结合迁移学习基于全卷积神经网络的ISAR自聚焦算法

doi:10.7527/S1000-6893.2023.28172

Abstract

Abstract:

The targets of Inverse Synthetic Aperture Radar （ISAR） imaging are mostly non-cooperative， and motion compensation is the key of ISAR imaging when the relative motion status of target is unknown. Fully Convolutional Network （FCN） has excellent feature extraction and fitting abilities， and an ISAR phase compensation algorithm based on FCN and Transfer Learning is proposed by utilizing the FCN in ISAR autofocusing in this paper. Firstly， a large number of simulation data sets with different phase errors are constructed and trained to provide phase compensation ability for FCN. In addition， the transfer training of simulation and measured data with different attitudes is carried out to improve the translational phase compensation ability. The measured data processing results show that the performance of FCN phase compensation algorithm is better than traditional algorithm， which verifies the effectiveness in the proposed method and the superiority compared with the traditional method.

Key words: inverse synthetic aperture radar, imaging, phase compensation, fully convolutional neural network, transfer learning

CLC Number:

V243.2

Lianzi WANG, Ling WANG, Daiyin ZHU. An ISAR autofocus imaging algorithm based on FCN and transfer learing[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(17): 328172.

Figures/Tables 12

Fig.1

Fig. 2

Fig.3

Fig.4

Table 1

Radar parameters

参数	符号	数值
载频	$f 0$	10 GHz
带宽	B	300 MHz
脉冲宽度	$T p$	$1 μ s$
脉冲重复频率	PRF	100 Hz
积累脉冲	$N a$	300

Table 1

Table 2

Fig.5

Fig.6

Table 3

Table 4

Table 5

Table 6

References 31

1	YU X， ZHU D Y， ZHANG J D， et al. Motion compensation algorithm based on the designing structured gram matrices method［J］. IET Radar， Sonar & Navigation， 2014， 8（3）： 209-219.
2	ZHU D Y， WANG L， YU Y S， et al. Robust ISAR range alignment via minimizing the entropy of the average range profile［J］. IEEE Geoscience and Remote Sensing Letters， 2009， 6（2）： 204-208.
3	汪玲. 逆合成孔径雷达成像关键技术研究［D］. 南京：南京航空航天大学， 2006： 18-49.
	WANG L. Research on key techniques of inverse synthetic aperture radar imaging［D］. Nanjing： Nanjing University of Aeronautics and Astronautics， 2006： 18-49 （in Chinese）.
4	WU W Z， HU P J， XU S Y， et al. Image registration for InISAR based on joint translational motion compensation［J］. IET Radar， Sonar & Navigation， 2017， 11（10）： 1597-1603.
5	BERIZZI F， CORSINI G. Autofocusing of inverse synthetic aperture radar images using contrast optimization［J］. IEEE Transactions on Aerospace and Electronic Systems， 1996， 32（3）： 1185-1191.
6	LI X， LIU G S， NI J L. Autofocusing of ISAR images based on entropy minimization［J］. IEEE Transactions on Aerospace and Electronic Systems， 1999， 35（4）： 1240-1252.
7	CARRARA W G， GOODMAN R S， MAJEWSKI R M. Spotlight synthetic aperture radar： signal processing algorithms［M］. Boston： Artech House， 1995.
8	朱兆达，邱晓晖，余志舜. 用改进的多普勒中心跟踪法进行ISAR运动补偿［J］. 电子学报， 1997， 25（3）： 65-69.
	ZHU Z D， QIU X H， YU Z S. ISAR motion compensation using modified Doppler centroid tracking method［J］. Acta Electronica Sinica， 1997， 25（3）： 65-69 （in Chinese）.
9	CHEN V C， MARTORELLA M. 逆合成孔径雷达成像［M］. 胡明春，孙俊，译.北京：国防工业出版社，2020：107-134.
	CHEN V C， MARTORELLA M. Inverse synthetic aperture radar imaging［M］. HU M C， SUN J， translated. Beijing： National Defense Industry Press， 2020： 107-134 （in Chinese）.
10	DENG Y， ZHANG Y H. Improved PGA algorithm based on adaptive range bins selection［C］// 2010 International Conference on Image Analysis and Signal Processing. Piscataway： IEEE Press， 2010： 232-235.
11	闫龙，郑妍，李颜超. 改进的机载SAR相位梯度自聚焦算法［J］. 应用科技， 2012， 39（1）： 39-43.
	YAN L， ZHENG Y， LI Y C. Improved algorithm of phase gradient autofocus for air-borne synthetic aperture radar［J］. Applied Science and Technology， 2012， 39（1）： 39-43 （in Chinese）.
12	卿吉明，徐浩煜，梁兴东，等. 一种可用于实时成像的改进PGA算法［J］. 雷达学报， 2015， 4（5）： 600-607.
	QING J M， XU H Y， LIANG X D， et al. An improved phase gradient autofocus algorithm used in real-time processing［J］. Journal of Radars， 2015， 4（5）： 600-607 （in Chinese）.
13	郑远攀，李广阳，李晔. 深度学习在图像识别中的应用研究综述［J］. 计算机工程与应用， 2019， 55（12）： 20-36.
	ZHENG Y P， LI G Y， LI Y. Survey of application of deep learning in image recognition［J］. Computer Engineering and Applications， 2019， 55（12）： 20-36 （in Chinese）.
14	MOUSAVI A， RICHARD G B. Learning to invert： Sig-nal recovery via deep convolutional networks［C］∥2017 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE Press， 2017：2272–2276.
15	何晓萍，沈雅云. 深度学习的研究现状与发展［J］. 现代情报， 2017， 37（2）： 163-170.
	HE X P， SHEN Y Y. Focus and trend of deep learning research［J］. Journal of Modern Information， 2017， 37（2）： 163-170 （in Chinese）.
16	张云，穆慧琳，姜义成，等. 基于深度学习的雷达成像技术研究进展［J］. 雷达科学与技术， 2021， 19（5）： 467-478.
	ZHANG Y， MU H L， JIANG Y C， et al. Overview of radar imaging techniques based on deep learning［J］. Radar Science and Technology， 2021， 19（5）： 467-478 （in Chinese）.
17	DING J S， WEN L W， ZHONG C， et al. Video SAR moving target indication using deep neural network［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020： 58（10）： 7194-7204.
18	WEN L W， DING J S， LOFFELD O. Video SAR moving target detection using dual faster R-CNN［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 2984-2994.
19	黄少寅. 基于深度学习的高分辨雷达成像技术研究［D］. 成都：电子科技大学， 2020.
	HUANG S Y. Research on high resolution radar imaging technology based on deep learning［D］. Chengdu： University of Electronic Science and Technology of China， 2020 （in Chinese）.
20	LIU Z， YANG S Y， FENG Z X， et al. Fast SAR autofocus based on ensemble convolutional extreme learning machine［J］. Remote Sensing， 2021， 13（14）： 2683.
21	CHEN J L， YU H W， XU G， et al. Airborne SAR autofocus based on blurry imagery classification［J］. Remote Sensing， 2021， 13（19）： 3872.
22	TANG W， QIAN J， WANG L， et al. SAR image autofocusing based on Res-Unet［C］∥IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. Piscataway： IEEE Press， 2022： 2971-2974.
23	HU C Y， WANG L， LI Z， et al. Inverse synthetic aperture radar imaging using a fully convolutional neural network［J］. IEEE Geoscience and Remote Sensing Letters， 2020， 17（7）： 1203-1207.
24	HU C， WANG L， LI Z， et al. A novel inverse synthetic aperture radar imaging method using con-volutional neural networks ［C］∥5th International Workshop on Compressed Sensing Applied to Radar， Multimodal Sensing， and Imaging （CoSeRa）. Piscataway： IEEE Press 2018： 1-5.
25	YUAN Y X， LUO Y， KANG L， et al. Range alignment in ISAR imaging based on deep recurrent neural network［J］. IEEE Geoscience and Remote Sensing Letters， 2022， 19： 1-5.
26	SHI H Y， LIU Y， GUO J W， et al. ISAR autofocus imaging algorithm for maneuvering targets based on deep learning and keystone transform［J］. Journal of Systems Engineering and Electronics， 2020， 31（6）： 1178-1185.
27	WANG L， LOFFELD K， MA K， et al. Sparse ISAR im-aging using a greedy Kalman filtering approach［J］. Signal Processing， 2017，138：1-10.
28	汪玲，朱栋强，马凯莉，等. 空间目标卡尔曼滤波稀疏成像方法［J］. 电子与信息学报， 2018， 40（4）： 846-852.
	WANG L， ZHU D Q， MA K L， et al. Sparse imaging of space targets using Kalman filter［J］. Journal of Electronics & Information Technology， 2018， 40（4）： 846-852 （in Chinese）.
29	BACCI A， GIUSTI E， CATALDO D， et al. ISAR resolution enhancement via compressive sensing： a comparison with state of the art SR techniques［C］∥2016 4th International Workshop on Compressed Sensing Theory and its Applications to Radar， Sonar and Remote Sensing （CoSeRa）. Piscataway： IEEE Press， 2016： 227-231.
30	WANG L， LOFFELD O. ISAR imaging using a null space ℓ1 minimizing Kalman filter approach［C］∥2016 4th International Workshop on Compressed Sensing Theory and its Applications to Radar， Sonar and Remote Sensing （CoSeRa）. Piscataway： IEEE Press， 2016： 232-236.
31	吴东，郝明. 基于图像对比度的舰船目标成像算法［J］. 电子测量技术， 2017， 40（12）： 110-116.
	WU D， HAO M. New ISAR imaging interval selection method for ship targets on sea based on imaging contrast［J］. Electronic Measurement Technology， 2017， 40（12）： 110-116 （in Chinese）.

超参数	学习率	学习率策略	迭代次数	优化策略
姿态1	0.000 01	固定	150	SGD
姿态2	0.000 01	固定	50	SGD

指标	ENT	IC	FA	MD	RRMSE	TCR
初像	7.882	3.338	808	14	1.311	27.182
MEA	7.024	6.097	86	29	0.519	31.606
PGA	6.773	7.762	57	29	0.474	33.564
CNN	6.191	11.22	10	12	0.196	67.075
FCN	6.556	8.715	3	2	0.120	68.336

指标	ENT	IC	FA	MD	RRMSE	TCR
初像	7.894	3.185	982	9	1.471	26.912
MEA	6.871	6.182	55	21	0.705	37.955
PGA	6.592	8.090	55	21	0.602	41.676
CNN	5.574	11.22	95	21	1.253	46.457
FCN	6.479	8.341	25	6	0.507	45.988

指标	ENT	IC	FA	MD	RRMSE	TCR
初像	6.309	7.745	257	106	0.980 9	44.913
MEA	6.181	8.913
PGA	6.160	9.174
CNN	6.521	8.608	156	117	0.613	51.645
FCN	5.260	11.202	74	110	0.549	57.392

指标	ENT	IC	FA	MD	RRMSE	TCR
初像	5.320	14.527	58	56	0.721	60.242
MEA	4.844	18.002
PGA	5.167	15.489
CNN	5.669	9.416	182	38	0.976	48.655
FCN	4.163	20.239	4	54	0.327	85.591

An ISAR autofocus imaging algorithm based on FCN and transfer learing

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 31

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Rongzu LI, Li LIU, Dun YANG. Optimal design of hydrogen-powered UAV based on multi-source domain fusion surrogate model [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(9): 630979-630979.
[2]	Jianing JIN, Ling WANG, Rui GONG, Daiyin ZHU. 3D imaging of passive squint InISAR using target-borne illuminator of opportunity [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(8): 330982-330982.
[3]	Yang JIAO, Yuting LU, Ba XU, Jian OUYANG. Transfer prediction of satellite traffic based on spatiotemporal correlation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(4): 330938-330938.
[4]	Zhihao ZHAO, Zhaohua YANG, Yun WU, Yuanjin YU. Single-photon counting imaging denoising method based on deep learning in low-light environment [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 630531-630531.
[5]	Zidi ZHONG, Qi GUO, Zhijun TU, Huijie ZHAO, Senbo WANG. Long-wave infrared polarization imaging based on liquid crystal polarization grating [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 630523-630523.
[6]	Chengjie GUO, Dian XU, Jinbao LI, Chaoyu CHENG, Shuochang GUO, Rui LI. Stress characterization of high-temperature digital image correlation experiments based on a data fusion-knowledge transfer method [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531574-531574.
[7]	Pengfei WANG, Lifang ZENG, Xueming SHAO, Jun LI. Multi-source data fusion modeling method for aerodynamic load of aircraft wing based on pre-training and fine-tuning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532297-532297.
[8]	Zichao LIU, Jiang WANG, Peng WANG, Defu LIN, Zhichuan HE. Time-constrained multi-missile cooperative guidance law [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730607-730607.
[9]	Li YAN, Jie ZHANG, Jiadong WANG. [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730559-730559.
[10]	Jiang CUI, Fan ZHOU, Yongfan CHEN, Li YU, Zhuoran ZHANG. A technique for aerospace generator rectifier fault diagnosis based on GAMF-CNN [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(24): 330398-330398.
[11]	Yanxin ZHANG, Hongjian ZHANG, Jianjun XIONG, Zhao ZHAO, Lin RAN, Xian YI. Ice accumulation identification and localization method based on ultrasonic guided waves [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(16): 129293-129293.
[12]	Biyao QIANG, Kaining SHI, Junxue REN, Yaoyao SHI. Instance transfer for tool remaining useful life prediction cross working conditions [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(13): 629038-629038.
[13]	Gongye YU, Weidong CAI, Minghui HU, Wencai LIU, Bo MA. Intelligent migration diagnosis of mechanical faults driven by hybrid fault mechanism and domain adaptation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(2): 426800-426800.
[14]	Haowen LUO, Shaoming HE, Tianyu JIN, Zichao LIU. Impact-angle-constrained with time-minimum guidance algorithm based on transfer learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 328400-328400.
[15]	Haowei NI, Guoyan LIU, Yi ZHOU, Biao ZHANG, Weijie LIU, Chuanlong XU. 3D front tomographic reconstruction of swirl flame by ultraviolet multi-camera imaging [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(18): 128331-128331.