A New Algorithm for Optimal Filtering of Discrete-Time Stationary Processes
Anders Lindquist · SIAM Journal on Control · 1974
An algorithm (which does not involve the usual Riccati-type equation) for computing the gain matrices of the Kalman filter is presented. If the dimension k of the state space is much larger than that of the observation process, the number of nonlinear equations to be solved in each step is of order k rather than $k^2$ as by the usual procedure.