OPTIMIZATION OF WEIGHTED HIGH-RESOLUTION RANGE PROFILE FOR RADAR TARGET RECOGNITION

For the recognition of high-resolution range profile （HRRP） in radar, the weighted HRRP can reduce the instability of range cells caused by the attitude change of targets. A novel approach is proposed to optimize the weighted HRRP. In the approach, the separability of weighted HRRPs in different targets is measured by de- signing an objective function, and the weighted coefficients are computed by using the gradient descent method, thus enhancing the influence of stable range cells. Simulation results based on five aircraft models show that the approach can effectively optimize the weighted HRRP and improve the recognition accuracy.

Schemes for synthesizing high-resolution range profile with extended OFDM-MIMO

Two novel schemes are proposed to synthesize high resolution range profile (HRRP) based on co-located multiple-input multiple-output (MIMO) system in the context of the joint radar and communication system. The difference between two schemes is the pattern of selecting pulses, which depends on the demand for the velocity information. The system, a type of frequency diverse array (FDA), takes full advantage of the phase-coded orthogonal frequency division multiplexing (OFDM) signal. Furthermore, the complete discrete form of the phase-coded OFDM echoes is utilized to derive the HRRP processing. The velocity estimation in the second scheme aims to eliminate velocity ambiguity, and high velocity can be retrieved exactly. Meanwhile, the imaging method is investigated with random frequency coding applied to an array. The desired performance of resolving velocity ambiguity and suppressing noise is shown by means of comparisons with previous work. The advantages in the radar imaging and the significance of the work are concluded in the end.

High resolution range profile analysis based on multicarrier phase-coded waveforms of OFDM radar

Orthogonal frequency division multiplexing（OFDM） radar with multicarrier phase-coded waveforms has been recently introduced to achieve high range resolution.The conventional method for obtaining the high resolution range profile（HRRP） is based on matched filters.A method of synthesizing HRRP based on the fast Fourier transform（FFT） and decoding is proposed.The mathematical expressions of HRRP are derived by assuming an elementary scenario of point-scattering targets.Based on the characteristic of OFDM multicarrier signals,it mainly analyzes the influence on HRRP exerted by several factors,such as velocity compensation errors,the sampling frequency offset,and so on.The conclusions are significant for the design of the OFDM imaging radar.Finally,the simulation results demonstrate the validity of the conclusions.

Length estimation of extended targets based on bistatic high resolution range profile

The approach to estimate the length of extended targets by using the bistatic high resolution range profile（ H RRP） is analyzed in this paper. The relationship between the bistatic H RRP and the monostatic H RRP of extended targets are investigated. It is demonstrated by simulations that the target length measured by the bistatic H RRP is more meaningful and accurate than that by the monostatic HRRP,though the monostatic H RRP has been well developed and widely used in target recognizing and classification. The estimation results of a cone shaped target are present and compared at the end of the paper. To assure the reliability of the simulation,the bistatic H RRP is obtained through the scattering field data calculated by a fullwave numerical method,FE-BI-MLFMA.

Multichannel noncoherent integration detection using high range resolution profile

A multichannel noncoherent integration detection method based on high range resolution profile was presented in this paper. According to the property of the moment generating function, the distribution characteristics of the noncoherent integrated signals with or without target presence were derived under the circumstance with noncorrelated Gaussian distribution noises. The loss of noncoherent integration was due to improper selection of integration range of cell numbers. A multi channel noncoherent integration detection scheme where the integration number in each channel va ries was proposed to solve this problem. The quality of this method for detection of various targets was evaluated. A comparison of fixed integration range cell number detection and multichannel inte gration detection for a high range resolution profile was presented. Simulation results indicated that the principle of the method was correct and performed well for unknown physical dimension targets. The method required little prior knowledge about target and was convenient for practical implementa tion.

THE INFLUENCE OF SPECKLE ON HIGH RESOLUTION RANGE PROFILE RECOGNITION BASED ON THE MATCHING SCORE

Template database is the key to radar automation target recognition based on High Resolution Range Profile (HRRP). From the traditional perspective, average HRRP is a valid template for it can represent each HRRP without scatterer Moving Through Range Cell (MTRC). However, template database based on this assumption is always challenged by measured data. One reason is that speckle happens in the frame without scatterer MTRC. Speckle makes HRRP fluctuate sharply and not match well with the average HRRP. We precisely introduce the formation mechanism of speckle. Then, we make an insight into the principle of matching score. Based on the conclusion, we study the properties of matching score between speckled HRRP and the average HRRP. The theoretical analysis and Monte Carlo experimental results demonstrate that speckle makes HRRP not to match well with the average HRRP according to the energy ratio of speckled scatterers. On the assumption of ideal scattering centre model, speckled HRRP has a matching score less than 85% with the average HRRP if speckled scatterers occupy more than 50% energy of the target.

基于语义引导层次化分类的雷达地面目标HRRP识别方法

高分辨距离像(HRRP)反映了目标空间散射结构在雷达视线方向的投影,近年来被认为是地面目标识别的重要途径。现有的HRRP识别方法采用手工特征加传统机器学习分类器,均属于平面分类方法,即采用统一标准不加区别的优选特征并单次决策最终类别。然而该方法在实际应用中面临种类繁杂、数据不平衡、HRRP姿态敏感性等诸多问题,难以获取最佳的应用效果。层次化方法采取分而治之思想,将一个复杂的细粒度识别任务拆解为多个简单的识别子任务。本文采用层次化识别的思路,提出了一种基于语义引导层次化分类的雷达地面目标识别方法。该方法以联合语义和数据构建的树形结构将一个复杂的细粒度识别任务拆解为多个简单的识别子任务,并针对每一个识别子任务匹配一套优选特征集和一个局部分类器。本方法在仿真数据和实测数据上完成了验证。实验结果表明了本文方法处理地面目标识别任务的有效性。

Radar group target recognition based on HRRPs and weighted mean shift clustering

When range high-resolution radar is applied to target recognition,it is quite possible for the high-resolution range profiles(HRRPs)of group targets in a beam to overlap,which reduces the target recognition performance of the radar.In this paper,we propose a group target recognition method based on a weighted mean shift(weighted-MS)clustering method.During the training phase,subtarget features are extracted based on the template database,which is established through simulation or data acquisition,and the features are fed to the support vector machine(SVM)classifier to obtain the classifier parameters.In the test phase,the weighted-MS algorithm is exploited to extract the HRRP of each subtarget.Then,the features of the subtarget HRRP are extracted and used as input in the SVM classifier to be recognized.Compared to the traditional group target recognition method,the proposed method has the advantages of requiring only a small amount of computation,setting parameters automatically,and having no requirement for target motion.The experimental results based on the measured data show that the method proposed in this paper has better recognition performance and is more robust against noise than other recognition methods.

A WEIGHTED FEATURE REDUCTION METHOD FOR POWER SPECTRA OF RADAR HRRPS

Feature reduction is a key process in pattern recognition. This paper deals with the feature reduction methods for a time-shift invariant feature, power spectrum, in Radar Automatic Target Recognition (RATR) using High-Resolution Range Profiles (HRRPs). Several existing feature reduction methods in pattern recognition are analyzed, and a weighted feature reduction method based on Fisher's Discriminant Ratio (FDR) is proposed in this paper. According to the characteristics of radar HRRP target recognition, this proposed method searches the optimal weight vector for power spectra of HRRPs by means of an iterative algorithm, and thus reduces feature dimensionality. Compared with the method of using raw power spectra and some existing feature reduction methods, the weighted feature reduction method can not only reduce feature dimensionality, but also improve recognition performance with low computation complexity. In the recognition experiments based on measured data, the proposed method is robust to different test data and achieves good recognition results.

空中目标动态HRRP特征可重构模拟方法

针对目前无源模拟技术无法实现目标动态电磁特征模拟的问题,提出了一种利用相位调制表面(phase-switched screen, PSS)进行空中目标动态高分辨距离像(high resolution range profile, HRRP)特征可重构的模拟方法。以无人直升机旋翼为例,对旋翼的运动状态进行了建模,并详细分析了其动态HRRP特征。另外,通过建立PSS的周期调制信号模型,详细分析了PSS对雷达入射波的调控效果。在此基础上,提出了一种调制频率时变的PSS可重构模拟方法,该方法能够生成随时间变化的可控谐波分量,模拟产生的谐波分量与无人直升机旋翼的动态HRRP特征变化规律相似。通过仿真数据对比分析,调制频率时变的PSS可重构模拟方法能够实现无人直升机旋翼的动态HRRP特征模拟效果。

Ship recognition based on HRRP via multi-scale sparse preserving method

In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.

基于快速密度搜索聚类算法的极化HRRP分类方法

该文针对人造目标的极化高分辨距离像,提出一种基于快速密度搜索聚类算法的分类方法。首先根据散射结构在频率和极化维度的特性,对散射中心的类型进行判别,在此基础上构造目标分类的特征矢量。然后采用快速密度搜索聚类算法,实现目标的分类。仿真实验结果表明,文中构建的特征矢量能较好地描述目标的结构属性,具有较强的可分性。而快速密度搜索聚类算法简单高效,在人造目标的分类识别中具有极大的应用潜力。

一种利用强度信息的雷达HRRP自动目标识别方法

针对雷达高分辨距离像(HRRP)的幅度敏感性,现有HRRP雷达自动目标识别(RATR)方法一般简单地能量归一化.本文借鉴切空间距离的思想,提出一种利用HRRP回波强度信息提高识别精度的方法,实测数据仿真试验证明与传统方法相比,该方法可提高识别率约5个百分点.

加权KNN分类器在HRRP库外目标拒判中的应用

针对雷达自动目标识别中的库外目标拒判问题,提出了一种人工生成库外样本的方法和一种加权k最邻近(knearest neighbors,KNN)分类器。通过人工生成库外高分辨距离像样本,解决了在训练阶段无法获取库外样本的难题。加权KNN分类器同时满足了基于问题和基于数据两大设计要求,能够很好地处理拒判问题。通过基于接收机工作特性(receiver operating characteristic,ROC)准则和基于损失函数准则的仿真实验,证明了加权KNN分类器具备优良的拒判性能。

基于H/A/α分解的全极化HRRP目标识别方法

针对现有基于H/A/α分解提取全极化高分辨率距离像(high range resolution profile,HRRP)特征的方法都没有考虑度量尺度对所提取特征性能影响的问题,提取了平均度量尺度下的特征子集,给出联合动态互信息概念用于选择最优平均度量尺度,并剔除特征子集中的冗余特征;在此基础上,结合Bagging和Boosting算法,提出一种宽带全极化雷达目标识别方法;最后在多类飞机目标HRRP样本集上验证了该方法的有效性。

一种用于雷达HRRP功率谱的加权特征压缩方法

针对雷达高分辨距离像的平移不变特征———功率谱特征,提出了一种基于F isher判决率的加权特征压缩方法.该方法利用目标功率谱特征的F isher判决率迭代搜索最优权向量,并根据最优权值的大小对特征向量降维.与直接使用原始功率谱特征及基于F isher可分性判据的几种现有的特征压缩方法相比,加权特征压缩方法在降维的同时可提高识别性能,且运算简单,在基于外场实测数据的识别实验中对测试数据具有良好的稳健性.

基于极化分集接收的HRRP欺骗干扰鉴别

有源宽带欺骗干扰能够生成虚假高分辨距离像(high resolution range profile,HRRP),严重影响成像雷达的目标特征提取与识别。为此,研究了基于极化分集接收的HRRP欺骗干扰鉴别方法。首先,建立了目标回波和欺骗干扰的正交极化宽带响应模型,分析了两者的极化相关特性差异;然后,利用正交极化HRRP之间的互相关系数作为鉴别量,提出了相应的鉴别算法;最后,利用飞机缩比模型及干扰机天线的暗室测量数据进行仿真实验。实验结果表明:在一定信噪比(signal-to-noise ratio,SNR)及鉴别门限条件下,正确鉴别概率将大于90%,验证了算法的有效性。

HRRP稀疏自编码器深层特征与散射中心特征的关联性研究

利用稀疏自编码器网络对典型目标一维高分辨距离像(high resolution range profile,HRRP)进行了学习训练,基于各层权重系数矩阵定义了一种综合权重系数,通过综合权重系数和降维特征与散射中心特征的对比分析,发现稀疏自编码器深层特征与散射中心特征之间具有一定的关联性,并对综合权重系数和深层降维特征的物理意义进行了解释。首先针对HRRP构建稀疏自编码器网络,经过深层学习后获取训练后的权重系数和降维后的特征,并与散射中心的位置特征和强度分布特征进行关联性分析。结果表明,综合权重系数矩阵为与散射中心密切相关的类字典系数矩阵,反映了距离域强散射中心位置随角度变化的可能的分子集;降维特征能够实现对强散射中心的学习和提取,反映了强散射中心位置和强度随角度的变化。最后分析了网络训练层数和降维维数对学习训练结果的影响,可指导后续网络参数的选择。文章首次针对雷达HRRP数据开展深度学习特征的可解释性研究,为后续深度学习在雷达数据处理中的广泛应用提供了有益的导引。

基于熵的自适应加权投票HRRP融合识别方法

基于不同分类器对同一样本分类能力不同,同一分类器对不同样本可分程度不同的思想,为不同样本赋予不同融合权重,提出了一种基于熵的自适应加权投票高分辨距离像(high range resolution profile,HRRP)融合识别方法。该方法将二分类相关向量机(relevance vector machine,RVM)扩展为多类分类RVM概率模型,并对不同HRRP特征样本进行分类,利用每个多类分类RVM输出的样本后验概率信息计算出的熵值自适应为各个样本赋予权重,使得不同分类器以及同一分类器对不同样本的决策占有不同的比重,熵值越大的样本赋予的融合权重越低,最后通过加权投票方法实现融合识别,得到目标的最终识别结果。仿真实验结果验证了所提方法的有效性。

一种新的雷达HRRP自适应划分角域建模方法

基于雷达方位渐变高分辨距离像(HRRP)的连续性,提出了一种自适应递归划分角域的建模方法,利用自适应高斯分类器和高斯过程分类器,从雷达数据中提取连续HRRP序列中包含的非线性结构信息;提出了一种判定角域边界的准则,递归地对雷达数据自适应划分角域.实测数据仿真试验证明了该方法优于传统的等间隔划分角域建模法.