A new approach to dual-band polarimetric radar remote sensing image classification

1 Introduction Comparing with a traditional synthetic aperture radar (SAR), a polarimetric SAR is able to provide target scattering characteristics in the polarimetric domain, so more in- formation is available for applications of radar remote sensing such as target detection, scattering behavior analysis and classification, etc.; a dual-band polarimetric SAR even provides frequency domain information for remote sensing applications, which achieves better result than a single band polarimet…     

基于Krogager分解和SVM的极化SAR图像分类

目标分解包括基于Sinclair矩阵的相干目标分解和基于Mueller矩阵的部分相干目标分解,Krogager分解即属于相干目标分解,它可以将任一对称Sinclair矩阵分解为球散射体、二面角散射体和螺旋体3个分量,这是极化合成孔径雷达(Synthetic Aperture Radar,SAR)图像特征提取的有效途径。把3个分量的分解系数作为极化散射特征,由其组成样本向量,运用基于统计学习理论的支持向量机(Support Vector Machines,SVM)设计多类分类器,提出了一种极化SAR图像分类算法,并对实测极化SAR数据进行分类实验。结果表明,将Krogager分解和SVM分类器结合起来,对极化SAR图像进行分类是可行和有效的,并且选择不同的参数得到的分类结果差别很大,验证了参数选择在SVM分类器中的重要作用。     

基于Cameron分解和SVM的极化SAR图像分类

Cameron分解先将极化散射矩阵分解为互易分量和非互易分量,再将互易分量进一步分解为对称分量和非对称分量,这是极化合成孔径雷达图像特征提取的有效途径。由四个分量的范数组成样本向量,运用基于统计学习理论的支持向量机设计分类器,提出了一种极化SAR图像分类算法,并对实测极化SAR数据进行分类实验。结果表明,将Cameron分解与SVM结合起来应用于极化SAR图像分类的算法是可行和有效的,通过选择不同的参数对分类结果影响很大,验证了参数选择在SVM分类器中的重要作用。     

基于低秩表示的非负张量分解算法

为了提高图像分类准确率,提出了一种基于低秩表示的非负张量分解算法。作为压缩感知理论的推广和发展,低秩表示将矩阵的秩作为一种稀疏测度,由于矩阵的秩反映了矩阵的固有特性,所以低秩表示能有效的分析和处理矩阵数据,本文把低秩表示引入到张量模型中,即引入到非负张量分解算法中,进一步扩展非负张量分解算法。实验结果表明,本文所提算法与其他相关算法相比,分类结果较好。     

Anisotropic analysis of polarimetric scattering and case studies with UAVSAR images

This article analyses the anisotropy of polarimetric scattering changing with azimuth incidence angle using a multi-look processed synthetic aperture radar (SAR) image. First, three canonical scattering models were developed to simulate the migration tracks on the Cameron polarimetric space. The migration tracks indicate that these polarimetric parameters have anisotropic property. Second, unmanned aerial vehicle synthetic aperture radar (UAVSAR) data are used to validate the simulated results. The Cameron scattering-type parameter z and the orientation angle calculated by SAR data are consistent with the simulated results by small perturbation method (SPM) double-scattering. Finally, based on the anisotropic analysis, a new method of extracting polarimetric information is proposed. Using this method, six parameters were obtained and two additional parameters, Purity and Stability, were derived. These parameters contain specific physical meaning and are useful in the recognition of the scattering mechanism. Purity can be used to recognize the simple structure scatterers with zero orientation. Stability has the potential to describe the dynamic property of scatterers.     

结合编码-解码网络和条件随机场的全极化合成孔径雷达土地覆盖分类

针对多极化合成孔径雷达影像地物分类特征表征性较弱及全卷积网络分类精度较低的问题,文中提出结合编码-解码网络(E-D-Net)和条件随机场(CRF)的全极化合成孔径雷达(SAR)土地覆盖分类算法.首先,利用Freeman分解和Pauli分解建模全极化SAR影像,提取各分解对应的散射特征.再借鉴语义分割网络模型的建模思想和多尺度卷积单元构建对称网络模型,将多尺度非对称卷积单元嵌入中层,设计E-D-Net网络模型.通过E-D-Net网络模型对PolSAR影像Freeman分解散射特征进行多层自主学习,获得初始分类结果.最后,利用全连接CRF结合Pauli相干分解伪彩色图信息,对初始分类结果再进行降噪和平滑优化,得到最终分类结果.在两地区PolSAR影像上的实验验证文中算法的有效性和可行性.     

基于高斯混合模型的分量对称正定矩阵模型

高斯混合模型(GMM)可以利用多个高斯分量捕捉图像集的变化信息,是一种良好的图像集描述方法.结合分量对称正定矩阵表示方法(CSPD),文中提出基于GMM的CSPD模型(G-CSPD).模型将图像集分成大小相同的子图像集,使用GMM描述每个子图像集,最终得到一个G-CSPD矩阵,该矩阵中元素描述子图像集之间相似性.在3个图像集上的实验表明,G-CSPD是具有鉴别性的图像集描述方法.     

一种多结构及文本融合的网络表征方法

网络表征通过对网络结构的深度学习得到节点的矢量表征,挖掘网络中潜在的信息,是社会计算中的一种重要降维方法。针对一种融合了网络中的文本和结构的、基于矩阵分解的网络表征方法TADW,首先分析并讨论了文本属性矩阵在矩阵分解式中的位置对网络表征效果的影响,并对此方法进行了优化;在此基础上,提出了一种融合关系结构、交互结构和文本属性的社交网络表征方法。在多个数据集上的实验结果表明,该方法在多分类任务中优于其他经典网络表征方法。     

A theory of tracking for a dynamic radar scatterer ensemble

The mathematical basis for tracking an ensemble of dynamically independent scatterers is presented. The scatterers need not be resolvable by the observing radar and may be arbitrarily numerous. A finite state representation is established for the ensemble by associating with it an oriented abstract object, for which input-output-state relations are derived and shown to have the response separation property. Reducibility of the derived state representation is examined. Special cases of practical importance, in which system reduction is possible, are developed in detail. An example illustrating the new tracking approach is presented, using a simulated one-dimensional scatterer ensemble.     

SAR images analysis based on polarimetric signatures

In the presented paper a new method of identification of canonical coherent scatterers in the quad-polarimetric SAR data are presented. The proposed method is based on the analysis of polarimetric signatures. The observed signatures are compared with the polarimetric signatures of four canonical objects: trihedral, dihedral and helix – right and left which represent basic scattering mechanisms: single bounce, double bounce and helix scattering. The polarimetric matrices are treated as vectors in a unitary space with a scalar product that generates the norm. A recognized object is classified to one of the four coherent classes by a Kohonen network. It is not trained in an iteration process but its weights are adjusted according to the given patterns. The network classification is supported by rules. The obtained maps of pixels that represent canonical objects are compared with a map of coherent scatterers which was obtained by using the polarimetric entropy approach. The developed method of canonical coherent scatterers identification based on the polarimetric signatures analysis allows us not only to identify precisely the canonical coherent scatterers but also to determine the type of scattering mechanism characteristic for each of them. Since the proposed method works on a single-look (non-averaged) SAR data, it does not cause any spatial nor spectral decrease of amount of information because averaging is not conducted. Moreover, the proposed method will enable us the identification of a type of scattering mechanism in the canonical coherent pixels. This is an improvement in comparison to the existing methods. The obtained results should be more precise because the full polarimetric information about the scatterers is used in the identification procedure.     

新型基于几何的3D非平稳V2V MIMO信道模型

针对具有多种通信场景和收发端快速移动的V2V通信系统,提出一种基于几何的3D V2V MIMO信道模型.该模型首次结合双球模型和半椭球体模型,分别使用双球和半椭球体模型表征动态和静止散射体;考虑到收发端的运动状态,引入时变的出发角、到达角以及路径长度用于研究V2 V信道的非平稳特性;对所提出的信道模型,推导了空间互相关、时间自相关和多普勒功率谱密度等统计特性函数,分析了不同场景和参数下的V2 V信道统计特性.结果表明,不同场景下V2 V信道各统计特性有较大差异,信道相关性与时间变化和散射体分布密切相关.仿真结果与理论值的高度拟合验证了模型的正确性,为V2 V通信链路的设计提供了理论依据,拓展了基于几何的V2 V信道建模领域的研究.     

表示学习中句子与随机游走序列等价性的一种新证明

表示学习是机器学习中通过浅层的神经网络将具有关联关系的信息映射到低维度向量空间中。词表示学习的目标是将词语与其上下文词语的关系映射到低维度的表示向量空间中,而网络表示学习的目标是将网络节点及上下文节点之间的关系映射到低维度的表示向量空间中。词向量是词表示学习的结果,而节点表示向量是网络表示学习的结果。DeepWalk通过随机游走策略获取网络节点上的游走序列作为word2vec模型中的句子,之后通过滑动窗口获取节点对输入到神经网络中进行训练,而word2vec和DeepWalk底层所采用模型和优化方法是相同的,即Skip-Gram模型和负采样优化方法,在word2vec和DeepWalk中负采样的Skip-Gram模型称为SGNS。现有研究结果表明,基于SGNS模型实现的词表示学习和网络表示学习算法均为隐式地分解目标特征矩阵。有学者提出基于单词词频服从Zipf定律和网络中节点度服从幂律分布,认为网络中的随机游走序列等同于语言模型中的句子,但是仅仅基于它们服从幂律分布的理由,来判断句子等同随机游走序列是不充分的。因此,基于SGNS隐式分解目标特征矩阵的理论和依据,设计了2个对比实验,利用奇异值分解和矩阵补全方法分别在3个公共数据集上做节点分类任务,通过实验证实了句子和随机游走序列的等同性。     

一种义项矩阵模型SMM

本文介绍了一个同时利用词语和义项来索引和检索文档的信息检索模型,称为“义项矩阵模型”SMM(Sense Matrix Model) . 利用词语和义项的关联提出了一种新的文档表示,即把文档表示成为一个term ×sense 矩阵,由此引进或建立起一些很有效用的数据分析技术,包括基于矩阵范数的文档相似度计算、文档向量和矩阵的离散余弦变换(DCT) 、多维数据正交分解(MAD) 等,并提供了一种新的、无需翻译或者模型训练集的跨语言检索和多语言文本分类的技术。另外,还讨论了对文档进行DCT的部分试验结果。     

Locality Preserving Collaborative Representation for Face Recognition

Face recognition has many applications in pattern recognition and computer vision, and many face recognition methods have been proposed. Among them, the recently proposed collaborative representation based face recognition has attracted the attention of researchers. Many variants and extensions of collaborative representation based classification (CRC) have been presented. However, most of CRC methods do not consider data locality, which is crucial for classification task. In this article, a novel collaborative representation based face recognition method, LP-CRC, is proposed, which balances data locality and collaborative representation. The proposed method incorporates a locality adaptor term into the robust collaborative representation based classification framework, leading to a novel unified objective function. The Augmented Lagrange Multiplier is used to optimize the objective function. Tests on standard benchmarks demonstrate that the proposed face recognition method is superior to existing methods and robust to noise and outliers.     

基于属性散射信息的随机梯度最小方差追踪SAR超分辨重建算法

无论军事还是民用合成孔径雷达（SAR）应用领域,对实现目标更高分辨、更精细描述的期望和需求都十分迫切。在稀疏表示框架下,构建了基于属性散射中心模型（ASC）部件级局部散射模型的SAR重建观测模型;提出一种基于信号域的散射中心属性参数空间分类策略,并联合频域外推,提出一种基于随机梯度最小方差追踪的部件级超分辨SAR重建算法。该算法最终的超分辨SAR图像由FFT获得,提高了算法效率;并且该算法实现了在重建超分辨SAR图像的同时获取高精度的目标散射中心属性级特征。仿真合成数据和电磁计算数据验证了算法的超分辨能力,并利用ASC属性的克拉美罗界对算法属性估计性能进行了评估。     

用于半监督分类的二阶近似谱图卷积模型

近年来, 基于局部一阶近似的谱图卷积方法在半监督节点分类任务上取得了明显优势, 但是在每次更新节点特征表示时, 只利用了一阶邻居节点信息而忽视了非直接邻居节点信息. 为此, 本文结合切比雪夫截断展开式及标准化的拉普拉斯矩阵, 通过推导及简化二阶近似谱图卷积模块, 提出了一种融合丰富局部结构信息的改进图卷积模型, 进一步提高了节点分类性能. 大量的实验结果表明, 本文提出的方法在不同数据集上的表现均优于现有的流行方法, 验证了模型的有效性.     

基于低秩表示与矩阵填充的人脸识别方法

基于回归分析的人脸识别方法在处理不完备数据矩阵时,先对矩阵进行填充,再使用人脸识别方法,因此会降低分类性能.为了更有效地执行关于不完备数据的识别,文中将低秩矩阵填充和低秩表示学习整合在同一个模型,提出基于低秩表示和低秩矩阵填充的人脸识别方法.通过最小化表示系数和矩阵秩交替计算样本低秩表示系数矩阵和恢复矩阵缺失项,再使用最近邻分类器实现分类.在一些公开人脸数据集上的实验表明,在训练样本矩阵元素随机缺失时,文中方法可以有效提高识别精度及降低填充误差.     

基于对象的合成孔径雷达影像极化分解方法

面向对象方法已成为全极化合成孔径雷达（SAR）影像处理的常用方法,但是极化分解仍以组成对象的像素为计算单元,针对以像素为单位的极化分解效率低的问题,提出一种面向对象的极化分解方法。通过散射相似性系数加权迭代,获得对象的极化表征矩阵并对其收敛性进行了分析,以对象极化表征矩阵的极化分解代替对象区域内所有像素的分解,提高极化特征获取效率。在此基础上,综合影像对象空间特征,并通过特征选择与支持向量机(SVM)分类进行分析和评价。通过AIRSAR Flevoland影像数据实验表明,面向对象的分解方法能够减少对象极化特征提取的时间,同时提高地物目标的分类精度。相对于监督Wishart方法,提出方法的总体精度和Kappa值分别提高了17%和20%。     

Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps

Heart sound classification, used for the automatic heart sound auscultation and cardiac monitoring, plays an important role in primary health center and home care. However, one of the most difficult problems for the task of heart sound classification is the heart sound segmentation, especially for classifying a wide range of heart sounds accompanied with murmurs and other artificial noise in the real world. In this study, we present a novel framework for heart sound classification without segmentation based on the autocorrelation feature and diffusion maps, which can provide a primary diagnosis in the primary health center and home care. In the proposed framework, the autocorrelation features are first extracted from the sub-band envelopes calculated from the sub-band coefficients of the heart signal with the discrete wavelet decomposition (DWT). Then, the autocorrelation features are fused to obtain the unified feature representation with diffusion maps. Finally, the unified feature is input into the Support Vector Machines (SVM) classifier to perform the task of heart sound classification. Moreover, the proposed framework is evaluated on two public datasets published in the PASCAL Classifying Heart Sounds Challenge. The experimental results show outstanding performance of the proposed method, compared with the baselines.