Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays

Georgios K. Papageorgiou; Mathini Sellathurai

doi:10.1109/ICASSP40776.2020.9054380

Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays

Georgios K. Papageorgiou, Mathini Sellathurai

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

19 Citations (Scopus)

Abstract

In this work, we focus on improving the Direction-of-Arrival (DoA) estimation of multiple targets/sources from a small number of snapshots. Estimation via the sample covariance matrix is known to perform poorly, since the true manifold structure is not revealed for a small number of samples. First, we explicitly model the sample covariance matrix that is used for the DoA estimation as a noisy version of the true one. Next, we employ a stacked denoising autoencoder (DAE) that predicts a statistically richer version of the sampled matrix that is subsequently used for the DoA estimation. Moreover, we consider a limited number of sensors (comparable to the number of sources) in a non-uniform linear configuration and introduce an end-to-end hybrid DoA prediction-estimation scheme. Results demonstrate significant improvement compared to the conventional approach.

Original language	English
Title of host publication	ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	IEEE
Pages	4632-4636
Number of pages	5
ISBN (Electronic)	978-1-5090-6631-5
DOIs	https://doi.org/10.1109/ICASSP40776.2020.9054380
Publication status	Published - 14 May 2020
Event	45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020 - Barcelona, Spain Duration: 4 May 2020 → 8 May 2020 https://2020.ieeeicassp.org/

Publication series

Name	IEEE International Conference on Acoustics, Speech and Signal Processing
ISSN (Electronic)	2379-190X

Conference

Conference	45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020
Abbreviated title	ICASSP 2020
Country/Territory	Spain
City	Barcelona
Period	4/05/20 → 8/05/20
Internet address	https://2020.ieeeicassp.org/

Keywords

Direction-of-arrival DoA estimation
deep learning
denoising autoencoder DAE
maximum interelement spacing constraint MISC arrays
sparse arrays

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP40776.2020.9054380

Cite this

Papageorgiou, G. K., & Sellathurai, M. (2020). Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4632-4636). (IEEE International Conference on Acoustics, Speech and Signal Processing). IEEE. https://doi.org/10.1109/ICASSP40776.2020.9054380

@inproceedings{e1419ab16c8a4c9ea990128305304846,

title = "Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays",

abstract = "In this work, we focus on improving the Direction-of-Arrival (DoA) estimation of multiple targets/sources from a small number of snapshots. Estimation via the sample covariance matrix is known to perform poorly, since the true manifold structure is not revealed for a small number of samples. First, we explicitly model the sample covariance matrix that is used for the DoA estimation as a noisy version of the true one. Next, we employ a stacked denoising autoencoder (DAE) that predicts a statistically richer version of the sampled matrix that is subsequently used for the DoA estimation. Moreover, we consider a limited number of sensors (comparable to the number of sources) in a non-uniform linear configuration and introduce an end-to-end hybrid DoA prediction-estimation scheme. Results demonstrate significant improvement compared to the conventional approach.",

keywords = "Direction-of-arrival DoA estimation, deep learning, denoising autoencoder DAE, maximum interelement spacing constraint MISC arrays, sparse arrays",

author = "Papageorgiou, {Georgios K.} and Mathini Sellathurai",

year = "2020",

month = may,

day = "14",

doi = "10.1109/ICASSP40776.2020.9054380",

language = "English",

series = "IEEE International Conference on Acoustics, Speech and Signal Processing",

publisher = "IEEE",

pages = "4632--4636",

booktitle = "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",

url = "https://2020.ieeeicassp.org/",

}

Papageorgiou, GK & Sellathurai, M 2020, Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, pp. 4632-4636, 45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054380

Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays. / Papageorgiou, Georgios K.; Sellathurai, Mathini.
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020. p. 4632-4636 (IEEE International Conference on Acoustics, Speech and Signal Processing).

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

TY - GEN

T1 - Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays

AU - Papageorgiou, Georgios K.

AU - Sellathurai, Mathini

PY - 2020/5/14

Y1 - 2020/5/14

N2 - In this work, we focus on improving the Direction-of-Arrival (DoA) estimation of multiple targets/sources from a small number of snapshots. Estimation via the sample covariance matrix is known to perform poorly, since the true manifold structure is not revealed for a small number of samples. First, we explicitly model the sample covariance matrix that is used for the DoA estimation as a noisy version of the true one. Next, we employ a stacked denoising autoencoder (DAE) that predicts a statistically richer version of the sampled matrix that is subsequently used for the DoA estimation. Moreover, we consider a limited number of sensors (comparable to the number of sources) in a non-uniform linear configuration and introduce an end-to-end hybrid DoA prediction-estimation scheme. Results demonstrate significant improvement compared to the conventional approach.

AB - In this work, we focus on improving the Direction-of-Arrival (DoA) estimation of multiple targets/sources from a small number of snapshots. Estimation via the sample covariance matrix is known to perform poorly, since the true manifold structure is not revealed for a small number of samples. First, we explicitly model the sample covariance matrix that is used for the DoA estimation as a noisy version of the true one. Next, we employ a stacked denoising autoencoder (DAE) that predicts a statistically richer version of the sampled matrix that is subsequently used for the DoA estimation. Moreover, we consider a limited number of sensors (comparable to the number of sources) in a non-uniform linear configuration and introduce an end-to-end hybrid DoA prediction-estimation scheme. Results demonstrate significant improvement compared to the conventional approach.

KW - Direction-of-arrival DoA estimation

KW - deep learning

KW - denoising autoencoder DAE

KW - maximum interelement spacing constraint MISC arrays

KW - sparse arrays

UR - http://www.scopus.com/inward/record.url?scp=85089226753&partnerID=8YFLogxK

U2 - 10.1109/ICASSP40776.2020.9054380

DO - 10.1109/ICASSP40776.2020.9054380

M3 - Conference contribution

T3 - IEEE International Conference on Acoustics, Speech and Signal Processing

SP - 4632

EP - 4636

BT - ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

T2 - 45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020

Y2 - 4 May 2020 through 8 May 2020

ER -

Papageorgiou GK , Sellathurai M. Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2020. p. 4632-4636. (IEEE International Conference on Acoustics, Speech and Signal Processing). doi: 10.1109/ICASSP40776.2020.9054380

Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this