Contour Extraction Method of ISAR Image Object Based on Improved Clean Algorithm

doi:10.3969/j.issn.1009-086x.2025.02.017

Abstract

Abstract:

Traditional methods can extract target contour features from inverse synthetic aperture radar （ISAR） images. However， they have the problem of low accuracy. Therefore， this article proposes a target contour extraction method from ISAR images based on an improved Clean algorithm. Based on the random occurrence of noise， this article establishes an optimization function for scattering point extraction， and uses the iterative Clean method to extract as many weak scattering points as possible. A scattering point quality evaluation method based on connectivity analysis is introduced. This method is used in the post-processing of the Clean algorithm. It denoises the points extracted by the Clean algorithm and preserves the scattering points of the target. The scattering point set is processed with alpha-shape and wavelet filtering to get the target contour. The simulation and measured data processing results show that this method gives more accurate contour than existing methods. It also has better noise resistance.

Key words: inverse synthetic aperture radar （ISAR） image, contour extraction, Clean algorithm, optimized iteration, noise point removal

摘要：

针对逆合成孔径雷达（inverse synthetic aperture radar, ISAR）图像目标轮廓特征提取的现有方法精度不高的问题，提出了一种基于改进Clean算法的ISAR像目标轮廓提取方法。先根据噪声随机出现的特点，建立散射点提取优化函数，并通过迭代Clean方法尽可能提取更多的微弱散射点；针对Clean算法的后处理，采用了基于连通性分析的散射点质量评估方法，对Clean算法提取的散射点进行去噪，并保留目标本体的散射点集；最后对散射点集，使用Alpha-Shape和小波滤波处理获得目标轮廓。仿真和实测数据处理结果表明，所提方法和现有的轮廓提取方法相比，轮廓特征提取精度更高，且抗噪声性能更好。

关键词: 逆合成孔径雷达图像, 轮廓提取, Clean算法, 优化迭代, 噪点去除

CLC Number:

TN95

Yuzhe FAN, Lingang FAN, Zhiheng ZHANG, Chengzeng CHEN. Contour Extraction Method of ISAR Image Object Based on Improved Clean Algorithm[J]. Modern Defense Technology, 2025, 53(2): 156-166.

范宇哲, 范林刚, 张志衡, 陈成增. 基于改进Clean算法的ISAR像目标轮廓提取方法[J]. 现代防御技术, 2025, 53(2): 156-166.

Figures/Tables 15

Fig. 1 Schematic diagram of target equivalent scattering points

Fig. 2 Process of contour extraction

Fig. 3 Points extracted by Clean algorithm based on optimizing threshold

Fig. 4 Removing isolated points

Fig. 5 Preserving the maximum connected set

Fig. 6 Contour formed by the line connecting the target boundary points

Fig. 7 Contour after wavelet filtering

Fig. 8 Artificial contour extraction from satellite simulation data

Fig. 9 Artificial contour extraction from Yak42 data

Fig. 10 Comparison of contour extraction methods for satellite simulation data

Table 1 Effect and operation time of contour extraction from satellite simulation data using different methods

轮廓提取方法	Hausdorff距离	SSIM	$P F O M$	$R N$	运行时间/s
Canny算子	20.615	0.969	0.380	0.301	1.33
自适应收敛方法	11.890	0.976	0.524	-0.604	20.78
常规Clean算法	11.402	0.976	0.563	-0.445	2.34
本文方法	10.630	0.978	0.574	-0.290	6.19

Table 1 Effect and operation time of contour extraction from satellite simulation data using different methods

轮廓提取方法	Hausdorff距离	SSIM	$P F O M$	$R N$	运行时间/s
Canny算子	20.615	0.969	0.380	0.301	1.33
自适应收敛方法	11.890	0.976	0.524	-0.604	20.78
常规Clean算法	11.402	0.976	0.563	-0.445	2.34
本文方法	10.630	0.978	0.574	-0.290	6.19

Fig. 11 Comparison of contour extraction methods for Yak42 measured data

Table 2 Effect and operation time of contour extraction from Yak42 measured data using different methods

轮廓提取方法	Hausdorff距离	SSIM	$P F O M$	$R N$	运行时间/s
Canny算子	9.434	0.939	0.692	0.052	1.44
自适应收敛方法	9.000	0.938	0.689	-0.092	15.35
常规Clean算法	9.291	0.941	0.523	-0.735	1.98
本文方法	6.325	0.943	0.709	-0.018	6.82

Table 2 Effect and operation time of contour extraction from Yak42 measured data using different methods

轮廓提取方法	Hausdorff距离	SSIM	$P F O M$	$R N$	运行时间/s
Canny算子	9.434	0.939	0.692	0.052	1.44
自适应收敛方法	9.000	0.938	0.689	-0.092	15.35
常规Clean算法	9.291	0.941	0.523	-0.735	1.98
本文方法	6.325	0.943	0.709	-0.018	6.82

Fig. 12 Hausdorff distance-SNR curve

Fig. 13 Contour extraction results under low signal-to-noise ratio

References 19

1	CAMP W W， MAYHAN J T， O'DONNELL R M. Wideband Radar for Ballistic Missile Defense and Range-Doppler Imaging of Satellites［J］. Lincoln Laboratory Journal， 2000， 12（2）： 267-280.
2	TOUMI A， HOELTZENER B， KHENCHAF A. Using Watersheds Segmentation on ISAR Image for Automatic Target Recognition［C］∥2007 2nd International Conference on Digital Information Management. Piscataway： IEEE， 2007： 285-290.
3	MANIKANDAN J， VENKATARAMANI B， JAYACHANDRAN M. Evaluation of Edge Detection Techniques Towards Implementation of Automatic Target Recognition［C］∥International Conference on Computational Intelligence and Multimedia Applications （ICCIMA 2007）. Piscataway： IEEE， 2007： 441-445.
4	刘慧敏，王宏强，黎湘. 逆合成孔径雷达像轮廓提取方法［J］. 系统工程与电子技术， 2010， 32（10）： 2076-2080.
	LIU Huimin， WANG Hongqiang， LI Xiang. Research on Contour Extraction Methods for Inverse Synthetic Aperture Radar Images［J］. Systems Engineering and Electronics， 2010， 32（10）： 2076-2080.
5	WEI Xia， ZHENG Sheng， ZENG Xiangyun， et al. Spindle Extraction Method for ISAR Image Based on Radon Transform［C］∥MIPPR 2015： Automatic Target Recognition and Navigation. Bellingham： SPIE， 2015： 981217.
6	杨虹，张雅声，尹灿斌. 空间目标的ISAR成像及轮廓特征提取［J］. 北京航空航天大学学报， 2019， 45（9）： 1765-1776.
	YANG Hong， ZHANG Yasheng， YIN Canbin. ISAR Imaging and Contour Feature Extraction of Space Targets［J］. Journal of Beijing University of Aeronautics and Astronautics， 2019， 45（9）： 1765-1776.
7	西安电子科技大学. 基于CLEAN算法散射中心提取的ISAR目标轮廓提取方法： CN201511016757.0［P］. 2016-03-09.
	Xidian University. ISAR Target Contour Extraction Method Based on CLEAN Algorithm Scattering Center Extraction： CN201511016757.0［P］. 2016-03-09.
8	王欣. 基于酉ESPRIT的超分辨ISAR成像及其应用［D］. 西安：西安电子科技大学， 2015.
	WANG Xin. Unitary ESPRIT Based on Superresolution ISAR Imaging and Its Applications［D］. Xi'an： Xidian University， 2015.
9	张馨元，齐玉涛，林刚. 含旋转部件的动态目标特征提取方法研究［J］. 电波科学学报， 2019， 34（1）： 65-69.
	ZHANG Xinyuan， QI Yutao， LIN Gang. Dynamic Object Feature Extraction with Rotating Parts［J］. Chinese Journal of Radio Science， 2019， 34（1）： 65-69.
10	HUANG K， HE S Y， ZHANG Y H， et al. Research on the Forward Parametric Scattering Center Modeling Method for the Ship on the Rough Surface Model［C］∥2020 IEEE International Conference on Computational Electromagnetics （ICCEM）. Piscataway： IEEE， 2020： 104-105.
11	ÖZDEMIR C. Inverse Synthetic Aperture Radar Imaging with MATLAB® Algorithms［M］. Hoboken： John Wiley & Sons， Inc， 2021.
12	王家东. 机动目标ISAR成像及空间目标特征提取方法研究［D］. 西安：西安电子科技大学， 2020.
	WANG Jiadong. Study on ISAR Imaging of Maneuvering Target and Feature Extraction of Space Targets［D］. Xi'an： Xidian University， 2020.
13	HOGBOM J A. Aperture Synthesis with a Non-Regular Distribution of Interferometer Baselines［J］. Astronony Astrophys Suppl， 1974， 15： 417.
14	WANG Yilun， SHOEMAKER C A. A General Stochastic Algorithmic Framework for Minimizing Expensive Black Box Objective Functions Based on Surrogate Models and Sensitivity Analysis［J］. （2014-10-23）［2024-01-09］. .
15	EDELSBRUNNER H， KIRKPATRICK D， SEIDEL R. On the Shape of a Set of Points in the Plane［J］. IEEE Transactions on Information Theory， 1983， 29（4）： 551-559.
16	HUTTENLOCHER D P， KLANDERMAN G A， RUCKLIDGE W J. Comparing Images Using the Hausdorff Distance［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 1993， 15（9）： 850-863.
17	于微波，周旺，杨宏韬. 基于DSnet网络的零件边缘轮廓提取［J］. 组合机床与自动化加工技术， 2023（2）： 169-173， 177.
	YU Weibo， ZHOU Wang， YANG Hongtao. Part Edge Contour Extraction Based on DSnet Network［J］. Modular Machine Tool & Automatic Manufacturing Technique， 2023（2）： 169-173， 177.
18	ABDOU I E， PRATT W K. Quantitative Design and Evaluation of Enhancement/Thresholding Edge Detectors［J］. Proceedings of the IEEE， 1979， 67（5）： 753-763.
19	江明达. 基于深度学习的SAR图像舰船轮廓提取方法研究［D］. 长春：吉林大学， 2023.
	JIANG Mingda. Research on Ship Contour Extraction Method in SAR Images Based on Deep Learning［D］. Changchun： Jilin University， 2023.

[1]	Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU. Aerodynamic Target Recognition Method Based on Incidence Angle-Guided Radar Image Feature Fusion [J]. Modern Defense Technology, 2025, 53(2): 129-140.
[2]	Xingyu HE, Chenyang SUN, Gang FANG. Multi-static ISAR Three-Dimensional Imaging of Spatial Micro-motion Target [J]. Modern Defense Technology, 2025, 53(2): 141-148.
[3]	Tao XING, Jun LI, Zhirui WANG. Airborne SAR Azimuth Wide Swath Scan Beam Control Method [J]. Modern Defense Technology, 2025, 53(2): 149-155.
[4]	Mingyu LU, Fei MENG, Yanqing WANG, Zhangfeng LI, Yan ZHANG. A Radar Detection Performance Evaluation Method Based on Hybrid Chi-square Model [J]. Modern Defense Technology, 2025, 53(2): 167-174.
[5]	Wenlei SUN, Rongjun GU, Yonghai WANG, Zhizeng ZHOU. Research on Echo Detection Method of Non-cooperative Hybrid Bistatic SAR [J]. Modern Defense Technology, 2025, 53(1): 140-146.
[6]	Donghua WANG, Shaohua CHEN, Chengxiao ZOU, Dongfang XIA. Clutter Suppression Method Based on Triple-Spectrum-Line Interpolation FFT [J]. Modern Defense Technology, 2024, 52(6): 80-87.
[7]	Huiyuan XING, Yaqi CUI, Ziling WANG, Wei XIONG, Bingdong JIANG. Target Detection Algorithm for Ships at Sea Under Complex Sea Conditions [J]. Modern Defense Technology, 2024, 52(6): 88-96.
[8]	Jiajun CHEN, Bing HU, Duanyang SHI, Lijia YANG. Radar Equipment Testability Evaluation Method Based on Improved TOPSIS-RSR [J]. Modern Defense Technology, 2024, 52(5): 162-172.
[9]	Liping YANG, Qiqing FANG, Yahui HU, Chenggang GU, Huimin WANG. Research on Knowledge Graph Construction Method of Early Warning Equipment Based on Deep Learning [J]. Modern Defense Technology, 2024, 52(5): 61-72.
[10]	Qiang LÜ, Haijun LIU, Hui ZHONG, Dezhong LIU. A Fusion Method for Target Tracking Measurement Data of Active and Passive Radar [J]. Modern Defense Technology, 2024, 52(4): 108-116.
[11]	Shunan HAN, Zhulong CHEN, Yongjun LU. Blind Separation of Overlapped Communication Signals Based on Modified Independent Component Analysis [J]. Modern Defense Technology, 2024, 52(3): 87-95.
[12]	Kang ZHAO, Yan YAN, Jiahao TIAN, Xu HE, Yuzhao LI, Lifeng HUANG. Design of Sparse MIMO Array for Near-Filed 3D Imaging [J]. Modern Defense Technology, 2024, 52(3): 112-119.
[13]	Xiaoyang WANG. Mechanism of Variable Polarization Jamming on Radar Side⁃lobe Cancellation [J]. Modern Defense Technology, 2024, 52(2): 145-150.
[14]	Xiaofeng AI, Jing WU, Jingke ZHANG, Yiqi ZHU, Zhiming XU, Qihua WU. Design and Implementation of Radar Intelligent Recognition Simulation System for Aerospace Targets [J]. Modern Defense Technology, 2024, 52(2): 151-162.
[15]	Cheng SHANG, Zhiming XU, Yang ZHANG, Kaiyu ZHANG, Qihua WU, Yiqi ZHU, Xiaofeng AI. Design and Realization of an Dynamic Electromagnetic Scattering Data Simulation System for Air Target [J]. Modern Defense Technology, 2024, 52(2): 163-171.