantic content in a video is the reliable detection and recognition of actions performed by objects. This is a difficult problem due to the enormous variability in an action's appearance when seen from different viewpoints and/or at different times. In this paper we address the recognition of actions by taking a novel approach that models actions as special types of 3D objects. Specifically, we observe that any action can be represented as a generalized cylinder, called the action cylinder. Reliable recognition is achieved by recovering the viewpoint transformation between the reference (model) and given action cylinders. A set of 8 corresponding points from time-wise corresponding cross-sections is shown to be sufficient to align the two cylinders under perspective projection. A surprising conclusion from visualizing actions as objects is that rigid, articulated, and nonrigid actions can all be modeled in a uniform framework.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognizing action events from multiple viewpoints


    Contributors:


    Publication date :

    2001-01-01


    Size :

    929364 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recognizing Action Events from Multiple Viewpoints

    Syeda-Mahmood, T. / Vasilescu, A. / Sethi, S. et al. | British Library Conference Proceedings | 2001



    Direct Virtual Viewpoint Synthesis from Multiple Viewpoints

    Ding, Y. / Redmill, D. | British Library Conference Proceedings | 2005


    Recognizing Planned, Multiperson Action

    Intille, S. S. / Bobick, A. F. | British Library Online Contents | 2001


    Global viewpoints

    Online Contents | 1998