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

LIU Yao-qiang; CHEN Wen-chao; SHI Li-xing; TIAN Long; WANG Peng-hui; CHEN Bo

doi:10.12263/DZXB.20250370

您当前的位置：

首页 >

文章列表页 >

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

PAPERS | 更新时间：2025-12-27

- Clutter Modeling and Radar Target Detection Method Based on Deep Unsupervised Variational Networks
- ACTA ELECTRONICA SINICA Vol. 53, Issue 8, Pages: 2691-2706(2025)
- 作者机构：
  
  1.西安电子科技大学雷达信号处理全国重点实验室，陕西西安 710071
  2.西安电子科技大学电子工程学院，陕西西安 710071
  3.西安电子科技大学计算机科学与技术学院，陕西西安 710071
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(6220010437;U21B2006);National Key Laboratory of Radar Signal Processing Fund(JKW202X0X;KGJ202401)
- DOI：10.12263/DZXB.20250370
  CLC： TN957.51;
- Received：10 May 2025，
  
  Accepted：16 August 2025，
  
  Published：25 August 2025
- 稿件说明：
移动端阅览
刘要强, 陈文超, 施力行, 等. 基于深度无监督变分网络的杂波建模与雷达目标检测方法[J]. 电子学报, 2025, 53(08): 2691-2706.

LIU Yao-qiang, CHEN Wen-chao, SHI Li-xing, et al. Clutter Modeling and Radar Target Detection Method Based on Deep Unsupervised Variational Networks[J]. Acta Electronica Sinica, 2025, 53(08): 2691-2706.
刘要强, 陈文超, 施力行, 等. 基于深度无监督变分网络的杂波建模与雷达目标检测方法[J]. 电子学报, 2025, 53(08): 2691-2706. DOI：10.12263/DZXB.20250370

LIU Yao-qiang, CHEN Wen-chao, SHI Li-xing, et al. Clutter Modeling and Radar Target Detection Method Based on Deep Unsupervised Variational Networks[J]. Acta Electronica Sinica, 2025, 53(08): 2691-2706. DOI：10.12263/DZXB.20250370

摘要

现代雷达目标检测往往面临复杂多变的杂波环境，传统的基于模型驱动的恒虚警率（Constant False Alarm Rate，CFAR）检测器容易出现模型失配的问题，现有的基于数据驱动的有监督深度学习方法存在烦琐且昂贵的标签问题.针对上述问题，本文提出了一种基于深度无监督变分网络的杂波建模方法，该方法利用面向雷达回波高维分布特征学习的变分自编码器（Variational Auto-Encoder，VAE），针对雷达回波处理后的距离-多普勒谱，实现对复杂杂波分布的重构建模.首先，在VAE的无监督推理-生成构架中引入卷积神经网络（Convolutional Neural Network，CNN）和循环神经网络（Recurrent Neural Network，RNN），分别利用CNN网络的局部特征捕捉能力和RNN网络的时序相关性信息提取能力来实现对距离-多普勒谱的重构建模.其次，为了充分地捕获距离-多普勒谱中不同区域的杂波分布特征及二维时空信息，本文提出了一种基于时空变分Transformer的杂波建模方法，该方法将Transformer架构引入到所提的深度无监督杂波建模的变分网络中，借助Transformer网络的自注意力机制来捕获R-D谱数据的全局相关性.再次，为了充分挖掘不同场景下R-D谱的杂波分布特征及保留原始数据的二维时空信息，设计了开关机制和二维位置编码机制以匹配Transformer网络架构.最后，结合分布外（Out-Of-Distribution，OOD）检测策略，本文提出了一种基于深度无监督变分网络的杂波建模与雷达目标检测方法，重构似然表示无监督变分网络准确重构出输入样本的难易程度.重构似然越大，重构样本与输入样本越相似.因此，本文利用重构似然定义OOD分数，作为划分目标与杂波的依据，实现雷达目标检测任务.通过仿真数据验证，本文所提的无监督杂波建模方法能够实现对雷达距离-多普勒谱杂波分布的精细重构，且相比传统CFAR方法，当达到80%检测概率时，本文提出的方法所需信杂噪比（Signal to Clutter plus Noise Ratio，SCNR）优化了5.6 dB.

Abstract

Modern radar target detection often faces complex and changeable clutter environments. Traditional model-driven constant false alarm rate (CFAR) detectors are prone to model mismatch problems

and existing data-driven supervised deep learning methods require cumbersome and expensive label problems. In response to the above problems

this paper proposes a clutter modeling method based on deep unsupervised variational networks. This method utilizes a variational autoencoder for learning the high-dimensional distribution features of radar echoes to achieve the reconstruction modeling of complex clutter distributions for the range-doppler spectrum after radar echo processing. Firstly

convolutional neural network (CNN) and recurrent neural network (RNN) are introduced into the unsupervised inference-generation framework of the variational autoencoder. The reconstruction modeling of range-doppler spectra is achieved by respectively utilizing the local feature capture ability of CNN networks and the temporal correlation information extraction ability of RNN networks. To fully capture the clutter distribution characteristics and two-dimensional spatiotemporal information in different regions of the range-doppler spectrum

this paper proposes a clutter modeling method based on spatiotemporal variational Transformer. This method introduces the Transformer architecture into the proposed deep unsupervised clutter modeling variational network. Capture the global correlation of R-D spectral data by leveraging the self-attention mechanism of the Transformer network. In order to fully explore the clutter distribution characteristics of R-D spectra in different scenarios and retain the two-dimensional spatiotemporal information of the original data

a switching mechanism and a two-dimensional position encoding mechanism are designed to match the Transformer network architecture. Finally

combined with the out-of-distribution (OOD) detection strategy

this paper proposes a clutter modeling and radar target detection method based on deep unsupervised variational networks

and reconstructs the likelihood representation of the unsupervised variational network to accurately reconstruct the difficulty level of the input samples. The greater the reconstruction likelihood

the more similar the reconstructed sample is to the input sample. Therefore

the OOD score is defined by using the reconstructed likelihood as the basis for dividing the target from clutter to achieve the radar target detection task. Verified by simulation data

the unsupervised clutter modeling method proposed in this paper can achieve fine reconstruction of the clutter distribution in the radar range-Doppler spectrum. Moreover

compared with the traditional CFAR method

when the detection probability reaches 80%

the signal to clutter plus noise ratio (SCNR) required by the method proposed in this paper The SCNR is optimized by 5.6 dB.

关键词

Keywords

references

ZHANG C X , XU Y S , CHEN W C , et al . IfCMD: A novel method for radar target detection under complex clutter backgrounds [J ] . Remote Sensing , 2024 , 16 ( 12 ): 2199 .

NAVAS R E , CUPPENS F , BOULAHIA CUPPENS N , et al . MTD, where art thou? A systematic review of moving target defense techniques for IoT [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 10 ): 7818 - 7832 .

WATTS S . Cell-averaging CFAR gain in spatially correlated K-distributed clutter [J ] . IEE Proceedings - Radar, Sonar and Navigation , 1996 , 143 ( 5 ): 321 .

WEISS M . Analysis of some modified cell-averaging CFAR processors in multiple-target situations [J ] . IEEE Transactions on Aerospace and Electronic Systems , 1982 , AES-18( 1 ): 102 - 114 .

邹成晓 , 张海霞 , 程玉堃 , 等 . 雷达恒虚警技术处理方法综述 [J ] . 雷达与对抗 , 2021 , 41 ( 2 ): 29 - 35 .

ZOU C X , ZHANG H X , CHENG Y K , et al . Review of radar constant false alarm technology processing methods [J ] . Radar and Countermeasures , 2021 , 41 ( 2 ): 29 - 35 . (in Chinese)

郭辰锋 . 复杂背景目标检测技术研究 [D ] . 哈尔滨 : 哈尔滨工业大学 , 2020 .

GUO C F . Reasearch on Target Detection Technology with Complex Background [D ] . Harbin : Harbin Institute of Technology , 2020 . (in Chinese)

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 770 - 778 .

TIAN J M , WANG C X , CAO J W , et al . Fully convolutional network-based fast UAV detection in pulse Doppler radar [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 5103112 .

LE H , DOAN V S , LE D P , et al . Micro-Doppler-radar-based UAV detection using inception-residual neural network [C ] // 2020 International Conference on Advanced Technologies for Communications . Piscataway : IEEE , 2020 : 177 - 181 .

YANG Y P , YANG F , SUN L G , et al . Echoformer: Transformer architecture based on radar echo characteristics for UAV detection [J ] . IEEE Sensors Journal , 2023 , 23 ( 8 ): 8639 - 8653 .

SHI Y , DU L , GUO Y C . Unsupervised domain adaptation for SAR target detection [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2021 , 14 : 6372 - 6385 .

SHI Y , DU L , GUO Y C , et al . Optical knowledge assisted unsupervised cross-domain SAR target detection [C ] // IET International Radar Conference . London : IET , 2024 : 1474 - 1480 .

张智 , 易华挥 , 郑锦 . 聚焦小目标的航拍图像目标检测算法 [J ] . 电子学报 , 2023 , 51 ( 4 ): 944 - 955 .

ZHANG Z , YI H H , ZHENG J . Focusing on small objects detector in aerial images [J ] . Acta Electronica Sinica , 2023 , 51 ( 4 ): 944 - 955 . (in Chinese)

KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL ] . ( 2022-12-10 )[ 2025-03-10 ] . https://arXiv.org/abs/1312.6114 https://arXiv.org/abs/1312.6114 .

ZHOU Y B . Rethinking reconstruction autoencoder-based out-of-distribution detection [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 7369 - 7377 .

HE K M , CHEN X L , XIE S N , et al . Masked autoencoders are scalable vision learners [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 15979 - 15988 .

JING H , CHENG Y Q , WU H , et al . Radar target detection with multi-task learning in heterogeneous environment [J ] . IEEE Geoscience and Remote Sensing Letters , 2022 , 19 : 4021405 .

ZAREMBA W , SUTSKEVER I , VINYALS O . Recurrent neural network regularization [EB/OL ] . ( 2015-02-19 )[ 2025-03-10 ] . https://arXiv.org/abs/1409.2329 https://arXiv.org/abs/1409.2329 .

VASWANI A . Attention is all you need [J ] . Advances in Neural Information Processing Systems , 2017 , 30 : 5998 - 6008 .

DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16 x 16 words: Transformers for image recognition at scale[EB/OL ] . ( 2021-06-03 )[ 2025-03-10 ] . https://arXiv.org/abs/2010.11929 https://arXiv.org/abs/2010.11929 .

FEDUS W , ZOPH B , SHAZEER N . Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity [EB/OL ] . ( 2022-06-16 )[ 2025-03-10 ] . https://arXiv.org/abs/2101.03961 https://arXiv.org/abs/2101.03961 .

SHAZEER N , MIRHOSEINI A , MAZIARZ K , et al . Outrageously large neural networks: The sparsely-gated mixture-of-experts layer [EB/OL ] . ( 2017-01-23 )[ 2025-03-10 ] . https://arXiv.org/abs/1701.06538 https://arXiv.org/abs/1701.06538 .

LIU Z Z , ZHOU J J , WANG Y F , et al . Unsupervised out-of-distribution detection with diffusion inpainting [C ] // Proceedings of the 40th International Conference on Machine Learning . Honolulu : Proceedings of Machine Learning Research , 2023

杜勇 , 李依林 , 杨海粟 . 基于ZMNL法的相关雷达杂波建模与仿真 [J ] . 火控雷达技术 , 2012 , 41 ( 4 ): 11 - 14 .

DU Y , LI Y L , YANG H S . Modeling and simulation of ZMNL-based correlated radar clutter [J ] . Fire Control Radar Technology , 2012 , 41 ( 4 ): 11 - 14 . (in Chinese)

汪斌 . 基于概率统计模型的复杂杂波背景下雷达目标检测方法研究 [D ] . 西安 : 西安电子科技大学 , 2019 .

WANG B . Research on Radar Target Detection Method in Complex Clutter Background Based on Probabilistic Statistical Model [D ] . Xi’an : Xidian University , 2019 . (in Chinese)

刘宁 . 地杂波背景下雷达目标检测方法的研究 [D ] . 西安 : 西安电子科技大学 , 2018 .

LIU N . Research on Radar Target Detection Method Under Ground Clutter Background [D ] . Xi’an : Xidian University , 2018 . (in Chinese)

LIANG X L , CHEN B , CHEN W C , et al . Unsupervised radar target detection under complex clutter background based on mixture variational autoencoder [J ] . Remote Sensing , 2022 , 14 ( 18 ): 4449 .

BRENNAN L , MALLETT J , REED I . Adaptive arrays in airborne MTI radar [J ] . IEEE Transactions on Antennas and Propagation , 1976 , 24 ( 5 ): 607 - 615 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Information Geometry Detector Based on Joint Optimization of Feature and Metric

Power Spectrum Manifold-Based Information Geometry DP-TBD Algorithm

A Likelihood-Ratio Detection Method of Radar Target Based on Particle Filtering

Range-Spread Target CFAR Detection Under SIRV Clutter

Related Author

WANG Hong-qiang

LI Xiang

YANG Zheng

CHENG Yong-qiang

WU Hao

CHENG Yong-qiang

YANG Zheng

Related Institution

College of Electronic Science and Technology， National University of Defense Technology

Wuhan Radar Institute

Research Institute of Information Fusion,Naval Aeronautical and Astronautical University

School of Electronic and Information Engineering Sun Yat-sen University Guangzhou Guangdong China

Air Force Early Warning Academy

⁰