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

time-varying

parameter. We derive those indexing

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

configurations.

 

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.