SAR图像的极化干涉非监督Wishart分类方法和实验研究

该文在合成孔径雷达图像的极化非监督Wishart分类的基础上,给出了一种利用极化干涉信息对合成孔径雷达图像进行非监督分类的方法。该方法主要利用一(66)的极化干涉相关矩阵,从而可以同时考虑单幅图像的全极化信息以及两幅像对之间的互相关信息。该文详细阐述了该方法的具体实现,并利用NASA/JPL的SIR-C/X-SAR系统在中国天山地区的L波段实测数据进行了实验研究。给出了利用该方法对实验数据进行分类的结果,并与极化非监督Wishart分类的结果进行了比较。结果表明,该方法能够很好地分辨不同类型的地物,保持地物的细节,并且比极化非监督Wishart分类结果有很大改善。     

基于随机蕨的极化SAR图像地物分类研究

传统极化SAR图像地物分类方法通常存在计算效率低和维度灾难等问题，受益于随机蕨分类器的简单性、鲁棒性和处理高维特征空间的能力，文中提出了一种基于随机蕨算法的极化SAR分类框架算法。随机蕨分类器中大量的二元特征捕获了极化SAR图像中地物的空间信息、纹理属性和与其相邻像素的关系。该方法能够在人工标注像素数量较少的情形下对极化SAR图像进行准确、高效的地物分类并且所需要的训练一个随机蕨分类器的时间仅需几十秒。最终的分类实验结果表明，该方法在Oberpfaffenhofen数据集上达到了较好的分类性能和运行效率。     

加权全极化SAR图像非监督Wishart分类方法

为提高基于极化目标分解与复Wishart非监督分类方法中对不同类别地物中心散射相关矩阵的估值精度与合理性,本文提出了加权全极化SAR图像非监督Wishart分类方法,该方法通过对求解每一类地物散射相关矩阵时,进行数值加权,使得求解的散射相关矩阵更能代表地物类别的中心。本文详细阐述了该方法的原理和实施步骤,并通过对AIRSAR的L波段实际数据进行分类实验,可知该加权算法无论在分类精确度上还是在迭代速度上,性能都有所提高。     

基于贝叶斯信息准则的极化干涉SAR图像非监督分类

该文提出一种利用贝叶斯信息准则自动确定聚类类别数的极化干涉SAR非监督分类算法。该方法首先利用Shannon熵特征对极化干涉SAR图像进行初始分类,然后利用期望最大化(Expectation-Maximization, EM)算法和标号代价(LabelCost)优化算法对分类结果进行迭代优化,同时通过贝叶斯信息准则(Bayesian Information Criterion, BIC)自动确定非监督分类的最佳类别数。实验结果表明该算法能够较准确地确定分类类别数,并具有较为满意的分类效果。     

基于邻域最小生成树的半监督极化SAR图像分类方法

该文针对极化SAR图像分类中只有少量标记样本的问题,提出了一种基于邻域最小生成树的半监督极化SAR图像分类方法。该方法针对极化SAR图像以像素为分类对象的特点,结合自训练方法的思想,利用极化SAR图像像素点的空间信息,提出了基于邻域最小生成树辅助学习的样本选择策略,增加自训练过程中被选择无标记样本的可靠性,扩充标记样本数量,训练更好的分类器。最终用训练好的分类器对极化SAR图像进行测试。对3组真实的极化SAR图像进行测试,实验结果表明,该方法在只有少量标记样本的情况下能获得满意的分类结果,且分类正确率明显优于传统的分类算法。      

一种联合特征值信息的全极化SAR图像监督分类方法

基于H/平面的分类器对于具有相似散射类型的地物的分类能力很差,为此该文直接使用特征值特征来进行分类。首先提取特征值特征,并使用一种自适应调整高斯分量个数的高斯混合模型对特征值分布进行较为准确地拟合,然后采用朴素贝叶斯分类器进行初步分类。针对可能存在特征值分布较为相近导致错分的问题,计算每两类地物的特征值分布的相似度,将相似度大于给定阈值的类别对组成相似性表,对于这些相似对再用基于Wishart距离的K近邻分类器进行细分。综合分析机载和星载SAR数据上的实验结果,表明这种方法能够克服基于H/的非监督分类方法对于特征值利用的一些不足,且与基于SVM的分类方法效果相当。      

双波段全极化SAR图像非监督分类方法及实验研究

该文首先采用H/分类对像素进行了初始猜测,然后进一步采用Bayes最大似然估计(ML）分类法对像素进行重新归类．不同波段电磁波对地物散射具有不同的属性,因而我们采用双波段全极化SAR数据结合的分类方法,得到了更好的分类结果．SAR图像的相干斑会影响图像的分类准确度和精度．在进行分类处理前,对双波段全极化SAR图像相干斑进行矢量滤波处理．该文使用NASA/JPL实验室在天山地区的实测数据对这些分类算法进行了实验研究．给出了单波段以及双波段全极化SAR分类结果的伪彩色图．其中双波段全极化SAR滤波后数据具有相对最优的分类结果．     

一种基于张量积扩散的非监督极化SAR图像地物分类方法

针对相似度表达的困难性以及极化SAR图像中固有的相干斑噪声问题,该文提出了一种基于张量积(TPG)扩散的非监督极化SAR图像地物分类算法。张量积扩散一般用于光学图像的分割或检索,目前研究表明,其已可用于极化SAR(PolSAR)图像地物分类。基于张量积扩散可以稳健地度量数据点之间的测地线距离,因此能够更好地挖掘数据点之间内在的相似度信息。首先,将极化SAR图像进行分割,生成许多超像素;其次,基于超像素提取7种特征并生成一个特征向量,进而利用高斯核构建相似度矩阵;再次,基于已构建的相似度矩阵,利用张量积扩散沿着数据点的内在流形结构进行相似度的传播,实现全局的相似性度量,从而获得一个具有更强判别能力的相似度矩阵;最后,基于此相似度矩阵进行谱聚类以得到地物分类结果。该文在仿真和实测极化SAR图像上均进行了大量实验,并与4种经典算法进行对比,结果表明该方法可以有效地结合空间邻域相似度信息并取得更高的分类精度。      

AdaBoost算法实现全极化SAR图像分类

文中提出了一种基于AdaBoost算法的全极化SAR(Synthetic Aperture Radar)图像分类方法.该方法将AdaBoost算法与HH、HV和VV三个极化通道数据结合起来,对全极化SAR图像进行分类,充分利用了极化信息和AdaBoost算法的快速收敛性.将该方法的仿真结果与H/α分类方法仿真结果进行比较,发现该方法分类模糊程度较低,在细节上分类更为准确,且在相同的情况下,该算法速度更快.     

基于全极化SAR非监督分类的迭代分类方法

本文在全极化合成孔径雷达(SAR)特征分解和最大似然估计(ML)分类的基础上,提出基于全极化SAR极化特征分解及最大似然估计的非监督分类迭代算法.这种方法灵活性好、精度高.本文提出了迭代分类方法的几种方案.针对特征分解和ML分类的各自特点,进行了分析比较,可以根据实际需要选择适合的迭代方法.并利用NASA JPL实验室的实测数据对该迭代分类算法进行了实验研究,得到了很好的实验结果.实验结果证明这种迭代算法有很好的适应性和很强的鲁棒性.     

Intensity-driven adaptive-neighborhood technique for polarimetric and interferometric SAR parameters estimation

In this paper, a new method to filter coherency matrices of polarimetric or interferometric data is presented. For each pixel, an adaptive neighborhood (AN) is determined by a region growing technique driven exclusively by the intensity image information. All the available intensity images of the polarimetric and interferometric terms are fused in the region growing process to ensure the validity of the stationarity assumption. Afterward, all the pixels within the obtained AN are used to yield the filtered values of the polarimetric and interferometric coherency matrices, which can be derived either by direct complex multilooking or from the locally linear minimum mean-squared error (LLMMSE) estimator. The entropy/alpha/anisotropy decomposition is then applied to the estimated polarimetric coherency matrices, and coherence optimization is performed on the estimated polarimetric and interferometric coherency matrices. Using this decomposition, unsupervised classification for land applications by an iterative algorithm based on a complex Wishart density function is also applied. The method has been tested on airborne high-resolution polarimetric interferometric synthetic aperture radar (POL-InSAR) images (Oberpfaffenhofen area-German Space Agency). For comparison purposes, the two estimation techniques (complex multilooking and LLMMSE) were tested using three different spatial supports: a fix-sized symmetric neighborhood (boxcar filter), directional nonsymmetric windows, and the proposed AN. Subjective and objective performance analysis, including coherence edge detection, receiver operating characteristics plots, and bias reduction tables, recommends the proposed algorithm as an effective POL-InSAR postprocessing technique.     

极化SAR图像分割方法研究

极化SAR图像分割是面向对象的极化SAR图像分析处理的重要组成部分,也是极化SAR图像处理的关键和难题。然而,目前还没有一种极化SAR分割方法被广泛接受。文章通过对现有的极化SAR图像分割方法进行综述,以使各位研究者对其有一个较全面的认识。文章首先介绍了国内外在极化SAR图像分割方面的主要研究机构;然后对现有的极化SAR图像分割算法进行了分类,并归纳了不同方法的基本思想,分析了各自的性能特点;最后对极化SAR图像分割方法的研究现状及发展趋势进行了总结和展望。     

一种改进的极化SAR图像四成分分解方法

目标分解是极化合成孔径雷达（SAR）应用的重要基础,其中四成分分解算法在对城市等复杂地物的分析中有很好的应用。原四成分分解得到的体散射分量通常较大,这是由于所应用的体散射模型不能完全描述实际复杂地物的随机散射过程造成的。为了更好分析地物的实际物理散射特性,结合新的体散射模型,提出了一种改进的全极化SAR图像四成分分解算法。对目标散射相干矩阵进行定向角旋转,利用新的体散射模型对目标矩阵进行分解,在分解过程中加入功率限制以防止分解中负功率的出现。最后对NASA/JPL实验室AIRSAR-L波段的旧金山数据,以及ALOS/PALSAR的北京地区极化数据进行了分析,实验结果验证了该方法的有效性。     

一种极化SAR图像T型港口识别方法

针对T型港口特有的几何结构特征, 提出了一种极化合成孔径雷达(Synthetic Aperture Radar, SAR)图像T型港口识别方法.该方法利用基于区域统计特性的极化SAR数据水平集分割方法实现精确的海岸线提取.在此基础上通过曲线分裂归并算法提取岸线特征点, 并利用T型港口始末特征点的近距离特性实现感兴趣区域提取.然后采用基于链码的直线判断方法提取港口轮廓线段, 并通过判断轮廓平行直线和垂线特征实现T型港口的识别.使用伯克利地区TerraSAR极化SAR数据进行实验验证, 结果表明了提出算法的有效性, 能在大场景范围内正确识别出沿岸T型港口.     

A three-component scattering model for polarimetric SAR data

An approach has been developed that involves the fit of a combination of three simple scattering mechanisms to polarimetric SAR observations. The mechanisms are canopy scatter from a cloud of randomly oriented dipoles, evenor double-bounce scatter from a pair of orthogonal surfaces with different dielectric constants and Bragg scatter from a moderately rough surface. This composite scattering model is used to describe the polarimetric backscatter from naturally occurring scatterers. The model is shown to describe the behavior of polarimetric backscatter from tropical rain forests quite well by applying it to data from NASA/Jet Propulsion Laboratory's (JPLs) airborne polarimetric synthetic aperture radar (AIRSAR) system. The model fit allows clear discrimination between flooded and nonflooded forest and between forested and deforested areas, for example. The model is also shown to be usable as a predictive tool to estimate the effects of forest inundation and disturbance on the fully polarimetric radar signature. An advantage of this model fit approach is that the scattering contributions from the three basic scattering mechanisms can be estimated for clusters of pixels in polarimetric SAR images. Furthermore, it is shown that the contributions of the three scattering mechanisms to the HH, HV, and VV backscatter can be calculated from the model fit. Finally, this model fit approach is justified as a simplification of more complicated scattering models, which require many inputs to solve the forward scattering problem     

A time-domain raw signal Simulator for interferometric SAR

In this paper, we present a time-domain (TD) raw signal simulator for an interferometric synthetic aperture radar (SAR). We consider the case of a spaceborne SAR operating in stripmap, spotlight, and hybrid modes, but the case of an airborne SAR can be considered as well. The spaceborne platform is considered as traveling on its nominal (Keplerian) orbit, and the targets are located on an ellipsoidal earth. We describe an accurate TD simulator, highlighting its usefulness in studying the effects on the SAR impulse response and on images from targets with limited extension due to operational conditions different from the nominal one.     

A Gaussian adaptive resonance theory neural network classificationalgorithm applied to supervised land cover mapping using multitemporalvegetation index data

Neural network classifiers have been shown to provide supervised classification results that significantly improve on traditional classification algorithms such as the Bayesian (maximum likelihood [ML]) classifier. While the predominant neural network architecture has been the feedforward multilayer perceptron known as backpropagation. Adaptive resonance theory (ART) neural networks offer advantages to the classification of optical remote sensing data for vegetation and land cover mapping. A significant advantage is that it does not require prior specification of the neural net structure, creating as many internal nodes as are needed to represent the calibration (training) data. The Gaussian ARTMAP classification algorithm bases the probability that input training samples belong to specific classes on the parameters of its Gaussian distributions: the means, standard deviations, and a priori probabilities. The performance of the Gaussian ARTMAP classification algorithm in terms of classification accuracy using independent validation data indicated was over 70% accurate when applied to an annual series of monthly 1-km advanced very high resolution radiometer (AVHRR) satellite normalized difference vegetation index (NDVI) data. The accuracies were comparable to those of fuzzy ARTMAP and a univariate decision tree, and significantly higher than a Bayesian classification algorithm. Algorithm testing is based on calibration and validation data developed and applied to Central America to map the International Geosphere-Biosphere Programme (IGBP) land cover classification system     

A Bayesian filtering technique for SAR interferometric phase fields

SAR interferograms are affected by a strong noise component which often prevents correct phase unwrapping and always impairs the phase reconstruction accuracy. To obtain satisfactory performance, most filtering techniques exploit prior information by means of ad hoc, empirical strategies. In this paper, we recast phase filtering as a Bayesian estimation problem in which the image prior is modeled as a suitable Markov random field, and the filtered phase field is the configuration with maximum a posteriori probability. Assuming the image to be residue free and generally smooth, a two-component MRF model is adopted, where the first component penalizes residues, while the second one penalizes discontinuities. Constrained aimulated annealing is then used to find the optimal solution. The experimental analysis shows that, by gradually adjusting the MRF parameters, the algorithm filters out most of the high-frequency noise and, in the limit, eliminates all residues, allowing for a trivial phase unwrapping. Given a limited processing time, the algorithm is still able to eliminate most residues, paving the way for the successful use of any subsequent phase unwrapping technique.     

A new scattering mechanism enhancement scheme for polarimetric SAR images

A new scattering mechanism enhancement scheme has been developed for natural (distributed) targets based on the eigenvalues and corresponding eigenvectors of the covariance matrix in order to identify different scattering events. First, three new vectors (v/sub 1/, v/sub 2/, and v/sub 3/) were constructed from the eigenvectors of the covariance matrix with some modifications. Then, those modified vectors were weighted by the eigenvalues of the covariance matrix as a weighting function. Thus, three vertices (A, B, and C) could be obtained in the three-dimensional space. In order to utilize them equally, a triangle (/spl Delta/ABC) was constructed by connecting these three vertices. The shape of the triangle may be changed due to the different scattering mechanisms because the vertices are obtained from the combination of eigenvalues and eigenvectors. The result indicated that different scattering mechanisms can be represented by using an exterior angle derived from the interior angles of the triangle. Results obtained from the newly developed scattering enhancement scheme, when compared with the results derived from existing schemes, were in agreement in terms of the dominant scattering mechanisms, including surface scattering, double-bounce scattering, and volume scattering. The experimental results with the Spaceborne Imaging Radar version C (SIR-C) L-band full polarimetric data demonstrate the effectiveness of the new scattering enhancement scheme.     

A phase signature for detecting wet subsurface structures using polarimetric L-band SAR

In this paper, we investigate the ability of L-band synthetic aperture radar (SAR) systems to penetrate soils to retrieve information about subsurface wet structures. Our experiment site, the Pyla dune, is a bare sandy area allowing high radar penetration and known to have large wet subsurface structures (paleosoils) at varying depths. Buried paleosoils, which act as moisture tanks, are detectable with radar, since they present a high permittivity due to their water content. By analyzing airborne polarimetric SAR data, we established that a phase signature is correlated to the buried wet palesoils: a phase difference of 23/spl deg/ between the horizontal (HH) and vertical (VV) channels was clearly observed. It allows detection of the paleosoil down to a larger depth (5.2 m) than when only considering HH and HV amplitude signals (3.5 m). In order to confirm this result, field measurements were performed that led to the same observed phase difference. We could fit our observations to the semiempirical model proposed by Oh and Sarabandi, and we reproduced the observed phenomenon using a two-layer integral equation method (IEM) model of the Pyla dune, which was completed by finite-difference time-domain (FDTD) numerical simulations. We show that the soil moisture significantly influences the radar response in terms of phase difference between the copolarized modes. Our study also shows that the single-scattering IEM model reproduces the observed phase difference fairly well for a natural outdoor site when combined to FDTD simulation results. This phase signature could be used as a new tool to map subsurface moisture in arid regions.