ResNet Applied for a Single-Snapshot DOA Estimation

M.L. Lima de Oliveira; Marco J.G. Bekooij

doi:10.1109/RadarConf2248738.2022.9763905

ResNet Applied for a Single-Snapshot DOA Estimation

M.L. Lima de Oliveira, Marco J.G. Bekooij

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

15 Citations (Scopus)

260 Downloads (Pure)

Abstract

In this paper, we discuss the usage of Residual Neural Networks (ResNets) for calculating the Direction Of Arrival (DOA) of MIMO radars and the estimation of the number of targets, using Minimum Redundancy Array (MRA). In addition, we are considering only the case of one snapshot at a time. This means that most techniques would deliver a poor estimation performance, whereas the Maximum Likelihood Estimation (MLE) algorithm delivers decent performance at a high computational cost. ResNet appears to be a viable alternative solution for this problem, being able to outperform MLE in some cases while having a less computational cost for scenarios with at least two different targets.

Original language	English
Title of host publication	2022 IEEE Radar Conference (RadarConf22)
ISBN (Electronic)	978-1-7281-5368-1
DOIs	https://doi.org/10.1109/RadarConf2248738.2022.9763905
Publication status	Published - 3 May 2022
Event	IEEE Radar Conference, RadarConf 2022 - New York, United States Duration: 21 Mar 2022 → 25 Mar 2022

Conference

Conference	IEEE Radar Conference, RadarConf 2022
Abbreviated title	RadarConf 2022
Country/Territory	United States
City	New York
Period	21/03/22 → 25/03/22

Keywords

22/2 OA procedure

Access to Document

10.1109/RadarConf2248738.2022.9763905

10.1109_radarconf2248738.2022.9763905Final published version, 966 KBLicence: Taverne

Cite this

@inproceedings{60e2b1bd8e6944f6a2a0a65533e93fd5,

title = "ResNet Applied for a Single-Snapshot DOA Estimation",

abstract = "In this paper, we discuss the usage of Residual Neural Networks (ResNets) for calculating the Direction Of Arrival (DOA) of MIMO radars and the estimation of the number of targets, using Minimum Redundancy Array (MRA). In addition, we are considering only the case of one snapshot at a time. This means that most techniques would deliver a poor estimation performance, whereas the Maximum Likelihood Estimation (MLE) algorithm delivers decent performance at a high computational cost. ResNet appears to be a viable alternative solution for this problem, being able to outperform MLE in some cases while having a less computational cost for scenarios with at least two different targets.",

keywords = "22/2 OA procedure",

author = "{Lima de Oliveira}, M.L. and Bekooij, {Marco J.G.}",

year = "2022",

month = may,

day = "3",

doi = "10.1109/RadarConf2248738.2022.9763905",

language = "English",

isbn = "978-1-7281-5369-8",

booktitle = "2022 IEEE Radar Conference (RadarConf22)",

note = "IEEE Radar Conference, RadarConf 2022, RadarConf 2022 ; Conference date: 21-03-2022 Through 25-03-2022",

}

TY - GEN

T1 - ResNet Applied for a Single-Snapshot DOA Estimation

AU - Lima de Oliveira, M.L.

AU - Bekooij, Marco J.G.

PY - 2022/5/3

Y1 - 2022/5/3

N2 - In this paper, we discuss the usage of Residual Neural Networks (ResNets) for calculating the Direction Of Arrival (DOA) of MIMO radars and the estimation of the number of targets, using Minimum Redundancy Array (MRA). In addition, we are considering only the case of one snapshot at a time. This means that most techniques would deliver a poor estimation performance, whereas the Maximum Likelihood Estimation (MLE) algorithm delivers decent performance at a high computational cost. ResNet appears to be a viable alternative solution for this problem, being able to outperform MLE in some cases while having a less computational cost for scenarios with at least two different targets.

AB - In this paper, we discuss the usage of Residual Neural Networks (ResNets) for calculating the Direction Of Arrival (DOA) of MIMO radars and the estimation of the number of targets, using Minimum Redundancy Array (MRA). In addition, we are considering only the case of one snapshot at a time. This means that most techniques would deliver a poor estimation performance, whereas the Maximum Likelihood Estimation (MLE) algorithm delivers decent performance at a high computational cost. ResNet appears to be a viable alternative solution for this problem, being able to outperform MLE in some cases while having a less computational cost for scenarios with at least two different targets.

KW - 22/2 OA procedure

U2 - 10.1109/RadarConf2248738.2022.9763905

DO - 10.1109/RadarConf2248738.2022.9763905

M3 - Conference contribution

SN - 978-1-7281-5369-8

BT - 2022 IEEE Radar Conference (RadarConf22)

T2 - IEEE Radar Conference, RadarConf 2022

Y2 - 21 March 2022 through 25 March 2022

ER -

ResNet Applied for a Single-Snapshot DOA Estimation

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this