MOTION ESTIMATION VIA DYNAMIC VISION

Estimating the three-dimensional motion of an object from a sequence o f projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation, manipulation, servo, tracking, docking, planning, and surveillance. Although ''visua l motion estimation'' is an old problem (the first formulations date b ack to the beginning of the century), only recently have tools from no nlinear systems estimation theory hinted at acceptable solutions. In t his paper we formulate the visual motion estimation problem in terms o f identification of nonlinear implicit systems with parameters on a to pological manifold and propose a dynamic solution either in the local coordinates or in the embedding space of the parameter manifold. Such a formulation has structural advantages over previous recursive scheme s, since the estimation of motion is decoupled from the estimation of the structure of the object being viewed, and therefore it is possible to handle occlusions in a principled way.