Time-varying Shape Tensors for Scenes with Multiply Moving Points


Anat Levin Lior Wolf  and Amnon Shashua

School of Computer Science and Engineering,

T he Hebrew University,

Jerusalem  Israel


We derive single view indexing functions for dynamic scenes ---

where dynamic is defined as a scene consisting of multiply moving

points each moving independently with constant velocity. The indexing

functions we derive are view independent and form a generalization of

the ``shape tensors'' associated with rigid scenes by introducing a


parameter. We derive those indexing

functions under full 3D projective, 3D affine, and various reduced



The indexing functions were implemented and tested for matching

against objects for which their non-rigid motion is an intrinsic part

of their character --- human gait recognition and hand gesture

identification are the two chosen application examples.