Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks

Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The broad adoption of radar sensors increases the chance of interference among sensors from different vehicles, generating corrupted range profiles and range-...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nicolae-Catalin Ristea, Andrei Anghel, Radu Tudor Ionescu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Autonomous driving automotive radar interference mitigation deep learning phase estimation fully convolutional networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/ed52fac519074e77a4cb8fc081f2c27c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ed52fac519074e77a4cb8fc081f2c27c
record_format	dspace
spelling	oai:doaj.org-article:ed52fac519074e77a4cb8fc081f2c27c2021-11-24T00:03:12ZEstimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks2169-353610.1109/ACCESS.2021.3128151https://doaj.org/article/ed52fac519074e77a4cb8fc081f2c27c2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9615067/https://doaj.org/toc/2169-3536Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The broad adoption of radar sensors increases the chance of interference among sensors from different vehicles, generating corrupted range profiles and range-Doppler maps. In order to extract distance and velocity of multiple targets from range-Doppler maps, the interference affecting each range profile needs to be mitigated. In this paper, we propose a fully convolutional neural network for automotive radar interference mitigation. In order to train our network in a real-world scenario, we introduce a new data set of realistic automotive radar signals with multiple targets and multiple interferers. To our knowledge, we are the first to apply weight pruning in the automotive radar domain, obtaining superior results compared to the widely-used dropout. While most previous works successfully estimated the magnitude of automotive radar signals, we propose a deep learning model that can accurately estimate the phase. For instance, our novel approach reduces the phase estimation error with respect to the commonly-adopted zeroing technique by half, from 12.55 degrees to 6.58 degrees. Considering the lack of databases for automotive radar interference mitigation, we release as open source our large-scale data set that closely replicates the real-world automotive scenario for multiple interference cases, allowing others to objectively compare their future work in this domain. Our data set is available for download at: <uri>http://github.com/ristea/arim-v2</uri>.Nicolae-Catalin RisteaAndrei AnghelRadu Tudor IonescuIEEEarticleAutonomous drivingautomotive radarinterference mitigationdeep learningphase estimationfully convolutional networksElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153491-153507 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Autonomous driving automotive radar interference mitigation deep learning phase estimation fully convolutional networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Autonomous driving automotive radar interference mitigation deep learning phase estimation fully convolutional networks Electrical engineering. Electronics. Nuclear engineering TK1-9971 Nicolae-Catalin Ristea Andrei Anghel Radu Tudor Ionescu Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
description	Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The broad adoption of radar sensors increases the chance of interference among sensors from different vehicles, generating corrupted range profiles and range-Doppler maps. In order to extract distance and velocity of multiple targets from range-Doppler maps, the interference affecting each range profile needs to be mitigated. In this paper, we propose a fully convolutional neural network for automotive radar interference mitigation. In order to train our network in a real-world scenario, we introduce a new data set of realistic automotive radar signals with multiple targets and multiple interferers. To our knowledge, we are the first to apply weight pruning in the automotive radar domain, obtaining superior results compared to the widely-used dropout. While most previous works successfully estimated the magnitude of automotive radar signals, we propose a deep learning model that can accurately estimate the phase. For instance, our novel approach reduces the phase estimation error with respect to the commonly-adopted zeroing technique by half, from 12.55 degrees to 6.58 degrees. Considering the lack of databases for automotive radar interference mitigation, we release as open source our large-scale data set that closely replicates the real-world automotive scenario for multiple interference cases, allowing others to objectively compare their future work in this domain. Our data set is available for download at: <uri>http://github.com/ristea/arim-v2</uri>.
format	article
author	Nicolae-Catalin Ristea Andrei Anghel Radu Tudor Ionescu
author_facet	Nicolae-Catalin Ristea Andrei Anghel Radu Tudor Ionescu
author_sort	Nicolae-Catalin Ristea
title	Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
title_short	Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
title_full	Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
title_fullStr	Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
title_full_unstemmed	Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks
title_sort	estimating the magnitude and phase of automotive radar signals under multiple interference sources with fully convolutional networks
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/ed52fac519074e77a4cb8fc081f2c27c
work_keys_str_mv	AT nicolaecatalinristea estimatingthemagnitudeandphaseofautomotiveradarsignalsundermultipleinterferencesourceswithfullyconvolutionalnetworks AT andreianghel estimatingthemagnitudeandphaseofautomotiveradarsignalsundermultipleinterferencesourceswithfullyconvolutionalnetworks AT radutudorionescu estimatingthemagnitudeandphaseofautomotiveradarsignalsundermultipleinterferencesourceswithfullyconvolutionalnetworks
_version_	1718416127887933440

Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks

Ejemplares similares