Information Geometry Detector Based on Joint Optimization of Feature and Metric

WU Hao; CHENG Yong-qiang; YANG Zheng; WANG Hong-qiang; LI Xiang

doi:10.12263/DZXB.20221340

您当前的位置：

首页 >

文章列表页 >

Information Geometry Detector Based on Joint Optimization of Feature and Metric

PAPERS | 更新时间：2025-12-11

- Information Geometry Detector Based on Joint Optimization of Feature and Metric
- ACTA ELECTRONICA SINICA Vol. 52, Issue 6, Pages: 1977-1988(2024)
- 作者机构：
  
  国防科技大学电子科学学院，湖南长沙 410079
- 作者简介：
- 基金信息：
  
  Distinguished Youth Science Foundation of Hunan Province(2022JJ0063);National Natural Science Foundation of China(61921001);Key Research and Development Program of China(2022YFB3902400)
- DOI：10.12263/DZXB.20221340
  CLC： TN957.51;
- Received：23 November 2022，
  
  Revised：2023-10-22，
  
  Published：25 June 2024
- 稿件说明：
移动端阅览
吴昊,程永强,杨政,等.特征与度量联合优化信息几何检测器[J].电子学报,2024,52(06):1977-1988.

WU Hao, CHENG Yong-qiang, YANG Zheng, et al.Information Geometry Detector Based on Joint Optimization of Feature and Metric[J].Acta Electronica Sinica, 2024, 52(06): 1977-1988.
吴昊,程永强,杨政,等.特征与度量联合优化信息几何检测器[J].电子学报,2024,52(06):1977-1988. DOI：10.12263/DZXB.20221340

WU Hao, CHENG Yong-qiang, YANG Zheng, et al.Information Geometry Detector Based on Joint Optimization of Feature and Metric[J].Acta Electronica Sinica, 2024, 52(06): 1977-1988. DOI：10.12263/DZXB.20221340

摘要

目前，信息几何检测器主要采用协方差矩阵特征模型，在矩阵流形上度量待检测单元数据与杂波数据间的差异，以区分目标与杂波，从而实现雷达目标检测.然而，在复杂杂波背景下，雷达回波信号信杂比低，杂波在其中占据主导地位.因此，含有目标回波的雷达回波信号与纯杂波具有统计相似性，该相似性使得二者在矩阵流形上较难区分，从而限制了信息几何检测器的性能优势.为突破特征表示所造成的性能增益限制，本文提出了基于特征与度量联合优化的信息几何检测器.首先设计了特征与度量可调的信息几何检测器灵活框架，并在此基础上基于纽曼-皮尔逊准则建立了特征与度量的联合优化模型，而后利用局部平坦假设与多层感知器，将联合优化模型中的决策变量参数化，并提出了双阶段优化求解方法.基于仿真数据与实测海杂波数据的实验结果表明，该方法检测性能优于现有信息几何检测器等典型目标检测方法，且在目标多普勒接近杂波谱峰时具有较大优势.

Abstract

Nowadays

information geometry detectors mostly utilized covariance matrix model and measured the difference between the sample data from the cell under test and clutter data on the matrix manifold to distinguish them for radar target detection. However

under complex clutter backgrounds

the received signal with target echoes is clutter-dominated due to the low signal-to-clutter ratio

so the similarity between them in terms of statistics leaded to the unavailable distinguishability

so the performance advantage of information geometry detector was limited. To break through this limit

this paper proposed the information geometry detector based on a joint optimization of feature and metric. Specifically

this paper first designed the flexible framework of information geometry detector with a changeable signal feature and a metric. Then

on the basis of this framework

the Neyman-Pearson criterion based joint optimization with respect to feature and metric was established. By utilizing the locally flatness hypothesis and multilayer perceptron

the decision variables in the optimization problem were parameterized

and then the two-stage algorithm for this optimization problem was deduced. Based on the simulated data and real-recorded sea clutter data

the experiments show that the superiority of the proposed method than existing information geometry detectors and typical detection methods. Moreover

the experimental results demonstrate that the proposed method possesses the great advantage in slow moving target detection when the target Doppler closes to the peak of the clutter spectrum.

关键词

Keywords

references

KELLY E J . An adaptive detection algorithm [J ] . IEEE Transactions on Aerospace and Electronic Systems , 1986 , AES-22( 2 ): 115 - 127 .

LIU W J , LIU J , HAO C P , et al . Multichannel adaptive signal detection: Basic theory and literature review [J ] . Science China Information Sciences , 2022 , 65 ( 2 ): 1 - 40 .

DE MAIO A , PALLOTTA L , LI J , et al . Loading factor estimation under affine constraints on the covariance eigenvalues with application to radar target detection [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2019 , 55 ( 3 ): 1269 - 1283 .

AUBRY A , DE MAIO A , PALLOTTA L , et al . Radar detection of distributed targets in homogeneous interference whose inverse covariance structure is defined via unitary invariant functions [J ] . IEEE Transactions on Signal Processing , 2013 , 61 ( 20 ): 4949 - 4961 .

CONTE E , LOPS M , RICCI G . Adaptive matched filter detection in spherically invariant noise [J ] . IEEE Signal Processing Letters , 1996 , 3 ( 8 ): 248 - 250 .

RONG Y , AUBRY A , DE MAIO A , et al . Adaptive radar detection in low-rank heterogeneous clutter via invariance theory [J ] . IEEE Transactions on Signal Processing , 2021 , 69 : 1492 - 1506 .

孙华飞 , 彭林玉 , 张真宁 . 信息几何及其应用 [J ] . 数学进展 , 2011 , 40 ( 3 ): 257 - 269 .

SUN H F , PENG L Y , ZHANG Z N . Information geometry and its applications [J ] . Advances in Mathematics , 2011 , 40 ( 3 ): 257 - 269 . (in Chinese)

黎湘 , 程永强 , 王宏强 , 等 . 信息几何理论与应用研究进展 [J ] . 中国科学: 信息科学 , 2013 , 43 ( 6 ): 707 - 732 .

LI X , CHENG Y Q , WANG H Q , et al . Progress in theory and applications of information geometry [J ] . Scientia Sinica (Informationis) , 2013 , 43 ( 6 ): 707 - 732 . (in Chinese)

AMARI S I . Information Geometry and Its Applications‍ [M ] . Tokyo : Springer Japan , 2016 .

程永强 . 雷达信号处理的信息理论与几何方法研究 [D ] . 长沙 : 国防科学技术大学 , 2012 .

CHENG Y Q . Information Theory and Geometric Methods of Radar Signal Processing [D ] . Changsha : National University of Defense Technology , 2012 . (in Chinese)

华小强 . 基于矩阵信息几何的雷达目标检测方法研究‍ [D ] . 长沙 : 国防科技大学 , 2018 .

HUA X Q . Research on Radar Target Detection Method Based on Matrix Information Geometry [D ] . Changsha : National University of Defense Technology , 2018 . (in Chinese)

陈茜茜 . 基于矩阵信息几何的机载雷达杂波抑制方法研究 [D ] . 长沙 : 国防科学技术大学 , 2022 .

CHEN X X . Matrix Information Geometry Based Clutter Suppression Method for Airborne Radar [D ] . Changsha : National University of Defense Technology , 2022 . (in Chinese)

CHENG Y Q , HUA X Q , WANG H Q , et al . The geometry of signal detection with applications to radar signal processing [J ] . Entropy , 2016 , 18 ( 11 ): 381 .

CHEN X X , CHENG Y Q , WU H , et al . Heterogeneous clutter suppression via affine transformation on Riemannian manifold of HPD matrices [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 1 - 13 .

WU H , CHENG Y Q , CHEN X X , et al . Geodesic normal coordinate-based manifold filtering for target detection‍ [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 1 - 15 .

YANG Z , CHENG Y Q , WU H , et al . Enhanced matrix CFAR detection with dimensionality reduction of Riemannian manifold [J ] . IEEE Signal Processing Letters , 2020 , 27 : 2084 - 2088 .

ARNAUDON M , BARBARESCO F , YANG L . Riemannian medians and means with applications to radar signal processing [J ] . IEEE Journal of Selected Topics in Signal Processing , 2013 , 7 ( 4 ): 595 - 604 .

HUA X Q , CHENG Y Q , WANG H Q , et al . Geometric means and medians with applications to target detection‍ [J ] . IET Signal Processing , 2017 , 11 ( 6 ): 711 - 720 .

HUA X Q , CHENG Y Q , WANG H Q , et al . Robust covariance estimators based on information divergences and Riemannian manifold [J ] . Entropy , 2018 , 20 ( 4 ): 219 .

HUA X Q , CHENG Y Q , WANG H Q , et al . Matrix CFAR detectors based on symmetrized Kullback-Leibler and total Kullback-Leibler divergences [J ] . Digital Signal Processing , 2017 , 69 : 106 - 116 .

华小强 , 程永强 , 王宏强 , 等 . 矩阵信息几何中值检测器‍ [J ] . 电子学报 , 2022 , 50 ( 2 ): 284 - 294 .

HUA X Q , CHENG Y Q , WANG H Q , et al . Matrix information geometric median detectors [J ] . Acta Electonica Sinica , 2022 , 50 ( 2 ): 284 - 294 . (in Chinese)

HUA X Q , ONO Y , PENG L Y , et al . Target detection within nonhomogeneous clutter via total bregman divergence-based matrix information geometry detectors [J ] . IEEE Transactions on Signal Processing , 2021 , 69 : 4326 - 4340 .

HUA X Q , PENG L Y . MIG Median detectors with manifold filter [J ] . Signal Processing , 2021 , 188 : 108176 .

ZHAO W J , LIU C , LIU W L , et al . Maximum eigenvalue-based target detection for the K-distributed clutter environment [J ] . IET Radar , Sonar & Navigation, 2018 , 12 ( 11 ): 1294 - 1306 .

ZHAO W J , LIU W L , JIN M L . Spectral norm based mean matrix estimation and its application to radar target CFAR detection [J ] . IEEE Transactions on Signal Processing , 2019 , 67 ( 22 ): 5746 - 5760 .

IOFFE S , SZEGEDY C . Batch normalization: Accelerating deep network training by reducing internal covariate shift [EB/OL ] . ( 2015-03-02 ) [ 2022-11-01 ] . https://doi.org/10.48550/arXiv.1502.03167 https://doi.org/10.48550/arXiv.1502.03167

KŮRKOVÁ V . Kolmogorov’s theorem and multilayer neural networks [J ] . Neural Networks , 1992 , 5 ( 3 ): 501 - 506 .

JARABO-AMORES M P , ROSA-ZURERA M , GIL-PITA R , et al . Study of two error functions to approximate the Neyman-Pearson detector using supervised learning machines [J ] . IEEE Transactions on Signal Processing , 2009 , 57 ( 11 ): 4175 - 4181 .

ROHMAN B P A , KURNIAWAN D , MIFTAHUSHUDUR M T . Switching CA/OS CFAR using neural network for radar target detection in non-homogeneous environment [C ] // 2015 International Electronics Symposium (IES) . Piscataway : IEEE , 2016 : 280 - 283 .

WU H , CHENG Y Q , CHEN X X , et al . Dual power spectrum manifold and toeplitz HPD manifold: Enhancement and analysis for matrix CFAR detection [EB/OL ] . ( 2022-06-24 )[ 2022-11-01 ] . https://arxiv.org/abs/2206.12060 https://arxiv.org/abs/2206.12060

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Power Spectrum Manifold-Based Information Geometry DP-TBD Algorithm

Global Dependency Guided Feature Reconstruction for Image Classification

Clutter Modeling and Radar Target Detection Method Based on Deep Unsupervised Variational Networks

Identification and Migration of Silent Security Patches in Blockchain Systems via Information Fusion

Broadband Wide-Beamwidth Phased Array System

Related Author

CHENG Yong-qiang

WANG Hong-qiang

WU Hao

CHENG Yong-qiang

YANG Zheng

LI Xiang

Wang Hong-qiang

Li Xiang

Related Institution

College of Electronic Science，National University of Defense Technology

Key Laboratory of Optoelectronic Information Control and Security Technology

School of Software, Liaoning Technical University

School of Computer Science and Technology, Xidian University

School of Electronic Engineering, Xidian University

⁰