Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars
Abstract Deep‐learning‐based radar imaging is developed with distributed frequency modulated continuous waveform multiple‐input multiple‐output (FMCW MIMO) radars in which a deep‐learning approach based on the convolutional neural network (CNN) is proposed to achieve radar images robust to adverse c...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-10-01
|
Series: | IET Radar, Sonar & Navigation |
Online Access: | https://doi.org/10.1049/rsn2.12105 |
id |
doaj-fc4f8a79bee4473baf74c1cdc4cfa924 |
---|---|
record_format |
Article |
spelling |
doaj-fc4f8a79bee4473baf74c1cdc4cfa9242021-09-14T05:24:19ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922021-10-0115101209122010.1049/rsn2.12105Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radarsJiho Seo0Yunji Yang1Yong‐gi Hong2Jaehyun Park3Division of Smart Robot Convergence and Application Engineering Department of Electronic Engineering Pukyong National University Busan South KoreaDivision of Smart Robot Convergence and Application Engineering Department of Electronic Engineering Pukyong National University Busan South KoreaDivision of Smart Robot Convergence and Application Engineering Department of Electronic Engineering Pukyong National University Busan South KoreaDivision of Smart Robot Convergence and Application Engineering Department of Electronic Engineering Pukyong National University Busan South KoreaAbstract Deep‐learning‐based radar imaging is developed with distributed frequency modulated continuous waveform multiple‐input multiple‐output (FMCW MIMO) radars in which a deep‐learning approach based on the convolutional neural network (CNN) is proposed to achieve radar images robust to adverse circumstances. Differently from the existing deep‐learning methods applied to radar object recognition, the deramped radar signal is exploited as the input of the proposed deep CNN (DCNN) without any processing related to the spectrogram transform and the subspace decomposition. To effectively train the proposed DCNN, the received signal is reformulated in terms of the reflection gain values in the (azimuth, range) patches in the image region of interest such that the output vector of the DCNN is composed of the reflection gain values in the associated patches. Furthermore, to overcome the limitations on the amount of training data and training time, the transfer learning approach is effectively applied to the distributed FMCW MIMO radar imaging. The proposed radar imaging is assessed with synthetic simulation data. Specifically, by transferring the pretrained DCNN model for a given reference radar to other distributed radars, the distributed radars can save about 52.4 % in training time compared with a DCNN having the same architecture but without transfer learning.https://doi.org/10.1049/rsn2.12105 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jiho Seo Yunji Yang Yong‐gi Hong Jaehyun Park |
spellingShingle |
Jiho Seo Yunji Yang Yong‐gi Hong Jaehyun Park Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars IET Radar, Sonar & Navigation |
author_facet |
Jiho Seo Yunji Yang Yong‐gi Hong Jaehyun Park |
author_sort |
Jiho Seo |
title |
Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
title_short |
Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
title_full |
Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
title_fullStr |
Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
title_full_unstemmed |
Transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
title_sort |
transfer learning‐based radar imaging with deep convolutional neural networks for distributed frequency modulated continuous waveform multiple‐input multiple‐output radars |
publisher |
Wiley |
series |
IET Radar, Sonar & Navigation |
issn |
1751-8784 1751-8792 |
publishDate |
2021-10-01 |
description |
Abstract Deep‐learning‐based radar imaging is developed with distributed frequency modulated continuous waveform multiple‐input multiple‐output (FMCW MIMO) radars in which a deep‐learning approach based on the convolutional neural network (CNN) is proposed to achieve radar images robust to adverse circumstances. Differently from the existing deep‐learning methods applied to radar object recognition, the deramped radar signal is exploited as the input of the proposed deep CNN (DCNN) without any processing related to the spectrogram transform and the subspace decomposition. To effectively train the proposed DCNN, the received signal is reformulated in terms of the reflection gain values in the (azimuth, range) patches in the image region of interest such that the output vector of the DCNN is composed of the reflection gain values in the associated patches. Furthermore, to overcome the limitations on the amount of training data and training time, the transfer learning approach is effectively applied to the distributed FMCW MIMO radar imaging. The proposed radar imaging is assessed with synthetic simulation data. Specifically, by transferring the pretrained DCNN model for a given reference radar to other distributed radars, the distributed radars can save about 52.4 % in training time compared with a DCNN having the same architecture but without transfer learning. |
url |
https://doi.org/10.1049/rsn2.12105 |
work_keys_str_mv |
AT jihoseo transferlearningbasedradarimagingwithdeepconvolutionalneuralnetworksfordistributedfrequencymodulatedcontinuouswaveformmultipleinputmultipleoutputradars AT yunjiyang transferlearningbasedradarimagingwithdeepconvolutionalneuralnetworksfordistributedfrequencymodulatedcontinuouswaveformmultipleinputmultipleoutputradars AT yonggihong transferlearningbasedradarimagingwithdeepconvolutionalneuralnetworksfordistributedfrequencymodulatedcontinuouswaveformmultipleinputmultipleoutputradars AT jaehyunpark transferlearningbasedradarimagingwithdeepconvolutionalneuralnetworksfordistributedfrequencymodulatedcontinuouswaveformmultipleinputmultipleoutputradars |
_version_ |
1717380102375866368 |