Multirate, multiresolution, recursive Kalman filter

被引：47

作者：

Cristi, R ^{[1
]}

Tummala, M ^{[1
]}

机构：

[1] USN, Postgrad Sch, Dept Elect & Comp Engn, Monterey, CA 93943 USA

来源：

SIGNAL PROCESSING | 2000年 / 80卷 / 09期

关键词：

D O I：

10.1016/S0165-1684(00)00104-3

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An approach to the decomposition of a signal into orthogonal components at different resolution levels is presented in this paper. It is shown that a signal generated by the standard state-space stochastic model can be decomposed into innovations at the different sampling frequencies associated to different levels of resolution. The main result is that these innovations are all uncorrelated with each other. A multiresolution multirate (MRMR) Kalman filter is then introduced which allows multiple MRMR observations to be combined in an optimal fashion. (C) 2000 Elsevier Science B.V. All rights reserved.

引用

页码：1945 / 1958

页数：14