A denoising approach to multisensor signal estimation

Anil M. Rao, Douglas L. Jones

Research output: Contribution to journalArticle

Abstract

Multisensor array processing of noisy measurements has received considerable attention in many areas of signal processing. The optimal processing techniques developed so far usually assume that the signal and noise processes are at least wide sense stationary, yet a need exists for efficient, effective methods for processing nonstationary signals. Although wavelets have proven to be useful tools in dealing with certain nonstationary signals, the way in which wavelets are to be used in the multisensor setting is still an open question. Based on the structure for optimal linear estimation of nonstationary multisensor data and statistical models of spatial signal coherence, we propose a multisensor denoising algorithm that fully exploits, in a statistically optimal fashion, the additional information afforded by multisensor measurements. Under certain conditions, we show that the proposed estimator can be realized efficiently and robustly in a completely blind fashion, employing only wavelet and discrete Fourier transforms while entailing only a small loss in performance.

Original languageEnglish (US)
Pages (from-to)1225-1234
Number of pages10
JournalIEEE Transactions on Signal Processing
Volume48
Issue number5
DOIs
StatePublished - May 1 2000

Fingerprint

Signal processing
Array processing
Discrete Fourier transforms
Data structures
Processing
Statistical Models

Keywords

  • Array processing
  • Denoising
  • Multisensor
  • Spatial coherence

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A denoising approach to multisensor signal estimation. / Rao, Anil M.; Jones, Douglas L.

In: IEEE Transactions on Signal Processing, Vol. 48, No. 5, 01.05.2000, p. 1225-1234.

Research output: Contribution to journalArticle

@article{2bb8815e3578401db117b8d5b3ee649d,
title = "A denoising approach to multisensor signal estimation",
abstract = "Multisensor array processing of noisy measurements has received considerable attention in many areas of signal processing. The optimal processing techniques developed so far usually assume that the signal and noise processes are at least wide sense stationary, yet a need exists for efficient, effective methods for processing nonstationary signals. Although wavelets have proven to be useful tools in dealing with certain nonstationary signals, the way in which wavelets are to be used in the multisensor setting is still an open question. Based on the structure for optimal linear estimation of nonstationary multisensor data and statistical models of spatial signal coherence, we propose a multisensor denoising algorithm that fully exploits, in a statistically optimal fashion, the additional information afforded by multisensor measurements. Under certain conditions, we show that the proposed estimator can be realized efficiently and robustly in a completely blind fashion, employing only wavelet and discrete Fourier transforms while entailing only a small loss in performance.",
keywords = "Array processing, Denoising, Multisensor, Spatial coherence",
author = "Rao, {Anil M.} and Jones, {Douglas L.}",
year = "2000",
month = "5",
day = "1",
doi = "10.1109/78.839971",
language = "English (US)",
volume = "48",
pages = "1225--1234",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - A denoising approach to multisensor signal estimation

AU - Rao, Anil M.

AU - Jones, Douglas L.

PY - 2000/5/1

Y1 - 2000/5/1

N2 - Multisensor array processing of noisy measurements has received considerable attention in many areas of signal processing. The optimal processing techniques developed so far usually assume that the signal and noise processes are at least wide sense stationary, yet a need exists for efficient, effective methods for processing nonstationary signals. Although wavelets have proven to be useful tools in dealing with certain nonstationary signals, the way in which wavelets are to be used in the multisensor setting is still an open question. Based on the structure for optimal linear estimation of nonstationary multisensor data and statistical models of spatial signal coherence, we propose a multisensor denoising algorithm that fully exploits, in a statistically optimal fashion, the additional information afforded by multisensor measurements. Under certain conditions, we show that the proposed estimator can be realized efficiently and robustly in a completely blind fashion, employing only wavelet and discrete Fourier transforms while entailing only a small loss in performance.

AB - Multisensor array processing of noisy measurements has received considerable attention in many areas of signal processing. The optimal processing techniques developed so far usually assume that the signal and noise processes are at least wide sense stationary, yet a need exists for efficient, effective methods for processing nonstationary signals. Although wavelets have proven to be useful tools in dealing with certain nonstationary signals, the way in which wavelets are to be used in the multisensor setting is still an open question. Based on the structure for optimal linear estimation of nonstationary multisensor data and statistical models of spatial signal coherence, we propose a multisensor denoising algorithm that fully exploits, in a statistically optimal fashion, the additional information afforded by multisensor measurements. Under certain conditions, we show that the proposed estimator can be realized efficiently and robustly in a completely blind fashion, employing only wavelet and discrete Fourier transforms while entailing only a small loss in performance.

KW - Array processing

KW - Denoising

KW - Multisensor

KW - Spatial coherence

UR - http://www.scopus.com/inward/record.url?scp=0038019702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038019702&partnerID=8YFLogxK

U2 - 10.1109/78.839971

DO - 10.1109/78.839971

M3 - Article

AN - SCOPUS:0038019702

VL - 48

SP - 1225

EP - 1234

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 5

ER -