AN EFFICIENT PARTICLE FILTERING TECHNIQUE ON THE GRASSMANN MANIFOLD

被引：18

作者：

Rentmeesters, Quentin ^{[1
]}

Absil, P. -A. ^{[1
]}

Van Dooren, Paul ^{[1
]}

Gallivan, Kyle ^{[2
]}

Srivastava, Anuj ^{[2
]}

机构：

[1] Catholic Univ Louvain, B-1348 Louvain, Belgium

[2] Florida State Univ, Tallahassee, FL 32306 USA

来源：

2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年

关键词：

time-varying subspace learning; Grassmann manifold; particle filtering; TRACKING;

D O I：

10.1109/ICASSP.2010.5495828

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Subspace tracking methods are widespread in signal and image processing. To reduce the influence of perturbations or outliers on the measurements, some authors have used a stochastic piecewise constant velocity model on the Grassmann manifold. This paper presents an efficient way to simulate such a model using a particular representation of the Grassmann manifold. By doing so, we can reduce the spatial and time complexity of filtering techniques based on this model. We also propose an approximation of this system which can be computed in a finite number of operations and show similar results if the subspace variation is slow.

引用

页码：3838 / 3841

页数：4

共 5 条

[1] Absil PA, 2008, OPTIMIZATION ALGORITHMS ON MATRIX MANIFOLDS, P1
[2] The geometry of algorithms with orthogonality constraints
Edelman, A
Arias, TA
Smith, ST
[J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 1998, 20 (02) : 303 - 353
[3] Gallivan KA, 2003, PROCEEDINGS OF THE 2003 IEEE WORKSHOP ON STATISTICAL SIGNAL PROCESSING, P315
[4] Bayesian and geometric subspace tracking
Srivastava, A
Klassen, E
[J]. ADVANCES IN APPLIED PROBABILITY, 2004, 36 (01) : 43 - 56
[5] Wang TS, 2008, INT CONF ACOUST SPEE, P969

← 1 →