Velocity Estimation of SAR Moving Ship via CV-EstNet

Yun Zhang; Qinglong Hua; Yicheng Jiang; Hongbo Li; Dan Xu

doi:10.1109/Radar53847.2021.10028471

Velocity Estimation of SAR Moving Ship via CV-EstNet

School of Electronics and Information Engineering, Harbin Institute of Technology

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

Abstract

Compared with the synthetic aperture radar (SAR) static target image, the moving target will produce additional Doppler center and Doppler modulation frequency change, which will cause the imaging result of the moving target to defocus and shift. Therefore, this paper proposes a complex-valued convolutional neural network (CV -CNN) architecture CV-EstNet. It adopts an end-to-end approach to complete the velocity estimation of SAR moving ship targets, and estimate the range velocity and azimuth velocity. Then, the proposed CV-EstN et is tested on the simulated target velocity estimation task of five-types SAR moving ships. The simulation shows that CV-EstN et can further reduce the velocity estimation error compared with the traditional real-valued CNN (RV-CNN) with the same degree of freedom.

Original language	English
Title of host publication	2021 CIE International Conference on Radar, Radar 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2128-2131
Number of pages	4
ISBN (Electronic)	9781665498142
DOIs	https://doi.org/10.1109/Radar53847.2021.10028471
State	Published - 2021
Externally published	Yes
Event	2021 CIE International Conference on Radar, Radar 2021 - Haikou, Hainan, China Duration: 15 Dec 2021 → 19 Dec 2021

Publication series

Name	Proceedings of the IEEE Radar Conference
Volume	2021-December
ISSN (Print)	1097-5764
ISSN (Electronic)	2375-5318

Conference

Conference	2021 CIE International Conference on Radar, Radar 2021
Country/Territory	China
City	Haikou, Hainan
Period	15/12/21 → 19/12/21

Keywords

CV-EstNet
Complex-valued convolutional neural network (CV-CNN)
deep learning
synthetic aperture radar (SAR)
velocity estimation

Access to Document

10.1109/Radar53847.2021.10028471

Cite this

@inproceedings{3d7e67b4257448f19a333ade4288efb1,

title = "Velocity Estimation of SAR Moving Ship via CV-EstNet",

abstract = "Compared with the synthetic aperture radar (SAR) static target image, the moving target will produce additional Doppler center and Doppler modulation frequency change, which will cause the imaging result of the moving target to defocus and shift. Therefore, this paper proposes a complex-valued convolutional neural network (CV -CNN) architecture CV-EstNet. It adopts an end-to-end approach to complete the velocity estimation of SAR moving ship targets, and estimate the range velocity and azimuth velocity. Then, the proposed CV-EstN et is tested on the simulated target velocity estimation task of five-types SAR moving ships. The simulation shows that CV-EstN et can further reduce the velocity estimation error compared with the traditional real-valued CNN (RV-CNN) with the same degree of freedom.",

keywords = "CV-EstNet, Complex-valued convolutional neural network (CV-CNN), deep learning, synthetic aperture radar (SAR), velocity estimation",

author = "Yun Zhang and Qinglong Hua and Yicheng Jiang and Hongbo Li and Dan Xu",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 CIE International Conference on Radar, Radar 2021 ; Conference date: 15-12-2021 Through 19-12-2021",

year = "2021",

doi = "10.1109/Radar53847.2021.10028471",

language = "英语",

series = "Proceedings of the IEEE Radar Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2128--2131",

booktitle = "2021 CIE International Conference on Radar, Radar 2021",

address = "美国",

}

Zhang, Y , Hua, Q , Jiang, Y , Li, H & Xu, D 2021, Velocity Estimation of SAR Moving Ship via CV-EstNet. in 2021 CIE International Conference on Radar, Radar 2021. Proceedings of the IEEE Radar Conference, vol. 2021-December, Institute of Electrical and Electronics Engineers Inc., pp. 2128-2131, 2021 CIE International Conference on Radar, Radar 2021, Haikou, Hainan, China, 15/12/21. https://doi.org/10.1109/Radar53847.2021.10028471

Velocity Estimation of SAR Moving Ship via CV-EstNet. / Zhang, Yun ; Hua, Qinglong ; Jiang, Yicheng et al.
2021 CIE International Conference on Radar, Radar 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2128-2131 (Proceedings of the IEEE Radar Conference; Vol. 2021-December).

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

TY - GEN

T1 - Velocity Estimation of SAR Moving Ship via CV-EstNet

AU - Zhang, Yun

AU - Hua, Qinglong

AU - Jiang, Yicheng

AU - Li, Hongbo

AU - Xu, Dan

PY - 2021

Y1 - 2021

N2 - Compared with the synthetic aperture radar (SAR) static target image, the moving target will produce additional Doppler center and Doppler modulation frequency change, which will cause the imaging result of the moving target to defocus and shift. Therefore, this paper proposes a complex-valued convolutional neural network (CV -CNN) architecture CV-EstNet. It adopts an end-to-end approach to complete the velocity estimation of SAR moving ship targets, and estimate the range velocity and azimuth velocity. Then, the proposed CV-EstN et is tested on the simulated target velocity estimation task of five-types SAR moving ships. The simulation shows that CV-EstN et can further reduce the velocity estimation error compared with the traditional real-valued CNN (RV-CNN) with the same degree of freedom.

AB - Compared with the synthetic aperture radar (SAR) static target image, the moving target will produce additional Doppler center and Doppler modulation frequency change, which will cause the imaging result of the moving target to defocus and shift. Therefore, this paper proposes a complex-valued convolutional neural network (CV -CNN) architecture CV-EstNet. It adopts an end-to-end approach to complete the velocity estimation of SAR moving ship targets, and estimate the range velocity and azimuth velocity. Then, the proposed CV-EstN et is tested on the simulated target velocity estimation task of five-types SAR moving ships. The simulation shows that CV-EstN et can further reduce the velocity estimation error compared with the traditional real-valued CNN (RV-CNN) with the same degree of freedom.

KW - CV-EstNet

KW - Complex-valued convolutional neural network (CV-CNN)

KW - deep learning

KW - synthetic aperture radar (SAR)

KW - velocity estimation

UR - https://www.scopus.com/pages/publications/85181125630

U2 - 10.1109/Radar53847.2021.10028471

DO - 10.1109/Radar53847.2021.10028471

M3 - 会议稿件

AN - SCOPUS:85181125630

T3 - Proceedings of the IEEE Radar Conference

SP - 2128

EP - 2131

BT - 2021 CIE International Conference on Radar, Radar 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 CIE International Conference on Radar, Radar 2021

Y2 - 15 December 2021 through 19 December 2021

ER -

Velocity Estimation of SAR Moving Ship via CV-EstNet

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this