摘要
双基合成孔径雷达(BiSAR)在实现对地面运动目标检测和成像时,需要抑制地面背景杂波。然而由于双基SAR收发分置的空间构型,会导致主瓣杂波出现严重的空时非平稳问题,从而恶化杂波抑制性能。基于稀疏恢复空时自适应处理方法(SR-STAP)虽然可以通过降低样本数量减少非平稳的影响,但是在处理过程中会出现字典离网问题,从而导致空时谱估计效果下降。并且大部分现有的典型SR-STAP方法虽然具有明确的数学关系和可解释性,但在针对复杂、多变场景时,也存在参数设置不恰当、运算复杂等问题。为解决上述一系列问题,该文提出了一种适用于双基SAR空时自适应杂波抑制处理的基于交替方向乘子法(ADMM)的复值神经网络ANM-ADMM-Net。首先,基于原子范数最小化(ANM)构建双基SAR连续空时域下杂波谱的稀疏恢复模型,克服传统离散字典模型下的离网问题;其次,采取ADMM对该双基SAR杂波谱稀疏恢复模型进行快速迭代求解;然后,根据迭代流程和数据流图进行网络化处理,将人工超参数迭代过程转换为网络可学习的ANM-ADMM-Net;再次,设置归一化均方根误差网络损失函数,并利用获取的数据集对网络模型进行训练;最后,利用训练后的ANM-ADMM-Net网络架构对双基SAR回波数据进行快速迭代处理,从而完成双基SAR杂波空时谱的精确估计和高效抑制。该文通过仿真试验和实测数据处理,表明该方法具有更好的杂波抑制性能和更加高效的运算效率。
Bistatic Synthetic Aperture Radar(BiSAR)needs to suppress ground background clutter when detecting and imaging ground moving targets.However,due to the spatial configuration of BiSAR,the clutter poses a serious space-time nonstationary problem,which deteriorates the clutter suppression performance Although Space-Time Adaptive Processing based on Sparse Recovery(SR-STAP)can reduce the nonstationary problem by reducing the number of samples,the off-grid dictionary problem will occur during processing,resulting in a decrease in the space-time spectrum estimation effect.Although most of the typical SR-STAP methods have clear mathematical relations and interpretability,they also have some problems,such as improper parameter setting and complicated operation in complex and changeable scenes.To solve the aforementioned problems,a complex neural network based on the Alternating Direction Method of Multiplier(ADMM),is proposed for BiSAR space-time adaptive clutter suppression.First,a sparse recovery model of the continuous clutter space-time domain of BiSAR is constructed based on the Atomic Norm Minimization(ANM)to overcome the off-grid problem associated with the traditional discrete dictionary model.Second,ADMM is used to rapidly and iteratively solve the BiSAR clutter spectral sparse recovery model.Third according to the iterative and data flow diagrams,the artificial hyperparameter iterative process is transformed into ANM-ADMM-Net.Then,the normalized root-mean-square-error network loss function is set up and the network model is trained with the obtained data set.Finally,the trained ANM-ADMM-Net architecture is used to quickly process BiSAR echo data,and the space-time spectrum of BiSAR clutter is accurately estimated and efficiently restrained.The effectiveness of this approach is validated through simulations and airborne BiSAR clutter suppression experiments.
作者
李中余
皮浩卓
李俊奥
杨青
武俊杰
杨建宇
LI Zhongyu;PI Haozhuo;LI Jun’ao;YANG Qing;WU Junjie;YANG Jianyu(School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China)
出处
《雷达学报(中英文)》
北大核心
2025年第5期1196-1214,共19页
Journal of Radars
基金
国家自然科学基金(62171084)
衢州市财政资助科研项目(2022D014)。
关键词
双基合成孔径雷达(BiSAR)
稀疏恢复
空时处理
杂波抑制
复值神经网络
Bistatic Synthetic Aperture Radar(BiSAR)
Sparse recovery
Space-time processing
Clutter suppression
Complex-valued neural network
