Kronecker canonical forms for perspective systems with applications to parameter identification

We introduce canonical forms for perspective dynamical systems and illustrate their application to parameter identification with the aid of a single CCD camera as sensor. We show that the parameters in the canonical form can be identified uniquely using an extended Kalman filter (EKF) provided that the a priori estimates of the parameters are close to the true value. The main contribution of the paper is twofold: parameterization of perspective dynamical systems with a given set of Kronecker indices and application of the EKF technique to identify the parameters