A nonlinear filtering method for geometric subspace tracking

Author

Srivastava, Anuj

Author_Institution

Dept. of Stat., Florida State Univ., Tallahassee, FL, USA

fYear

2000

fDate

2000

Firstpage

504

Lastpage

508

Abstract

We formulate the problem of tracking principal subspaces as a problem in nonlinear filtering. The subspaces are represented by their complex projection-matrices, and moving subspaces correspond to trajectories on the Grassmann manifold. Taking a Bayesian approach, we impose a smoothness prior on the subspace rotation. Combining ideas from importance sampling and sequential methods, we apply a recursive Monte Carlo approach to solving for MMSE estimates

Keywords

Bayes methods; Monte Carlo methods; filtering theory; importance sampling; least mean squares methods; nonlinear filters; tracking filters; Bayesian approach; Grassmann manifold; MMSE estimates; complex projection-matrices; geometric subspace tracking; importance sampling; nonlinear filtering method; recursive Monte Carlo approach; sequential methods; smoothness prior; subspace rotation; Bayesian methods; Filtering; Image analysis; Monte Carlo methods; Principal component analysis; Recursive estimation; Signal analysis; Statistics; Time varying systems; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensor Array and Multichannel Signal Processing Workshop. 2000. Proceedings of the 2000 IEEE

Conference_Location

Cambridge, MA

Print_ISBN

0-7803-6339-6

Type

conf

DOI

10.1109/SAM.2000.878060

Filename

878060