A reduced-order-model Bayesian obstacle detection algorithm

Mahadevan Ganesh; Stuart C. Hawkins

doi:10.1007/978-3-030-38230-8_2

A reduced-order-model Bayesian obstacle detection algorithm

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We develop an efficient Bayesian algorithm for solving the inverse problem of classifying and locating certain two dimensional objects using noisy far field data obtained by illuminating them with a radiating wave. While application of Bayesian algorithms for wave-propagation inverse problems is itself innovative, the principal novelty in this work is in using (i) a surrogate Bayesian posterior distribution computed using a generalised polynomial chaos approximation; and (ii) an efficient wave-propagation-specific reduced order model in place of the full multiple scattering forward model. We demonstrate the capability of this approach with simulations in which we accurately detect two dimensional objects, with shapes motivated by safety and security applications.

Original language	English
Title of host publication	2018 Matrix annals
Editors	David R. Wood, Jan de Gier, Cheryl E. Praeger, Terence Tao
Place of Publication	Cham
Publisher	Springer, Springer Nature
Pages	17-27
Number of pages	11
ISBN (Electronic)	9783030382308
ISBN (Print)	9783030382292
DOIs	https://doi.org/10.1007/978-3-030-38230-8_2
Publication status	Published - 2020
Event	2018 Matrix Annals - , Australia Duration: 8 Jan 2018 → 21 Dec 2018

Publication series

Name	MATRIX Book Series
Publisher	Springer
Volume	3
ISSN (Print)	2523-3041
ISSN (Electronic)	2523-305X

Conference

Conference	2018 Matrix Annals
Country/Territory	Australia
Period	8/01/18 → 21/12/18

Access to Document

10.1007/978-3-030-38230-8_2

https://www.matrix-inst.org.au/wp_Matrix2016/wp-content/uploads/2019/05/Ganesh.pdf

Cite this

@inproceedings{ae2976646fa443a988f5bb4bc46acfcd,

title = "A reduced-order-model Bayesian obstacle detection algorithm",

abstract = "We develop an efficient Bayesian algorithm for solving the inverse problem of classifying and locating certain two dimensional objects using noisy far field data obtained by illuminating them with a radiating wave. While application of Bayesian algorithms for wave-propagation inverse problems is itself innovative, the principal novelty in this work is in using (i) a surrogate Bayesian posterior distribution computed using a generalised polynomial chaos approximation; and (ii) an efficient wave-propagation-specific reduced order model in place of the full multiple scattering forward model. We demonstrate the capability of this approach with simulations in which we accurately detect two dimensional objects, with shapes motivated by safety and security applications.",

author = "Mahadevan Ganesh and Hawkins, {Stuart C.}",

year = "2020",

doi = "10.1007/978-3-030-38230-8_2",

language = "English",

isbn = "9783030382292",

series = "MATRIX Book Series",

publisher = "Springer, Springer Nature",

pages = "17--27",

editor = "Wood, {David R.} and {de Gier}, Jan and Praeger, {Cheryl E.} and { Tao}, Terence",

booktitle = "2018 Matrix annals",

address = "United States",

note = "2018 Matrix Annals ; Conference date: 08-01-2018 Through 21-12-2018",

}

A reduced-order-model Bayesian obstacle detection algorithm. / Ganesh, Mahadevan ; Hawkins, Stuart C.
2018 Matrix annals. ed. / David R. Wood; Jan de Gier; Cheryl E. Praeger; Terence Tao. Cham: Springer, Springer Nature, 2020. p. 17-27 (MATRIX Book Series; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A reduced-order-model Bayesian obstacle detection algorithm

AU - Ganesh, Mahadevan

AU - Hawkins, Stuart C.

PY - 2020

Y1 - 2020

N2 - We develop an efficient Bayesian algorithm for solving the inverse problem of classifying and locating certain two dimensional objects using noisy far field data obtained by illuminating them with a radiating wave. While application of Bayesian algorithms for wave-propagation inverse problems is itself innovative, the principal novelty in this work is in using (i) a surrogate Bayesian posterior distribution computed using a generalised polynomial chaos approximation; and (ii) an efficient wave-propagation-specific reduced order model in place of the full multiple scattering forward model. We demonstrate the capability of this approach with simulations in which we accurately detect two dimensional objects, with shapes motivated by safety and security applications.

AB - We develop an efficient Bayesian algorithm for solving the inverse problem of classifying and locating certain two dimensional objects using noisy far field data obtained by illuminating them with a radiating wave. While application of Bayesian algorithms for wave-propagation inverse problems is itself innovative, the principal novelty in this work is in using (i) a surrogate Bayesian posterior distribution computed using a generalised polynomial chaos approximation; and (ii) an efficient wave-propagation-specific reduced order model in place of the full multiple scattering forward model. We demonstrate the capability of this approach with simulations in which we accurately detect two dimensional objects, with shapes motivated by safety and security applications.

U2 - 10.1007/978-3-030-38230-8_2

DO - 10.1007/978-3-030-38230-8_2

M3 - Conference proceeding contribution

SN - 9783030382292

T3 - MATRIX Book Series

SP - 17

EP - 27

BT - 2018 Matrix annals

A2 - Wood, David R.

A2 - de Gier, Jan

A2 - Praeger, Cheryl E.

A2 - Tao, Terence

PB - Springer, Springer Nature

CY - Cham

T2 - 2018 Matrix Annals

Y2 - 8 January 2018 through 21 December 2018

ER -

A reduced-order-model Bayesian obstacle detection algorithm

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this