一种基于极化分解特征和SVDD的扩展目标检测算法

doi:10.11959/j.issn.1000-0801.2023197

电信科学 ›› 2023, Vol. 39 ›› Issue (10): 64-73.doi: 10.11959/j.issn.1000-0801.2023197

• 研究与开发 • 上一篇

一种基于极化分解特征和SVDD的扩展目标检测算法

李强¹, 姚远昕², 孔祥琦³

¹ 工业和信息化部机关服务局，北京 100804
² 中国信息通信研究院西部分院，重庆 401336
³ 国家无线电监测中心检测中心，北京 100041

修回日期:2023-09-19 出版日期:2023-10-01 发布日期:2023-10-01
作者简介:李强（1976- ），男，工业和信息化部机关服务局高级工程师，主要研究方向为计算机技术、软件工程、无线电技术等
姚远昕（1996- ），男，中国信息通信研究院西部分院工程师，主要研究方向为无线电频谱规划、国内外无线电管理相关政策
孔祥琦（1995- ），女，国家无线电监测中心检测中心工程师，主要研究方向为无线电设备检测、无线电频谱管理等

A range spread target detection algorithm based on polarimetric features and SVDD

Qiang LI¹, Yuanxin YAO², Xiangqi KONG³

¹ Agency Service Bureau of the Ministry of Industry and Information Technology, Beijing 100804, China
² West Institute of CAICT, Chongqing 401336, China
³ The State Radio Monitoring Center Testing Center, Beijing 100041, China

Revised:2023-09-19 Online:2023-10-01 Published:2023-10-01

摘要/Abstract

摘要：

多极化距离高分辨雷达是地面静止目标检测的重要手段，其回波中目标占据多个距离单元，成为扩展目标。传统基于回波能量的扩展目标检测方法的性能随信杂比的降低而下降。提出一种基于极化分解特征的扩展目标检测算法，利用目标和杂波之间的极化散射特性差异提升低信杂比下的检测性能。所提方法提取16 种极化分解特征组成特征向量作为检测统计量，再使用支持向量数据描述（SVDD）算法估计判别门限。在判别门限的训练阶段，杂波数据的极化分解特征被提取用作训练数据。并且为保证虚警概率，在SVDD的目标函数中引入了两个惩罚参数。使用实测数据进行了实验验证，所提方法在戈壁背景、虚警概率为 10^-4、检测概率为90%的情况下，所需信杂比约为12.6 dB，相较于基于能量的对比方法降低约1.7 dB。

关键词: 极化高分辨雷达, 扩展目标检测, 极化分解, FAC-SVDD

Abstract:

Multi-polarization range high resolution radar is an important mean for ground target detection.In the echo formed by it, the target occupies multiple range cells and becomes an extended target.The traditional spread target detection method relies on energy, and the detection performance decreases when the signal-to-clutter ratio decreases.A spread target detection algorithm based on polarization decomposition features was proposed, which improved the detection performance under low signal-to-clutter ratio by using the difference of polarization scattering characteristics between target and clutter.Specifically, 16 kinds of polarization decomposition features were extracted to form feature vectors as detection statistics, and then support vector data description (SVDD) was used to obtain the detection threshold.When training the detection threshold, the polarization decomposition features of clutter were extracted as training data.In order to ensure the false alarm probability, two penalty parameters were introduced into the objective function of SVDD.The experimental results show that the proposed method requires a signal-to-clutter ratio of about 12.6 dB in the case of Gobi background, false alarm probability of 10^-4 and detection probability of 90%, which is about 1.7 dB lower than the energy-based methods.

Key words: polarimetric high resolution radar, range spread target detection, polarimetric decomposition, FAC-SVDD

中图分类号:

TN956

李强, 姚远昕, 孔祥琦. 一种基于极化分解特征和SVDD的扩展目标检测算法[J]. 电信科学, 2023, 39(10): 64-73.

Qiang LI, Yuanxin YAO, Xiangqi KONG. A range spread target detection algorithm based on polarimetric features and SVDD[J]. Telecommunications Science, 2023, 39(10): 64-73.

图/表 8

图1

图2

表1

图3

图4

图5

图6

表2

参考文献 28

[1]	LONG T , LIANG Z N , LIU Q H . Advanced technology of high-resolution radar:target detection,tracking,imaging,and recognition[J]. Science China (Information Sciences), 2019,62(4): 5-30.
[2]	王雪松 . 雷达极化技术研究现状与展望[J]. 雷达学报, 2016,5(2): 119-131.
	WANG X S . Status and prospects of radar polarimetry techniques[J]. Journal of Radars, 2016,5(2): 119-131.
[3]	NOVAK L M , SECHTIN M B , CARDLLO M J . Studies of target detection algorithms that use polarimetric radar data[J]. IEEE Transactions on Aerospace and Electronic Systems, 1989,25(2): 150-165.
[4]	HUGHES P K . A high resolution radar detection strategy[J]. IEEE Transactions on Aerospace and Electronic Systems, 1983,19(5): 663-667.
[5]	CHEN X L , HOU K Y , CHAND S Q ,et al. Detection of range-spread targets based on order statistics[J]. Digital Signal Processing, 2023(133).
[6]	JIANG Y , WANG Y H , LI Y ,et al. Eigenvalue-based ground target detection in high-resolution range profiles[J]. IET Radar Sonar and Navigation, 2020,14(11): 1747-1756.
[7]	WANG Z Y , LI G , LI M . Adaptive detection of distributed target in the presence of signal mismatch in compound Gaussian clutter[J]. Digital Signal Processing, 2020(102).
[8]	石星宇, 许述文, 王晓峰 ,等. 复合高斯杂波下距离扩展目标斜对称自适应子空间检测器[J]. 信号处理, 2023,39(6): 1036-1046.
	SHI X Y , XU S W , WANG X F ,et al. Persymmetric adaptive subspace detectors for range-spread targets in compound-Gaussian clutter[J]. Journal of Signal Processing, 2023,39(6): 1036-1046.
[9]	REN Z C , YI W , ZHAO W J ,et al. Range-spread target detection based on adaptive scattering centers estimation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023(61): 1-14.
[10]	JING X C , SU H T , SHEN L ,et al. Adaptive radar detection in the clutter and noise cover pulse jamming environment[J]. Signal Processing, 2022,205:108852.
[11]	SHI X Y , YANG C Q , WANG X F ,et al. Dual-polarimetric persymmetric adaptive subspace detector for range-spread targets in heavy tailed non-Gaussian clutter[J]. IEEE Geoscience and Remote Sensing Letters, 2023(20): 1.
[12]	郭鹏程 . 复杂背景下雷达地面目标检测与识别技术研究[D]. 西安:西安电子科技大学, 2022.
	GUO P C . Detection and recognition for radar ground target in complex environments[D]. Xi'an:Xidian University, 2022.
[13]	YUAN Y , ZHU H , WANG Q ,et al. Correlation feature-based detector for range distributed target in sea clutter[J]. Eurasip Journal on Advances in Signal Processing, 2018(1): 1.
[14]	XU S , ZHU J , SHUI P ,et al. Floating small target detection in sea clutter by one-class SVM based on three detection features[C]// Proceedings of International Applied Computational Electromagnetics Society Symposium - China. Piacataway:IEEE Press, 2019.
[15]	SHI Y , XIE X , LI D . Range distributed floating target detection in sea clutter via feature-based detector[J]. IEEE Geoscience and Remote Sensing Letters, 2016: 1847-1850.
[16]	SHUI P L , LIU H W , BAO Z . Range-spread target detection based on cross time-frequency distribution features of two adjacent received signals[J]. IEEE Transactions on Signal Processing, 2009,57(10): 3733-3745.
[17]	YANG X L , WEN G J , MA C H ,et al. CFAR detection of moving range-spread target in white Gaussian noise using waveform contrast[J]. IEEE Geoscience ＆ Remote Sensing Letters, 2016,13(2): 282-286.
[18]	LIU C , YANG J , ZHENG J ,et al. An unsupervised port detection method in polarimetric SAR images based on three- component decomposition and multi-scale thresholding segmentation[J]. Remote Sensing, 2022,14(1): 205.
[19]	LI H L , CUI X C , CHEN S W . PolSAR ship detection with optimal polarimetric rotation domain features and SVM[J]. Remote Sensing, 2021,13(19): 3932.
[20]	PRAJAPATI K , PRAJAPATI P , RAMAKRISHNAN R ,et al. Feature combination of Pauli and H/A/Alpha decomposition for improved oil spill detection using SAR[J]. Recent Trends in Image Processing and Pattern Recognition, 2021(1380): 134-147.
[21]	ZHAI W , WANG X Q , BI Y X ,et al. Extraction of earthquake damage information and mapping of buildings from single post-earthquake polarimetric synthetic aperture radar image based on polarimetric decomposition and texture features[J]. Sens.Mater., 2022,34(12): 4451-4462.
[22]	RODING M , THOMA R S . Polarimetric covariance matrix processing for target discrimination in time domain[A]// 2015 16th International Radar Symposium (IRS)[C]. 2015.
[23]	陈华华, 陈哲 . 基于钉板分布稀疏变分自编码器的异常检测算法研究[J]. 电信科学, 2022,38(12): 65-77.
	CHEN H H , CHEN Z . Research on anomaly detection algorithm based on sparse variational autoencoder using spike and slab prior[J]. Telecommunications Science, 2022,38(12): 65-77.
[24]	LI Y Z , XIE P C , TANG Z S ,et al. SVM-based sea-surface small target detection:a false-alarm-rate-controllable approach[J]. IEEE Geoscience and Remote Sensing Letters, 2019,16(8): 1225-1229.
[25]	ZHANG L , LI Y , WANG Y H ,et al. Polarimetric HRRP recognition based on ConvLSTM with self-attention[J]. IEEE Sensors Journal, 2021,21(6): 7884-7898.
[26]	LIANG Z N , GAI J Y , CHEN X L ,et al. A method for threshold setting and false alarm probability evaluation for radar detectors[J]. Signal Processing, 2023(207).
[27]	CHEN X L , GAI J Y , LIANG Z N ,et al. Adaptive double threshold detection method for range-spread targets[J]. IEEE Signal Processing Letters, 2022(29): 254-258.
[28]	GERLACH K , STEINER M , LIN F . Detection of a spatially distributed target in white noise[J]. IEEE Signal Processing Letters, 1997(4): 198-200.

参数名称	参数值
雷达波段	W
距离分辨率	0.1 m
极化形式	HH、VH
地形	戈壁
目标种类	2类（厢货车、卡车）
方位角度	4个（迎头、前斜、正侧、尾追）
信杂比	1～20 dB，间隔1 dB
训练数据量	杂波：50 000条
测试数据量	每信杂比20 000条（每姿态5 000条）

算法名称	运行时间/s	内存占用峰值/kbit
双门限算法	67.98	2 048.00
M/N算法	63.16	1 012.00
SDD-GLRT算法	1 283.38	7 896.00
所提算法	336.39	18 176.00

一种基于极化分解特征和SVDD的扩展目标检测算法

A range spread target detection algorithm based on polarimetric features and SVDD

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 28

相关文章 0

Metrics

推荐阅读 0