空间目标ISAR图像部件正向标记方法

doi:10.12305/j.issn.1001-506X.2026.04.07

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (4): 1165-1173.doi: 10.12305/j.issn.1001-506X.2026.04.07

• 传感器与信号处理 • 上一篇

空间目标ISAR图像部件正向标记方法

杨泽莹(), 陈卓, 徐志明(), 艾小锋, 吴其华, 王玲

国防科技大学电子科学学院CEMEE国家重点实验室，湖南长沙 410073

收稿日期:2024-10-22 修回日期:2025-01-23 接受日期:2026-02-16 出版日期:2025-03-11 发布日期:2025-03-11
通讯作者: 徐志明 E-mail:Yzing0617@163.com;zmxu_nudt@163.com
作者简介:杨泽莹（2000—），女，硕士研究生，主要研究方向为空间目标信息处理
陈　卓（2001—），男，硕士研究生，主要研究方向为目标极化散射特性
艾小锋（1983—），男，副研究员，博士，主要研究方向为雷达目标特性分析
吴其华（1990—），男，讲师，博士，主要研究方向为雷达电子对抗与雷达成像技术
王　玲（1975—），女，教授，博士，主要研究方向为雷达智能信息处理
基金资助:
国家自然科学基金青年科学基金项目（62401580）；国家自然科学基金（62541134）资助课题

Forward labeling method for ISAR image components of space targets

Zeying YANG(), Zhuo CHEN, Zhiming XU(), Xiaofeng AI, Qihua WU, Ling WANG

State Key Laboratory Complex Eletromagnetic Environmental Effects on Electronics and Information System，National University of Denfense Technology，Changsha 410073，China

Received:2024-10-22 Revised:2025-01-23 Accepted:2026-02-16 Online:2025-03-11 Published:2025-03-11
Contact: Zhiming XU E-mail:Yzing0617@163.com;zmxu_nudt@163.com

摘要/Abstract

摘要：

为解决基于深度学习空间目标逆合成孔径雷达（inverse synthetic aperture radar，ISAR）图像解译的数据需求痛点，提出一种空间目标ISAR图像部件正向标记方法。首先，将空间目标三维模型按照部件进行分割；然后，将不同部件进行投影，考虑目标自身遮挡，利用深度缓冲器算法进行面元遮挡判断；最后，将投影面得到的不同部件的点集合进行边缘检测，得到部件标记结果。所提方法可实现空间目标ISAR图像部件的正向标记，解决人工效率低下和精细部件人工标记难以实现的问题，为面向深度学习的空间目标ISAR图像部件辨识方法提供有力的标签数据支撑。

关键词: 空间目标, 部件标记, 逆合成孔径雷达, 深度学习

Abstract:

To address the pain point of data requirements for deep learning based spatial target inverse synthetic aperture radar (ISAR) image interpretation, a forward labeling method for ISAR image components of space targets is proposed. Firstly, the three-dimensional model of the space target is divided into parts according to components. Then, different components are projected, and considering that the target itself is occluded, the depth buffer algorithm is used to judge the face element occlusion. Finally, the point collection of different parts is detected at the edge, and the component labels are obtained. The proposed method realizes the forward labeling of ISAR image components of space targets, solves the problems of low manual efficiency and difficulty to achieve manual labeling of fine components, providing strong data labeling support for the space targets component identification method of ISAR images oriented to deep learning.

Key words: space target, component labeling, inverse synthetic aperture radar (ISAR), deep learning

中图分类号:

杨泽莹, 陈卓, 徐志明, 艾小锋, 吴其华, 王玲. 空间目标ISAR图像部件正向标记方法[J]. 系统工程与电子技术, 2026, 48(4): 1165-1173.

Zeying YANG, Zhuo CHEN, Zhiming XU, Xiaofeng AI, Qihua WU, Ling WANG. Forward labeling method for ISAR image components of space targets[J]. Systems Engineering and Electronics, 2026, 48(4): 1165-1173.

图/表 13

图1

图2

图3

图4

图5

图6

图7

表1

表2

图8

表3

图9

图10

参考文献 31

1	MARCHETTI E, STOVE A G, HORAE E G, et al. Space-based sub-THz ISAR for space situational awareness concept and design[J]. IEEE Trans. on Aerospace and Electronic Systems, 2022, 58 (3): 1558- 1573. doi: 10.1109/TAES.2021.3126375
2	ZHOU Y J, ZHANG L, WEI S P, et al. Dynamic analysis of spin satellites through the quadratic phase estimation in multiple-station radar images[J]. IEEE Trans. on Computational Imaging, 2020, 6, 894- 907. doi: 10.1109/TCI.2020.2995052
3	XIE P F, ZHANG L, DU C, et al. Space target attitude estimation from ISAR image sequences with key point extraction network[J]. IEEE Signal Processing Letters, 2021, 28, 1041- 1045. doi: 10.1109/LSP.2021.3075606
4	ZHOU Y J, ZHANF L, CAO Y H. Dynamic estimation of spin spacecraft based on multiple-station ISAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2020, 58 (4): 2977- 2989. doi: 10.1109/TGRS.2019.2959270
5	SHAO S, ZHANG L, LIU H W, et al. Images of 3D maneuvering motion targets for interferometric ISAR with 2-D joint sparse reconstruction[J]. IEEE Trans. on Geoscience and Remote Sensing, 2020, 59(11): 9397: 9423.
6	ZHOU Y J, MA Y, ZHANG L, et al. Review of on-orbit state estimation of space targets with radar imagery[J]. Journal of Radars, 2021, 10 (4): 607- 621.
7	ZHANG S H, LIU Y X, LI X, et al. Joint sparse aperture ISAR auto focusing and scaling via modified newton method-based variational Bayesian inference[J]. IEEE Trans. on Geoscience and Remote Sensing, 2019, 57 (7): 4857- 4869. doi: 10.1109/TGRS.2019.2893505
8	HUO C Y, YIN H C, XING X Y. Attitude direction estimation for space target antenna loadbased on radar image features[J]. Chinese Journal of Radio Science, 2019, 34 (1): 45- 51.
9	WANG H T, YANG Q, WANG H, et al. Precise motion compensation method in terahertz ISAR imaging based on sharpenss maximization[J]. Electronics Letters, 2022, 58 (21): 813- 815. doi: 10.1049/ell2.12615
10	MARCHETTI E, STOVE A, CHERNIAKOV M, et al. Space-based sub-Thz ISAR system for objects with translational motion[C]// Proc. of the IEEE Radar Confenence, 2020: 21−25.
11	ZHOU Y J, WEI S P, ZHANG L, et al. Dynamic estimation of spin satellite from the single-station ISAR image sequence with the hidden Markov model[J]. IEEE Trans. on Aerospace and Electronic Systems, 2022, 58 (5): 4626- 4638. doi: 10.1109/TAES.2022.3164015
12	XIE P F, ZHANG L, MA Y, et al. Attitude estimation and geometry inversion of satellite based on oriented object detection[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 4023505. doi: 10.1109/lgrs.2022.3169686
13	CUI X C, FU Y W, SU Y, et al. Physical parameters joint estimation of satellite parabolic antenna with key frame Pol-ISAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62, 5100416.
14	杜兰, 吕国欣, 石钰. 基于GAN的ISAR图像语义分割方法[J]. 雷达科学与技术, 2021, 19 (5): 479- 484,490,464.
	DU L, LYU G X, SHI Y. ISAR image semantic segmentation based on GAN[J]. Radar Science and Technology, 2021, 19 (5): 479- 484,490,464.
15	PENG K, XIANG F, LIU Y X, et al. ISAR image segmentation for space target based on contrastive learning and NL-Unet[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20, 3506105.
16	武光辉, 童创明, 李西敏, 等. 基于并行PO/EEC的ISAR回波与成像仿真[J]. 现代雷达, 2016, 38 (10): 18- 22.
	WU G, TONG C, LI X M, et al. ISAR echo simulation and imaging based on parallel hybrid PO/EEC method[J]. Modern Radar, 2016, 38 (10): 18- 22.
17	JIANG Y, ZHANG P Y, LI J P, et al. Wide-band radar target modeling and echo simulation[J]. Aerospace Shanghai, 2019, 36 (4): 71- 75.
18	WANG J D, DU L, LI Y C, et al. Attitude and size estimation on satellite targets based on ISAR image interpretetion[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5109015.
19	卢奎锋, 段锐, 李沫, 等. Ka频段宽带步进频ISAR成像仿真[J]. 系统仿真技术, 2021, 17 (3): 143- 147.
	LU K F, DUAN R, LI M, et al. Ka-band broadband stepped frequency ISAR imaging simulation[J]. System Simulation Technology, 2021, 17 (3): 143- 147.
20	ZHOU Y J, ZHANG L, CAO Y H, et al. optical-and-radar image fusion for dynamic estimation of spin satellites[J]. IEEE Trans. on Image Processing, 2020, 29, 2963- 2976.
21	黎吉顺, 张雅声, 尹灿斌, 等. 空间目标部件标记ISAR成像仿真方法[J]. 现代雷达, 2025, 47 (7): 46- 55.
	LI J S, ZHANG Y S, YIN C B, et al. ISAR imaging simulation method of space target component labeling[J]. Modern Radar, 2025, 47 (7): 46- 55.
22	匡燕, 李安, 李子扬, 等. ENVISAT卫星综述[J]. 遥感信息, 2007, 1, 90- 92.
	KUANG Y, LI A, LI Z Y, et al. ENVISAT satellite overview[J]. Remote Sensing Information, 2007, 1, 90- 92.
23	XIE P F, ZHANG L, DU C, et al. Space target attitude estimation from ISAR image sequences with key point extraction network[J]. IEEE Signal Processing Letters, 2021, 28, 1042- 1045.
24	DU R Z, LIU L, BAI X R, et al. Instantaneous attitude estimation of spacecraft utilizing joint optical-and-ISAR observation[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5112114.
25	CEXUS J C, TOUMI A, RIAHI M. Target recognition from ISAR image using polar mapping and shape matrix[C]//Proc. of the 5th International Conference on Advanced Technologies for Signal and Image Processing, 2020.
26	XUE R H, BAI X R, CAO X Y, et al. Sequential ISAR target classification based on hybrid transformer[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5111411.
27	XUE R H, BAI X R, ZHOU F, et al. SAISAR-Net: a robust sequential adjustment ISAR image classification network[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5214715.
28	ANDREAS KAMP. From the Paleolithic to Postmidernity-the genisis of our epochal system[M]. Amsterdam: John Benjamins Publishing Company, 2010.
29	KOU P, LIU Y X, ZHANG C, et al. Attitude estimation method of spacecraft in orbit with complex structure using sequential ISAR images[J]. Systems Engineering and Electronics, 2023, 45 (8): 2438- 2445.
30	LIU L, ZHOU Z B, ZHOU F, et al. A new 3-D geometry reconstruction method of space target utilizing the scatterer energy accumulation of ISAR image sequence[J]. IEEE Trans. on Geoscience and Remote Sensing, 2020, 58 (12): 8345- 8357.
31	TORRALBA A, RUSSELL B C, YUEN J. LabelMe: online image annotation and applications[J]. Proceedings of the IEEE, 2010, 98 (8): 1467- 1484.

部件中文名称	英文名称	颜色（RGB）	颜色示例
太阳能帆板	Solar panel	[1 1 0]
主体	Body	[1 0 0]
SAR天线	SAR antenna	[0 1 0]
RA2天线	RA2-antenna	[0 0 1]
X波段天线	X-band antenna	[0 1 1]
全球臭氧层监视仪	GOMOS	[0 0.4470 0.7410]
中等分辨率成像频谱仪	MERIS	[0.9290 0.6940 0.1250]
载荷	Payload	[0.4940 0.1840 0.5560]
大气探测迈克尔逊干涉仪	MIPAS	[0.6350 0.0780 0.1840]
先进跟踪扫描辐射计	AATSR	[0.8500 0.3250 0.0980]
扫描成像吸收频谱仪	SCIAMACHY	[0.01 0.66 0.62]
Ka波段天线	Ka-band antenna	[0.3010 0.7450 0.9330]

部件中文名称	英文名称	颜色（RGB）	颜色示例
太阳能帆板	Solar panel	[1 1 0]
主体	Body	[1 0 0]
天线1	Antenna-1	[0 1 0]
天线2	Antenna-2	[0 0 1]
储能设备	Battery	[1 0 1]
对接机构	Docking machansim	[0.4660 0.6740 0.1880]
喷管	Nozzle	[0.9290 0.6940 0.1250]
载荷	Payload	[0.4940 0.1840 0.5560]
望远镜	Telescope	[0.6350 0.0780 0.1840]

参数	设量
模型名称	EnviSat/天链一号
中心频率/GHz	10
带宽/GHz	2
俯仰角/(°)	$0\sim 90 $
方位角/(°)	$ -180 \sim 180$

[1]	程鲲, 雷洪涛, 吕志轩. 改进YOLOv8的轻量级无人机跟踪方法[J]. 系统工程与电子技术, 2026, 48(3): 737-750.
[2]	张龙, 朱连宏, 杨波, 雷震, 冯轩铭. MFA-Net：一种面向复杂对抗环境的反舰导弹智能识别多模态自适应融合网络[J]. 系统工程与电子技术, 2026, 48(3): 894-907.
[3]	田弘宇, 葛松虎, 郭宇, 崔中普, 梁潇. 低干噪比下多特征融合的通信干扰识别方法[J]. 系统工程与电子技术, 2026, 48(3): 1061-1071.
[4]	包玉刚, 贾皓翔, 赵旦峰. 基于高阶递归网络的单幅图像去雨滴模型[J]. 系统工程与电子技术, 2026, 48(1): 12-21.
[5]	陈海青, 汪刘应, 刘顾, 王龙, 葛超群, 陈孟州. 合成孔径雷达图像去噪算法研究进展[J]. 系统工程与电子技术, 2026, 48(1): 94-105.
[6]	李开明, 张袁鹏, 罗迎, 代肖楠. 弹道导弹雷达目标识别研究进展[J]. 系统工程与电子技术, 2025, 47(9): 2870-2889.
[7]	季策, 马相宇, 牟晓宇, 赵家毅. TS-GRU-VTA：基于深度学习的车辆信道估计方案[J]. 系统工程与电子技术, 2025, 47(9): 3093-3098.
[8]	闫小伟, 凌冲, 石胜斌. 地表未爆子弹药快速检测系统设计与实现[J]. 系统工程与电子技术, 2025, 47(8): 2639-2645.
[9]	张琬滢, 高由兵, 李泽一, 李鹏飞, 张伟. 基于双路径特征融合网络的背景信号抑制算法[J]. 系统工程与电子技术, 2025, 47(7): 2406-2413.
[10]	张新征, 闫梦可, 朱晓林. 噪声伪标签容忍的半监督SAR目标识别[J]. 系统工程与电子技术, 2025, 47(6): 1796-1805.
[11]	贾竣皓, 陈学斌, 李璋峰, 叶春茂. 空间群目标ISAR成像与检测方法[J]. 系统工程与电子技术, 2025, 47(6): 1843-1854.
[12]	姜智杰, 宋恒, 胡楠, 段兰茜, 曹平. 隧道环境毫米波雷达目标识别与分类算法[J]. 系统工程与电子技术, 2025, 47(5): 1453-1460.
[13]	聂千祁, 沙明辉, 朱应申, 王崇宇, 崔念强. 基于盲源分离结合奇异谱分析的雷达多分量信号识别方法[J]. 系统工程与电子技术, 2025, 47(4): 1168-1175.
[14]	袁磊, 杨艳娟, 郭毅, 戴鹏. 相关噪声下基于深度学习的LDPC码码率半盲识别算法[J]. 系统工程与电子技术, 2025, 47(4): 1335-1345.
[15]	沈夏闰, 李若楠, 张昊田. 基于CVAE-LSTM的服务器KPI异常检测[J]. 系统工程与电子技术, 2025, 47(3): 1019-1027.

空间目标ISAR图像部件正向标记方法

Forward labeling method for ISAR image components of space targets

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价