雷达目标特征提取的一种方法

针对雷达高分辨率距离像（HRRP）方位敏感性和平移敏感性的问题,在对一维距离像进行预处理的基础上,提取两个平移不变特征：中心矩和熵,并将二者形成组合特征,采用Karhunen—Loeve变换进一步进行特征压缩,运用并比较了最大最小距离判别法和SVM分类器的识别性能．实验结果表明中心矩一熵组合特征提取方法能够显著增强目标的可分性,大大提高识别率。     

适用于组合特征识别的最近邻模糊分类器

在用多种特征进行简单的串联组合识别时,不同特征具有不同的特征类型和衡量尺寸,针对串联组合特征的这种特点,提出了一种最近邻模糊分类器.该分类器首先把待识别目标的组合特征与训练模板中的组合特征样本一一进行比较,从而得到了一个特征差矩阵.提出用模糊分布函数在同类特征差之间进行处理,生成一个隶属度矩阵,然后用算术平均法对隶属度矩阵进行处理,并用最大隶属度准则来进行分类判决.识别框架表明最近邻模糊分类器对组合特征中的各种不同特征的特征类型和衡量尺寸没有一致性要求,也无需对串联组合特征矢量做任何预处理.最后,用外场实测数据进行验证,结果表明,最近邻模糊分类器能够有效地解决多种特征串联组合的雷达目标识别问题.     

基于双谱特征的超宽带雷达人体目标识别

为了在人体微多普勒特征不明显条件下识别静态人体目标及人体姿态,提出了一种结合双谱对角线起伏特性与目标强散射点分布特征进行人体目标识别的方法。首先,通过分析静态人体目标双谱,提取双谱对角线起伏特性作为分类特征,降低了双谱数据的维数,减少了双谱特征冗余。然后,结合目标强散射点分布特征从不同角度描述目标,并构造用于目标识别的特征向量。最后,用支持向量机实现目标识别。仿真和实测结果均表明,双谱对角线起伏特性与目标强散射点分布特征融合的方法可以有效识别出静态人体目标并且实现人体姿态识别。     

利用奇异值特征的激光成像雷达目标识别

随着激光技术的发展,激光成像雷达在现代战争复杂战场环境中逐渐获得了广泛的应用,目前激光成像雷达目标识别技术已成为国内外研究的热点.基于激光成像雷达的距离像,以地面军事目标为识别对象,提出了针对奇异值特征的激光成像雷达目标识别算法.利用奇异值特征表征图像具有良好的稳定性,通过分析识别率与奇异值特征数目的关系,从激光成像雷...     

雷达目标特征提取的一种方法

将小波变换和马氏距离相结合，提出了一种基于ISAR成像的雷达目标特征提取方法。对ISAR成像数据进行正交二进Symlet小波分解和门限处理，对数据进行压缩，然后计算压缩后坐标点的马氏（Mahalanobis)距离，得到目标稳定的特征向量。由实验结果看出，此向量具有在一定范围内的不变性，能够用于雷达目标识别。     

雷达目标识别的一种方法

利用目标的方位角、运动速度、俯仰角和雷达散射截面积（RCS），提出了一种雷达目标识别方法。由目标的实测数据，计算特征向量总体的均值和协方差矩辄及其逆矩阵，由距离判别法进行目标识别。识别结果表明，该方法简单、识别效果较好，具有一定的实际应用价值。     

基于判别矢量子空间的雷达目标距离剖面像识别

提出了一种基于判别矢量子空间的雷达目标距离剖面像识别方法。判别矢量子空间一方面在分析意义上是较优的,同时该子空间的维数不受目标类别数限制,从而能够提取更有效的目标分类特征,改善目标正确识别率。仿真实验结果表明：该方法识别率高于特征图像方法和正则子空间法。     

离散余弦(正弦)变换在雷达目标识别中的应用

在基于雷达高分辨距离像（HRRP）的目标识别中,平移敏感性的消除及特征维数的压缩在实际应用中有着重要意义。本文首先利用零相位表示法获取平移不变的HRRP,然后引入离散余弦变换（DCT）和离散正弦变换（DST）进行特征压缩,提取低频DCT（DST）系数作为识别特征;并利用幂变换法降低了分类器的识别性能对特征维数的敏感性。基于实测数据的试验结果验证了结论的正确性。     

D-S证据理论在雷达目标识别中的应用

为解决雷达终端目标识别问题,采用基于推理的数据融合方法。分析了Dempster-Shafer(D-S)证据理论用于多传感器数据融合的基本概念和理论,并结合最小风险准则将其应用于雷达终端目标识别的数据融合中。实验结果证明了基于融合后的识别结果较单传感器单周期的识别结果好,验证了这一方法的正确性和有效性。     

一种新的Morlet小波及其在雷达信号特征提取中的应用研究

为准确估计雷达信号的瞬时频率,文中提出了一种基于新Morlet小波原子提取信号小波脊线的方法。通过分析小波脊线原理,使用新Morlet小波原子提取雷达辐射源信号的小波脊线特征。同时,针对不同调制类型的雷达信号,根据小波分解时—频约束关系,分析了正确提取信号脊线特征的条件。仿真实验表明,与普通Morlet小波原子相比,基于改进的Morlet小波提取信号脊线特征具有较强的检测概率和抗噪性能,其方法的有效性为实验结果所证实。     

超宽带探地雷达自动目标识别研究

超宽带探地雷达由于回波信号信息丰富的特点,特征向量的选取成为了自动目标识别的关键.首先利用宽相关处理进行滤波和典型数据提取.提取纵向和横向典型数据用于目标形状识别;提取典型回波道数据进行功率谱分析用于目标材质识别,并利用RBF网络从而实现目标的自动识别.实测数据处理表明:该方法可有效的完成管状物和球状物、铝和铁的识别.     

离散贝叶斯分类算法雷达目标一维距离像识别

首先讨论了传统贝叶斯分类器设计方法的局限性,然后提出了离散贝叶斯分类算法,并推导了离散贝叶斯分类器的分类误差估算公武.用大量的实测高分辨雷达目标回波数据进行计算机模拟,离散贝叶斯分类算法获得了平均94.33%的正确识别率,分类误差估算公式估算的分类误差为5.23%.计算机模拟结果表明了该方法的有效性.     

粒子群优化的SVM在雷达目标识别中的应用

支持向量机(SVM)在雷达目标高分辨距离像(HRRP)识别中可获得较高的正确识别率和更好的泛化性能,然而其性能很大程度上取决于其参数包括核函数参数σ2和惩罚因子C的合理选择。所以利用粒子群优化算法(PSO)全局搜索能力强的优点来搜寻最优参数,并针对粒子群优化易陷入局部最优的问题,提出一种惯性权重自适应改变的改进方法。通过对雷达目标高分辨率距离像(HRRP)的识别实验发现,利用PSO优化SVM参数的方法克服了传统SVM存在的很难精确找到最优参数的缺点,识别准确率也有很大提高;同时惯性权重自适应改变的方法也有效解决了PSO优化的"早熟"问题,大大缩短参数寻优时间。     

Efficient radar target recognition using the MUSIC algorithm andinvariant features

An efficient technique is developed to recognize target type using one-dimensional range profiles. The proposed technique utilizes the Multiple Signal Classification algorithm to generate superresolved range profiles. Their central moments are calculated to provide translation-invariant and level-invariant feature vectors. Next, the computed central moments are mapped into values between zero and unity, followed by a principal component analysis to eliminate the redundancy of feature vectors. The obtained features are classified based on the Bayes classifier, which is one of the statistical classifiers. Recognition results using five different aircraft models measured at compact range are presented to assess the effectiveness of the proposed technique, and they are compared with those of the conventional range profiles obtained by inverse fast Fourier transform     

LLE-based classification algorithm for MMW radar target recognition

In this paper, a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding (LLE), to avoid the defect of traditional manifold learning algorithms, which can not deal with new sample points. The algorithm defines an error as a criterion by computing a sample’s reconstruc-tion weight using LLE. Furthermore, the existence and characteristics of low dimensional manifold in range-profile time-frequency information are explored using manifold learning algorithm, aiming at the problem of target recognition about high range resolution MilliMeter-Wave (MMW) radar. The new algo-rithm is applied to radar target recognition. The experiment results show the algorithm is efficient. Com-pared with other classification algorithms, our method improves the recognition precision and the result is not sensitive to input parameters.     

Moving target feature extraction for airborne high-range resolutionphased-array radar

We study the feature extraction of moving targets in the presence of temporally and spatially correlated ground clutter for airborne high-range resolution (HRR) phased-array radar. To avoid the range migration problems that occur in HRR radar data, we first divide the HRR range profiles into low-range resolution (LRR) segments. Since each LRR segment contains a sequence of HRR range bins, no information is lost due to the division, and hence, no loss of resolution occurs. We show how to use a vector auto-regressive (VAR) filtering technique to suppress the ground clutter, Then, a parameter estimation algorithm is proposed for target feature extraction. From the VAR-filtered data, the target Doppler frequency and the spatial signature vectors are first estimated by using a maximum likelihood (ML) method. The target phase history and direction-of-arrival (DOA) (or the array steering vector for an unknown array manifold) are then estimated from the spatial signature vectors by minimizing a weighted least squares (WLS) cost function. The target radar cross section (RCS)-related complex amplitude and range-related frequency of each target scatterer are then extracted from the estimated target phase history by using RELAX, which is a relaxation-based high-resolution feature extraction algorithm. Numerical results are provided to demonstrate the performance of the proposed algorithm     

基于图像中心矩和特征向量的目标识别方法

单独使用中心矩进行目标识别,不仅算法耗时,而且效果也不理想。针对这个问题,提出了一种基于图像中心矩和特征向量相结合的目标识别方法,该方法具备了中心矩和可见光图像特征量各自的优点,降低了特征空间维数。通过引入匹配模板特征向量之间的欧式距离,进一步降低了算法的复杂度,提高了系统识别的速度,算例仿真验证了本方法的有效性和实时性。     

A quasi-parametric algorithm for synthetic aperture radar target feature extraction and imaging with angle diversity

We present synthetic aperture radar (SAR) target feature extraction and imaging techniques with angle divesity. We first establish a flexible data model that describes each target scatterer as a two-dimensional (2D) complex sequence with arbitrary amplitude and constant phase in range and cross-range. A new algorithm, referred to as the QUasiparametric ALgorithm for target feature Extraction (QUALE), is then presented for SAR target feature extraction via data fusion through angle diversity based on the flexible data model. QUALE first estimates the model parameters, which include, for each scatterer, a 2D arbitrary real-valued amplitude sequence, a constant phase, and scatterer locations in range and cross-reange. QUALE then averages the estimated 2D real-valued amplitude sequence over range by making the assumption that the scatterer radar cross section is approximately consant. QUALE next models the so-obtained 1D sequence with a simple sinc function by assuming that the scatterer is approximately a dihedral (a trihedral is approximated as a very short dihedral) and estimates the relevant sinc function parameters by minimizing a nonlinear least-squares fitting function. Finally, the approximate 2D SAR image is reconstructed by using the estimated features. Numerical examples are given to demonstrate the perfomance of the proposed algorithm.This work was supported in part by AFRL/SNAT, Air Force Research Laboratory, Air Force Materiel Command, USAF, under grant no. F33615-99-1-1507, and the National Science Foundation Grant MIP-9457388. The U.S. Goverment is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.     

GA优化的稀疏分解在雷达目标识别中的应用

特征提取是雷达目标识别系统中很关键的环节,获得一种稳健的目标特征尤为重要。可以利用稀疏分解的方法把雷达高分辨距离像(HRRP)表示在一个超完备Gabor时频字典上,进而提取字典原子的特征参数作为特征向量进行识别;针对匹配追踪算法计算量大的问题,利用遗传算法搜索能力强收敛速度快的优点对OMP算法进行改进。通过对雷达高分辨距离像(HRRP)的识别实验表明,采用Gabor原子提取的特征参数作为特征向量对雷达目标的分类效果比较好。同时,基于GA改进的OMP算法大大降低了参数寻优的计算量。