Title :
Optimal linear estimation and data fusion
Author :
Elliott, Robert J. ; Van Der Hoek, John
Author_Institution :
Haskayne Sch. of Bus., Univ. of Calgary, Alta., Canada
fDate :
4/1/2006 12:00:00 AM
Abstract :
Optimal mean square linear estimators are determined for general uncorrelated noise. We allow the noise variance matrix in the observation process to be singular. This requires properties of generalized inverses which are developed in Section II. The proofs appear to be new. When there are two observation sequences the optimal method of recursively fusing the two is determined. We derive a new formula for the covariance of the two estimates which then provides exact dynamics for a fused estimate.
Keywords :
filtering theory; matrix algebra; noise; sensor fusion; statistical analysis; data fusion; general uncorrelated noise; generalized inverses; noise variance matrix; observation process; optimal mean square linear estimation; Covariance matrix; Gaussian noise; Information filtering; Information filters; Mathematics; Nonlinear filters; Particle filters; Random variables; Recursive estimation; Vectors; Data fusion; optimal linear estimation;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2006.872768
