Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network
Conventional direction-of-arrival (DOA) estimation methods are primarily used in point source scenarios and based on array signal processing. However, due to the local scattering caused by sea surface, signals observed from radar antenna cannot be regarded as a point source but rather as a spatially...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/14/2681 |
id |
doaj-2b3a2e482afc47bb89cecb5e8d43e890 |
---|---|
record_format |
Article |
spelling |
doaj-2b3a2e482afc47bb89cecb5e8d43e8902021-07-23T14:04:09ZengMDPI AGRemote Sensing2072-42922021-07-01132681268110.3390/rs13142681Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural NetworkXiuyi Zhao0Ying Yang1Kun-Shan Chen2State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaConventional direction-of-arrival (DOA) estimation methods are primarily used in point source scenarios and based on array signal processing. However, due to the local scattering caused by sea surface, signals observed from radar antenna cannot be regarded as a point source but rather as a spatially dispersed source. Besides, with the advantages of flexibility and comparably low cost, synthetic aperture radar (SAR) is the present and future trend of space-based systems. This paper proposes a novel DOA estimation approach for SAR systems using the simulated radar measurement of the sea surface at different operating frequencies and wind speeds. This article’s forward model is an advanced integral equation model (AIEM) to calculate the electromagnetic scattered from the sea surface. To solve the DOA estimation problem, we introduce a convolutional neural network (CNN) framework to estimate the transmitter’s incident angle and incident azimuth angle. Results demonstrate that the CNN can achieve a good performance in DOA estimation at a wide range of frequencies and sea wind speeds.https://www.mdpi.com/2072-4292/13/14/2681direction-of-arrival (DOA) estimationconvolutional neural network (CNN)sea surface scatteringradar remote sensing |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiuyi Zhao Ying Yang Kun-Shan Chen |
spellingShingle |
Xiuyi Zhao Ying Yang Kun-Shan Chen Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network Remote Sensing direction-of-arrival (DOA) estimation convolutional neural network (CNN) sea surface scattering radar remote sensing |
author_facet |
Xiuyi Zhao Ying Yang Kun-Shan Chen |
author_sort |
Xiuyi Zhao |
title |
Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network |
title_short |
Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network |
title_full |
Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network |
title_fullStr |
Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network |
title_full_unstemmed |
Direction-of-Arrival Estimation over Sea Surface from Radar Scattering Based on Convolutional Neural Network |
title_sort |
direction-of-arrival estimation over sea surface from radar scattering based on convolutional neural network |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-07-01 |
description |
Conventional direction-of-arrival (DOA) estimation methods are primarily used in point source scenarios and based on array signal processing. However, due to the local scattering caused by sea surface, signals observed from radar antenna cannot be regarded as a point source but rather as a spatially dispersed source. Besides, with the advantages of flexibility and comparably low cost, synthetic aperture radar (SAR) is the present and future trend of space-based systems. This paper proposes a novel DOA estimation approach for SAR systems using the simulated radar measurement of the sea surface at different operating frequencies and wind speeds. This article’s forward model is an advanced integral equation model (AIEM) to calculate the electromagnetic scattered from the sea surface. To solve the DOA estimation problem, we introduce a convolutional neural network (CNN) framework to estimate the transmitter’s incident angle and incident azimuth angle. Results demonstrate that the CNN can achieve a good performance in DOA estimation at a wide range of frequencies and sea wind speeds. |
topic |
direction-of-arrival (DOA) estimation convolutional neural network (CNN) sea surface scattering radar remote sensing |
url |
https://www.mdpi.com/2072-4292/13/14/2681 |
work_keys_str_mv |
AT xiuyizhao directionofarrivalestimationoverseasurfacefromradarscatteringbasedonconvolutionalneuralnetwork AT yingyang directionofarrivalestimationoverseasurfacefromradarscatteringbasedonconvolutionalneuralnetwork AT kunshanchen directionofarrivalestimationoverseasurfacefromradarscatteringbasedonconvolutionalneuralnetwork |
_version_ |
1721286072650956800 |