Multi-chromatic analysis polarimetric interferometric synthetic aperture radar (MCA-PolInSAR) for urban classification

One of the problems of Synthetic Aperture Radar (SAR) polarimetric decomposition, is that oriented urban areas and vegetation signatures are decomposed into the same volume scattering mechanism. Such indetermination makes it difficult to distinguish vegetation from the oblique urban areas with respect to the radar illumination direction within the volume scattering mechanism. This event occurs because oriented targets exhibit similar polarimetric responses. This paper presents an improvement of the PolSAR decomposition scheme which permits the performing of more accurate classification. The method uses the information existing form the interference generated between two Doppler sub-aperture SAR images. This interferometric polarimetric SAR (PolInSAR) multi-chromatic analysis (MCA-PolInSAR) signal processing method permits the efficient separation of oriented buildings from vegetation yielding considerably improved results in which oriented urban areas are recognized, from volume scattering, as double-bounce objects. Results also show a considerable improvement in the robustness of classification and also in terms of definition and precision.     

基于物理散射模型的全极化SAR图像增强滤波算法

针对传统的极化SAR滤波方法图像中城镇区域和植被区域地物在滤波中易被混淆, 导致滤波后图像中地物边缘保持效果下降的问题, 提出了一种增强的保持极化散射特性的滤波算法。利用一种增强的四分量极化分解方法获取更加精确的地物散射机制, 并将散射机制信息引入滤波方法中, 使滤波算法中像素的散射机制更精确。增强的四分量极化分解方法引入了极化SAR数据的定向角补偿技术、一种新的体散射模型以及两种散射功率限制条件, 来改进Freeman-Durden分解的结果。理论分析和实验结果表明, 改进后的方法获取了比传统的极化SAR图像滤波算法更加理想的计算结果。     

A novel algorithm for land use and land cover classification using RADARSAT-2 polarimetric SAR data

This study proposes a new four-component algorithm for land use and land cover (LULC) classification using RADARSAT-2 polarimetric SAR (PolSAR) data. These four components are polarimetric decomposition, PolSAR interferometry, object-oriented image analysis, and decision tree algorithms. First, polarimetric decomposition can be used to support the classification of PolSAR data. It is aimed at extracting polarimetric parameters related to the physical scattering mechanisms of the observed objects. Second, PolSAR interferometry is used to extract polarimetric interferometric information to support LULC classification. Third, the main purposes of object-oriented image analysis are delineating image objects, as well as extracting various textural and spatial features from image objects to improve classification accuracy. Finally, a decision tree algorithm provides an efficient way to select features and implement classification. A comparison between the proposed method and the Wishart supervised classification which is based on the coherency matrix was made to test the performance of the proposed method. The overall accuracy of the proposed method was 86.64%, whereas that of the Wishart supervised classification was 69.66%. The kappa value of the proposed method was 0.84, much higher than that of the Wishart supervised classification, which exhibited a kappa value of 0.65. The results indicate that the proposed method exhibits much better performance than the Wishart supervised classification for LULC classification. Further investigation was carried out on the respective contribution of the four components to LULC classification using RADARSAT-2 PolSAR data, and it indicates that all the four components have important contribution to the classification. Polarimetric information has significant implications for identifying different vegetation types and distinguishing between vegetation and urban/built-up. The polarimetric interferometric information extracted from repeat-pass RADARSAT-2 images is important in reducing the confusion between urban/built-up and vegetation and that between barren/sparsely vegetated land and vegetation. Object-oriented image analysis is very helpful in reducing the effect of speckle in PolSAR images by implementing classification based on image objects, and the textural information extracted from image objects is helpful in distinguishing between water and lawn. The decision tree algorithm can achieve higher classification accuracy than the nearest neighbor classification implemented using Definiens Developer 7.0, and the accuracy of the decision tree algorithm is similar with that of the support vector classification which is implemented based on the features selected using genetic algorithms. Compared with the nearest neighbor and support vector classification, the decision tree algorithm is more efficient to select features and implement classification. Furthermore, the decision tree algorithm can provide clear classification rules that can be easily interpreted based on the physical meaning of the features used in the classification. This can provide physical insight for LULC classification using PolSAR data.     

高阶条件随机场引导的多分支极化SAR图像分类

目的 针对极化合成孔径雷达（polarimetric synthetic aperture radar,PolSAR）小样本分类问题,基于充分挖掘有限样本的极化、空间特征考虑,提出一种由高阶条件随机场（conditional random field,CRF）引导的多分支分类网络模型。方法 利用Yamaguchi非相干目标分解方法,构建每个像素的极化特征向量。设计了由高阶CRF能量函数引导的多卷积分支特征提取网络,将像素点极化特征向量作为输入,分别提取像素点的像素特征、邻域特征和位置特征信息。将以上特征进行加和融合,并输入到softmax分类器中得到预分类结果。利用超像素方法对预分类结果图进行进一步修正和调优,平滑相邻像素之间的特异性和相似性。结果 采用1%的采样率对两组真实的极化SAR数据进行测试。同时,为了更好地模拟实际应用中训练样本位置分布不均匀的情况,考虑了空间不相交采样方法作为对比实验。综合两种采样策略的实验结果表明,相较于只利用像素级特征或简单利用空间特征的方法,本文方法总分类精度平均提升7%～10%,不同地物类别的分类精准度均在90%以上,运行速度相比于支持向量机（support vector machine,SVM）提高了2.5倍以上。结论 通过构建高阶CRF引导的卷积神经网络,将像素特征信息、同质区域特征和地理位置信息进行融合,有效建立了像素级和对象级数据之间的尺度关联,进一步扩充了像素点之间的空间依赖性,提取到了更强大更准确的表征特征,显著提高了标记样本数量较少情况下的卷积网络模型的分类性能,进一步保证了地物目标散射机制表征的全面性和可靠性。     

基于目标相干散射特性的极化SAR图像分解分类方法

基于对目标极化相干散射特性的分析,我们改进了Cloude和Lee等人提出的极化特征分解及非监督分类算法,以适应高分辨率极化SAR图像中复杂的地物细节特征。实验结果表明,相对传统方法,该方法更能够保留目标的细节特征、准确地估计目标极化相干矩阵,因此能够获得更好的分解分类结果。另外,该方法还具有较好的收敛性和鲁棒性。     

Analysis of the applicability of multi-temporal full polarimetric airborne L-band SAR scattering to paddy rice field mapping

ABSTRACT

A Synthetic Aperture Radar (SAR) is an all-weather imaging system that is often used for mapping paddy rice fields and estimating the area. Fully polarimetric SAR is used to detect the microwave scattering property. In this study, a simple threshold analysis of fully polarimetric L-band SAR data was conducted to distinguish paddy rice fields from soybean and other fields. We analysed a set of ten airborne SAR L-band 2 (Pi-SAR-L2) images obtained during the paddy rice growing season (in June, August, and September) from 2012 to 2014 using polarimetric decomposition. Vector data for agricultural land use areas were overlaid on the analysed images and the mean value for each agricultural parcel computed. By quantitatively comparing our data with a reference dataset generated from optical sensor images, effective polarimetric parameters and the ideal observation season were revealed. Double bounce scattering and surface scattering component ratios, derived using a four-component decomposition algorithm, were key to extracting paddy rice fields when the plant stems are vertical with respect to the ground. The alpha angle was also an effective factor for extracting rice fields from an agricultural area. The data obtained during August show maximum agreement with the reference dataset of estimated paddy rice field areas.     

A novel super-resolution method of PolSAR images based on target decomposition and polarimetric spatial correlation

The polarimetric synthetic aperture radar (PolSAR) is becoming more and more popular in remote-sensing research areas. However, due to system limitations, such as bandwidth of the signal and the physical dimension of antennas, the resolution of PolSAR images cannot be compared with those of optical remote-sensing images. Super-resolution processing of PolSAR images is usually desired for PolSAR image applications, such as image interpretation and target detection. Usually, in a PolSAR image, each resolution contains several different scattering mechanisms. If these mechanisms can be allocated to different parts within one resolution cell, details of the images can be enhanced, which that means the resolution of the images is improved. In this article, a novel super-resolution algorithm for PolSAR images is proposed, in which polarimetric target decomposition and polarimetric spatial correlation are both taken into consideration. The super-resolution method, based on polarimetric spatial correlation (SRPSC), can make full use of the polarimetric spatial correlation to allocate different scattering mechanisms of PolSAR images. The advantage of SRPSC is that the phase information can be preserved in the processed PolSAR images. The proposed methods are demonstrated with the German Aerospace Center (DLR) Experimental SAR (E-SAR) L-band full polarized images of the Oberpfaffenhofen Test Site Area in Germany, obtained on 30 September 2000. The experimental results of the SRPSC confirms the effectiveness of the proposed methods.¹     

Multi-mode PolInSAR experiments using an airborne X-band SAR system in China

In this paper, we describe our polarimetric interferometric synthetic aperture radar (PolInSAR) experiments with high-resolution X-band data acquired by a multi-mode airborne SAR system over an area of Linshui in southern China. First, we introduce our latest multi-mode X-band airborne imaging radar system (Multi-Mode-XSAR), which integrates three operation modes of bistatic, ping-pong, and mixed. Then, the Multi-Mode-XSAR data set and the corresponding ground measurements in test areas are briefly described. Considering the characteristics of the Multi-Mode-XSAR imagery, a dual-baseline polarimetric interferometry (DPI) method is proposed in this article. The proposed method guarantees a high coherence on the full polarimetric data and combines the benefits of short and long baselines to facilitate the phase unwrapping and promote height sensitivity. Our PolInSAR experiment results demonstrate that the DPI method is capable of generating DSM with higher accuracy than other multi-baseline (MB) methods and the Multi-Mode-XSAR imagery has great potential in PolInSAR applications.     

全极化SAR极化特征谱应用研究

在分析特征值分解结果,全部散射机制组合和极化特征谱性质的基础上,提出基于3个特征谱参数的假彩色合成方法,可以更加有效直观地反映地物散射特征,再对散射熵、散射角、反熵和4个极化特征谱参数进行特征选择分析,给出最佳的多维特征向量选择方案,从而实现传统遥感图像分类器如同ISODATA算法对极化SAR图像的分类。实验选择了一景Radarsat\|2标准全极化SAR数据,包含典型的城市、植被和水体三大类地物,实验结果表明:极化特征谱假彩色合成充分反映了各地物散射特征,特征谱和散射角组成了最佳特征向量,非监督分类结果表明:该方法克服了城市与植被在H\|Alpha平面上分布界限模糊的问题,分类精度高于H\|Alpha平面非监督分类,与Wishart-H-Alpha-A分类方法相当。     

极化SAR相干斑抑制的非局部加权最小均方误差滤波算法

目的 相干斑的存在严重影响了极化合成孔径雷达(PolSAR)的影像质量.对相干斑的抑制是使用SAR数据的必不可少的预处理程序.提出一种基于非局部加权的线性最小均方误差(LMMSE)滤波器的极化SAR滤波的方法.方法 该方法的主要过程是利用非局部均值的理论来获取LMMSE估计器中像素样本的权重.同时,在样本像素的选取过程中,利用待处理像素的极化散射特性和邻域块的异质性来排除不相似像素以加速算法,同时达到保持点目标和自适应调节块窗口大小的目的.结果 模拟影像和真实影像上进行的实验结果表明,采用这种方法滤波后影像的质量得到明显改善.和传统的LMMSE算法相比,无论是单视的影像还是多视的影像,本文方法去噪结果的等效视数都高出8视以上;峰值信噪比也提升了5.8 dB.同时,去噪后影像分类的总体精度也达到了83％以上,该方法的运行效率也比非局部均值算法有了较大提升.结论 本文方法不仅能够有效抑制相干斑噪声,还能较好地保持边缘和细节信息以及极化散射特性.这将会为后续高效利用SAR数据提供保障.     

Imaging and structural feature decomposition of a complex target using multi-aspect polarimetric scattering

Based on the Huynen parametric decomposition of target scattering matrix, the polarimetric ellipse parameters are transformed and applied to decomposition of scattering mechanisms of a complex target in VHR POL-SAR images (very high resolution, polarimetric synthetic aperture radar). Making use of multi-aspect (or circle-aspect) and wideband VHR POL-SAR images, scattering mechanisms of a volumetric target and its structural components are recognized over image pixels. Utilizing the layover features, the target height profile is also estimated from two-dimensional image. As example, polarimetric scattering data of some vehicles on ground, including multi-aspect simulated data and experimental measurements, are applied to validations of scattering mechanism decompositions and target structural feature recognition.     

一种新的简缩极化SAR图像H/α特征空间

现有简缩极化(Compact Polarimetry)SAR图像H/α经验特征空间存在两个问题:一是没有考虑简缩极化模式下的散射熵普遍高于全极化模式;二是在散射机制重叠区域,简缩极化H/α空间的分类能力较弱,尤其是多次散射。针对以上问题首先定量分析了DCP模式简缩极化SAR的散射角与全极化SAR数据散射角之间的关系,且在对7组不同传感器的SAR数据分析的基础上,提出了散射熵的替代参数ED,基于Monte Carlo模拟实验得到了H/α分解的各参数(熵H、平均散射角α和替代参数ED)分解的稳态条件;然后通过统计各散射机制在ED/α分布的密度空间,提出了一种新的简缩极化SAR图像ED/α特征空间。实验结果表明:替代参数ED与全极化熵具有良好相关性,而且ED/α特征空间提高了散射机制分类的精度。     

A unified three-component scattering model for polarimetric coherent target decomposition

In this article, first, the properties of the symmetric scattering space are examined based on the representation of the maximum symmetric scattering component proposed by Touzi. The symmetric scattering unit disc in the complex plane is mapped to a more intuitive unit sphere representation, and a new simpler classification method for symmetric scatterers is proposed based on a simplified symmetric scatterer scattering matrix metric distance. Then, a unified three-component scattering model for polarimetric coherent target decomposition (CTD) is proposed. Pauli decomposition, sphere, dihedral, helix (SDH) decomposition and Cameron decomposition can be expressed as a simplified form of the unified model with some certain restrictions, respectively. In addition, SDH decomposition and Cameron decomposition are proved to be equivalent by verification of restrictions’ consistency. Finally, by the combination of SDH decomposition and symmetric scatterer classification, a scattering matrix classification scheme is proposed to classify the scatterers into 12 scattering types.     

Application of incoherent target decomposition theorems to classify snow cover over the Himalayan region

Snow cover is an important parameter for hydrological modelling and climate change modelling. Various methods are available only for wet snow-cover mapping using conventional synthetic aperture radar (SAR) data. Total snow (wet + dry) cover mapping with SAR data is still a topical research area. Therefore, incoherent target decomposition theorems have been implemented on fully polarimetric SAR data to characterize the scattering of various targets. Further classification techniques – both unsupervised and supervised – have been applied for accurate mapping of total snow cover. For this purpose, Advanced Land Observing Satellite – phased array-type L-band SAR (ALOS–PALSAR) data (12 May 2007) have been analysed for snow classification of glaciated terrain in and around Badrinath region in Himalaya. An ALOS-Advanced Visible and Near Infrared Radiometer (AVNIR)-2 image (6 May 2007) was also used to provide assistance in the selection of different training classes. It has been found that the application of incoherent target decomposition theorems such as H/A/α and four-component scattering mechanism models are good for extracting the desired information of snow cover from fully polarimetric PALSAR data. Finally, based on these target decomposition theorems and the Wishart classifier, PALSAR data have been classified into snow or non-snow cover, and the user accuracy of snow classes was found to be better than the user accuracy of other classes. Hence, the application of incoherent target decomposition theorems with full polarimetric ALOS-PALSAR data is useful for snow-cover mapping.     

一种新的基于Wishart MRF的全极化SAR图像分类方法

无监督的Wishart分类算法在多次迭代后,容易出现错分现象,即多个类别属于同一类散射机制,或者多种散射都拥有相同的类别标签。针对此问题,提出了一种新的基于Wishart MRF的无监督全极化SAR图像分类方法。新方法改进了散射机制保持的方式,即并不是完全限制像素点的散射机制,而是根据像素点的散射机制在迭代过程中给定一个有限的范围。同时,使用一种自适应区域的MRF方法来提取像素点的先验信息。该方法不仅考虑了全极化SAR数据的散射性质,而且结合了统计特性和邻域信息,并在一定程度上保持了散射性质。实验结果证明,与传统的Wishart和基于散射机制保持的Wishart算法相比,该方法在JPL/NASA的AIRSAR数据上取得了更好的分类结果。     

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.     

A novel approach to polarimetric SAR data processing based on Nonlinear PCA

In remotely sensed Synthetic Aperture Radar (SAR) images, scattering from a target is often the result of a mixture of different mechanisms. For this reason, detection of targets and classification of SAR images may be very difficult and very different from other sensor imagery. Fully polarimetric data offer the possibility to separate the different mechanisms, interpret them and consequently identify the geometry of the targets. To achieve this task, several target decomposition techniques have been proposed in the literature to improve the interpretation of this kind of data. Among these, the physical based techniques are the most considered.     

深度置信网络在极化SAR图像分类中的应用

目的 深度置信网络能够从数据中自动学习、提取特征,在特征学习方面具有突出优势。极化SAR图像分类中存在海量特征利用率低、特征选取主观性强的问题。为了解决这一问题,提出一种基于深度置信网络的极化SAR图像分类方法。方法 首先进行海量分类特征提取,获得极化类、辐射类、空间类和子孔径类四类特征构成的特征集;然后在特征集基础上选取样本并构建特征矢量,用以输入到深度置信网络模型之中;最后利用深度置信网络的方法对海量分类特征进行逐层学习抽象,获得有效的分类特征进行分类。结果 采用AIRSAR数据进行实验,分类结果精度达到91.06%。通过与经典Wishart监督分类、逻辑回归分类方法对比,表现了深度置信网络方法在特征学习方面的突出优势,验证了方法的适用性。结论 针对极化SAR图像海量特征的选取与利用,提出了一种新的分类方法,为极化SAR图像分类提供了一种新思路,为深度置信网络获得更广泛地应用进行有益的探索和尝试。     

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。     

A novel measure of target scattering randomness with application to polarimetric SAR image classification

A novel measure of target scattering randomness, called the average degree of randomness (ADoR), is introduced in this article. The proposed parameter ADoR is based on the degrees of polarization of the scattered waves using orthogonally polarized incident waves. Combining the ADoR and the Freeman decomposition, which is applied to discriminate the dominant scattering mechanism of the target, a new scheme for unsupervised classification of polarimetric synthetic aperture radar (PolSAR) images is designed. Considering that the preset intervals of the randomness measure may not fit the data distribution, an iterative classification method is developed. The effectiveness of the randomness measure and the proposed methods is demonstrated using a National Aeronautics and Space Administration (NASA)/Jet Propulsion Laboratory (JPL) AIRborne Synthetic Aperture Radar (AIRSAR) PolSAR image.