Most work in action recognition deals with sequences acquired by stationary cameras with fixed viewpoints. Due to the camera motion, the trajectories of the body parts contain not only the motion of the performing actor but also the motion of the camera. In addition to the camera motion, different viewpoints of the same action in different environments result in different trajectories, which can not be matched using standard approaches. In order to handle these problems, we propose to use the multi-view geometry between two actions. However, well known epipolar geometry of the static scenes where the cameras are stationary is not suitable for our task. Thus, we propose to extend the standard epipolar geometry to the geometry of dynamic scenes where the cameras are moving. We demonstrate the versatility of the proposed geometric approach for recognition of actions in a number of challenging sequences.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognizing human actions in videos acquired by uncalibrated moving cameras


    Contributors:
    Yilma, A. (author) / Shah, M. (author)


    Publication date :

    2005-01-01


    Size :

    523997 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras

    Yilmaz, A. / Shah, M. / IEEE | British Library Conference Proceedings | 2005


    Flexible 3D models from uncalibrated cameras

    Cootes, T. F. / Di Mauro, E. C. / Taylor, C. J. et al. | British Library Online Contents | 1996


    Free-Viewpoint Image Synthesis from Multiple-Viewimages Taken with Uncalibrated Moving Cameras

    Ito, Y. / Saito, H. | British Library Conference Proceedings | 2005


    Nondimensional star identification for uncalibrated star cameras

    Samaan, Malak A. / Mortari, Daniele / Junkins, John L. | Springer Verlag | 2006