View and scale insensitive action representation and recognition

In this paper a view and scale insensitive action representation VSI-Surf is proposed. Scale invariant shape descriptor R-transform is used to extract compact 1D feature from view insensitive posture representation "Envelop shape" which uses only two orthogonal cameras without accurate calibration. Considering action is a posture sequence, to integrate temporal information, 1D posture feature is then extended in time dimension. Then we get an action representation insensitive to viewpoint and scale, which is called VSI-Surf. Actions recognition is processed in a hierarchical framework, in which body actions and gestures are recognized in different level. Encouraging recognition results have been demonstrated on the multi-view IXMAS action dataset.