Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training

Sufficient synthetic aperture radar (SAR) data is the key element in achieving excellent target recognition performance for most deep learning algorithms. It is unrealistic to obtain sufficient SAR data from the actual measurements, so SAR simulation based on electromagnetic scattering modeling has...

Full description

Saved in:
Bibliographic Details
Main Authors: Liping Hu, Canming Yao, Jian Huang, Jinfan Liu, Guanyong Wang
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:International Journal of Antennas and Propagation
Online Access:http://dx.doi.org/10.1155/2022/7537732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849308559559360512
author Liping Hu
Canming Yao
Jian Huang
Jinfan Liu
Guanyong Wang
author_facet Liping Hu
Canming Yao
Jian Huang
Jinfan Liu
Guanyong Wang
author_sort Liping Hu
collection DOAJ
description Sufficient synthetic aperture radar (SAR) data is the key element in achieving excellent target recognition performance for most deep learning algorithms. It is unrealistic to obtain sufficient SAR data from the actual measurements, so SAR simulation based on electromagnetic scattering modeling has become an effective way to obtain sufficient samples. Simulated and measured SAR images are nonhomologous data. Due to the fact that the target geometric model of SAR simulation is not inevitably consistent with the real object, the SAR sensor model in SAR simulation may be different from the actual sensor, the background environment of the object is also inevitably different from that of SAR simulation, the error of electromagnetic modeling method itself, and so on. There are inevitable differences between the simulated and measured SAR images, which will affect the recognition performance. To address this problem, an SAR simulation method based on a high-frequency asymptotic technique and a discrete ray tracing technique is proposed in this paper to obtain SAR simulation images of ground vehicle targets. Next, various convolutional neural networks (CNNs) and AugMix data augmentation methods are proposed to train only on simulated data, and then target recognition on MSTAR measured data is performed. The experiments show that all the CNNs can achieve incredible recognition performance on the nonhomologous SAR data, and the RegNetX-3.2GF achieves state-of-the-art performance, up to 84.81%.
format Article
id doaj-art-04251c8490e04334a61ae7bc659b569f
institution Kabale University
issn 1687-5877
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series International Journal of Antennas and Propagation
spelling doaj-art-04251c8490e04334a61ae7bc659b569f2025-08-20T03:54:25ZengWileyInternational Journal of Antennas and Propagation1687-58772022-01-01202210.1155/2022/7537732Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data TrainingLiping Hu0Canming Yao1Jian Huang2Jinfan Liu3Guanyong Wang4Science and Technology on Electromagnetic Scattering LaboratorySchool of Electronics and Communication EngineeringBeijing Institute of Tracking and Telecommunications TechnologyScience and Technology on Electromagnetic Scattering LaboratoryBeijing Institute of Radio MeasurementSufficient synthetic aperture radar (SAR) data is the key element in achieving excellent target recognition performance for most deep learning algorithms. It is unrealistic to obtain sufficient SAR data from the actual measurements, so SAR simulation based on electromagnetic scattering modeling has become an effective way to obtain sufficient samples. Simulated and measured SAR images are nonhomologous data. Due to the fact that the target geometric model of SAR simulation is not inevitably consistent with the real object, the SAR sensor model in SAR simulation may be different from the actual sensor, the background environment of the object is also inevitably different from that of SAR simulation, the error of electromagnetic modeling method itself, and so on. There are inevitable differences between the simulated and measured SAR images, which will affect the recognition performance. To address this problem, an SAR simulation method based on a high-frequency asymptotic technique and a discrete ray tracing technique is proposed in this paper to obtain SAR simulation images of ground vehicle targets. Next, various convolutional neural networks (CNNs) and AugMix data augmentation methods are proposed to train only on simulated data, and then target recognition on MSTAR measured data is performed. The experiments show that all the CNNs can achieve incredible recognition performance on the nonhomologous SAR data, and the RegNetX-3.2GF achieves state-of-the-art performance, up to 84.81%.http://dx.doi.org/10.1155/2022/7537732
spellingShingle Liping Hu
Canming Yao
Jian Huang
Jinfan Liu
Guanyong Wang
Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
International Journal of Antennas and Propagation
title Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
title_full Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
title_fullStr Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
title_full_unstemmed Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
title_short Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
title_sort highly robust synthetic aperture radar target recognition method based on simulation data training
url http://dx.doi.org/10.1155/2022/7537732
work_keys_str_mv AT lipinghu highlyrobustsyntheticapertureradartargetrecognitionmethodbasedonsimulationdatatraining
AT canmingyao highlyrobustsyntheticapertureradartargetrecognitionmethodbasedonsimulationdatatraining
AT jianhuang highlyrobustsyntheticapertureradartargetrecognitionmethodbasedonsimulationdatatraining
AT jinfanliu highlyrobustsyntheticapertureradartargetrecognitionmethodbasedonsimulationdatatraining
AT guanyongwang highlyrobustsyntheticapertureradartargetrecognitionmethodbasedonsimulationdatatraining