Application of neural networks to radar image classification

A number of methods have been developed to classify ground terrain types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are often grouped into supervised and unsupervised approaches. Supervised methods have yielded higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new terrain classification technique is introduced to determine terrain classes in polarimetric SAR images, utilizing unsupervised neural networks to provide automatic classification, and employing an iterative algorithm to improve the performance. Several types of unsupervised neural networks are first applied to the classification of SAR images, and the results are compared to those of more conventional unsupervised methods. Results show that one neural network method-Learning Vector Quantization (LVQ)-outperforms the conventional unsupervised classifiers, but is still inferior to supervised methods. To overcome this poor accuracy, an iterative algorithm is proposed where the SAR image is reclassified using a maximum likelihood (ML) classifier. It is shown that this algorithm converges, and significantly improves classification accuracy     

Unsupervised segmentation of synthetic aperture Radar sea ice imagery using a novel Markov random field model

Environmental and sensor challenges pose difficulties for the development of computer-assisted algorithms to segment synthetic aperture radar (SAR) sea ice imagery. In this research, in support of operational activities at the Canadian Ice Service, images containing visually separable classes of either ice and water or multiple ice classes are segmented. This work uses image intensity to discriminate ice from water and uses texture features to identify distinct ice types. In order to seamlessly combine image spatial relationships with various image features, a novel Bayesian segmentation approach is developed and applied. This new approach uses a function-based parameter to weight the two components in a Markov random field (MRF) model. The devised model allows for automatic estimation of MRF model parameters to produce accurate unsupervised segmentation results. Experiments demonstrate that the proposed algorithm is able to successfully segment various SAR sea ice images and achieve improvement over existing published methods including the standard MRF-based method, finite Gamma mixture model, and K-means clustering.     

Restoration of polarimetric SAR images using simulated annealing

Filtering synthetic aperture radar (SAR) images ideally results in better estimates of the parameters characterizing the distributed targets in the images while preserving the structures of the nondistributed targets. However, these objectives are normally conflicting, often leading to a filtering approach favoring one of the objectives. An algorithm for estimating the radar cross-section (RCS) for intensity SAR images has previously been proposed in the literature based on Markov random fields and the stochastic optimization method simulated annealing. A new version of the algorithm is presented applicable to multilook polarimetric SAR images, resulting in an estimate of the mean covariance matrix rather than the RCS. Small windows are applied in the filtering, and due to the iterative nature of the approach, reasonable estimates of the polarimetric quantities characterizing the distributed targets are obtained while at the same time preserving most of the structures in the image. The algorithm is evaluated using multilook polarimetric L-band data from the Danish airborne EMISAR system, and the impact of the algorithm on the unsupervised H-α classification is demonstrated     

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。     

A NEW UNSUPERVISED CLASSIFICATION ALGORITHM FOR POLARIMETRIC SAR IMAGES BASED ON FUZZY SET THEORY

In this letter, a new method is proposed for unsupervised classification of terrain types and man-made objects using POLarimetric Synthetic Aperture Radar （POLSAR） data. This technique is a combination of the usage of polarimetric information of SAR images and the unsupervised classification method based on fuzzy set theory. Image quantization and image enhancement are used to preprocess the POLSAR data. Then the polarimetric information and Fuzzy C-Means （FCM） clustering algorithm are used to classify the preprocessed images. The advantages of this algorithm are the automated classification, its high classification accuracy, fast convergence and high stability. The effectiveness of this algorithm is demonstrated by experiments using SIR-C/X-SAR （Spaceborne Imaging Radar-C/X-band Synthetic Aperture Radar） data.     

SAR图像的自动分割方法研究

由于存在相干斑噪声的影响,给SAR图像分割造成很大的困难,该文提出了一种SAR图像的自动分割方法。首先在特征提取阶段,通过计算小波能量提取纹理信息,用邻域统计量提取灰度信息,用保边缘平均灰度提取边缘信息,以确保边缘准确。然后提出一种改进的完全无监督的聚类算法进行图像分割,该算法可以自动确定分割的类型数目。由于该方法充分考虑了SAR图像的纹理、灰度和边缘信息,因而极大地提高了其最终分割性能。实验结果证明了该方法的有效性。     

基于H-α和改进C-均值的全极化SAR图像非监督分类

该文提出一种基于H-α和改进C-均值的全极化SAR图像非监督分类方法.该方法先按H-α对全极化SAR图像进行基于散射机理的分类,再将分类结果作为改进C-均值算法的初始类别划分,从而实现地物分类.迭代次数确定是C-均值动态聚类算法的关键,文中利用图像熵给出了一种新的迭代终止准则.与H-α方法相比,该文方法能在保留分类结果物理散射机理的同时,实现有效的地物分类.NASA/JPL实验室AIRSAR系统获取的L波段旧金山全极化SAR数据的实验结果验证了该文方法的有效性.     

基于Wishart分布和MRF的多视全极化SAR图像分割

提出一种新的多视全极化SAR图像分割方法.将描述多视协方差矩阵的Wishart分布与马尔可夫随机场模型结合起来,利用迭代条件模型法(ICM)求取最大后验概率准则下的分割结果,其中ICM所需的初始分割图由基于Wishart分布的最大似然法获得.NASA/JPL实验室AIRSAR系统多视全极化数据的实验结果表明,与几种常用方法相比,本文方法分割精度更高,分割结果图中孤立像素少,图像连通性好.     

Unsupervised segmentation of polarimetric SAR data using thecovariance matrix

A method for unsupervised segmentation of polarimetric synthetic aperture radar (SAR) data into classes of homogeneous microwave polarimetric backscatter characteristics is presented. Classes of polarimetric backscatter are selected on the basis of a multidimensional fuzzy clustering of the logarithm of the parameters composing the polarimetric covariance matrix. The clustering procedure uses both polarimetric amplitude and phase information, is adapted to the presence of image speckle, and does not require an arbitrary weighting of the different polarimetric channels; it also provides a partitioning of each data sample used for clustering into multiple clusters. Given the classes of polarimetric backscatter, the entire image is classified using a maximum a posteriori polarimetric classifier. Four-look polarimetric SAR complex data of lava flows and of sea ice acquired by the NASA/JPL airborne polarimetric radar (AIRSAR) are segmented using this technique     

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。     

Unsupervised classification of multifrequency and fullypolarimetric SAR images based on the H/A/Alpha-Wishart classifier

Introduces a new classification scheme for dual frequency polarimetric SAR data sets. A (6×6) polarimetric coherency matrix is defined to simultaneously take into account the full polarimetric information from both images. This matrix is composed of the two coherency matrices and their cross-correlation. A decomposition theorem is applied to both images to obtain 64 initial clusters based on their scattering characteristics. The data sets are then classified by an iterative algorithm based on a complex Wishart density function of the 6×6 matrix. A class number reduction technique is then applied on the 64 resulting clusters to improve the efficiency of the interpretation and representation of each class. An alternative technique is also proposed which introduces the polarimetric cross-correlation information to refine the results of classification to a small number of clusters using the conditional probability of the cross-correlation matrix. These classification schemes are applied to full polarimetric P, L, and C-band SAR images of the Nezer Forest, France, acquired by the NASA/JPL AIRSAR sensor in 1989     

Baltic Sea ice SAR segmentation and classification using modified pulse-coupled neural networks

A method for segmentation and classification of Baltic Sea ice synthetic aperture radar (SAR) images, based on pulse-coupled neural networks (PCNNs), is presented. Also, automated training, which is based on decomposing the total pixel value distribution into a mixture of class distributions, is presented and discussed. The algorithms have been trained and tested using logarithmic scale Radarsat-1 ScanSAR Wide mode images over the Baltic Sea ice. Before the decomposition into mixture of class distributions, an incidence angle correction, specifically designed for these Baltic Sea ice SAR images, is applied. Because the data distributions in the uniform areas of these images are very close to Gaussian distributions, the data are decomposed into a mixture of Gaussian distributions, using the Expectation-Maximazation algorithm. Only uniform image areas are used in the decomposition phase. The mixture of distributions is compared to the distributions of the Baltic Sea ice classes, based on earlier scatterometer measurements and visual video interpretations of the sea ice classes. The parameter values for the PCNN segmentation are defined based on this mixture of distributions. The PCNN segmentation results are also compared to the operational sea ice information of digitized ice charts and to visual interpretation of the sea ice class.     

基于无监督分类的多视极化SAR相干斑滤波

相干斑噪声是引起SAR图像降质的主要原因之一。多视极化白化滤波器(MPWF)是一种专门应用于多视极化SAR图像降噪的有效技术。其中,滤波器参数估计的精确度直接决定了其滤波性能的好坏。对此,该文提出了一种新的基于无监督分类的自适应窗算法。该算法以分类图像作为对象;在滑动矩形窗内以中心像素作为参照物,自动搜索与其同类的像素并用于MPWF参数估计。实验结果表明,与其他几种典型的算法相比,该法不仅有效地抑制了相干斑,而且对图像的纹理信息具有很好的保持能力。     

基于局部竞争策略的极化SAR图像精细分类

合成孔径雷达（Synthetic Aperture Radar, SAR）成像技术已经成为一种高分辨对地观测的重要手段之一,而极化SAR图像地物分类一直是其中的研究热点。基于复Wishart分布的最大似然（Maximum Likelihood,ML）分类器是最经典的极化SAR图像分类算法之一,但由于地物类型的复杂性、区域的不均匀性等原因使得基于像素的ML-Wishart分类器的分类精度不高。针对这个问题,本文提出了一种基于复Wishart分布的局部最大后验概率（Maximum a Posteriori,MAP）竞争方法,该算法通过计算伪先验概率,并在每个像素的局部窗口中实施MAP分类器,可以提高复杂区域图像的分类精度。该文主要研究了4种基于Wishart分布的分类算法,包括经典复Wishart分类算法、混合复Wishart模型、基于马尔科夫随机场（Markov Random Field, MRF）的混合复Wishart模型和基于局部竞争策略的MAP分类算法。在混合模型建模中,不同于以往的对整幅图像进行建模的模型策略,本文采用对单个类别进行混合建模的策略。实验对比分析了上述4个分类器和SVM分类器在C波段RADARSAT-2多时相的全极化SAR农田数据上的分类效果。实验结果表明,所提出的基于局部竞争策略的分类器对数据的分类结果稳定,具有最高的分类精度,基于混合Wishart的MRF模型分类结果次之。     

（英）集成颜色特征和统计特征的极化SAR图像城区分类框架

在传统的利用极化合成孔径雷达(PolSAR)遥感图像分类中,除了近期一个有监督分类的工作,很少涉及颜色特征。与该工作不同,在本文中,针对城区分类,利用颜色特征构造一个新颖的无监督的分类框架。首先,基于最近提出的PolSAR数据的四分量分解模型,计算了常用的颜色空间：YUV,RGB,HSI和CIELab,通过引入颜色熵量化的选择颜色特征,然后,联合纹理特征和扩展的散射功率熵,用自适应的均值漂移算法分割PolSAR图像,最后,根据基于G0分布的距离测度合并聚簇为较为匀质的地物类别。通过L波段AIRSAR数据和C波段Radarsat-2的PolSAR数据验证了提出算法的有效性,分类正确率表明,相比于已有的工作,提出的算法对于城区有较好的区分能力。     

多视极化合成孔径雷达图象的分类和极化通道优化

本文提出一个新的最大似然(ML)分类算法对多视全极化合成孔径雷达(SAR)图象进行分类,给出了应用NASA/JPL机载L波段四视全极化SAR实测数据的试验结果,证明了新算法的有效性。此外,本文还将所提算法应用于部分的多视全极化SAR数据中,实现了地貌类型分类的极化通道优化。     

CLASSIFICATION OF MULTI-LOOK POLARIMETRIC SAR IMAGERY AND POLARIZATION CHANNEL OPTIMIZATION

In this paper, a new maximum likelihood (ML) classification algorithm is proposed to classify the multi-look polarimetric synthetic aperture radar (SAR) imagery. Experimental results with the NASA/JPL airborne L-band polarimetric SAR data demonstrate the effectiveness of the new algorithm. Furthermore, when using the algorithm in the classifications with subsets of the multi-look polarimetric SAR data, the polarization-channel optimization for the terrain type classification is implemented.     

基于小波变换和马尔可夫随机场的极化SAR图像自动分类

本文提出一种对极化合成孔径雷达(SAR)图像进行自动多分辨率分类的方法。首先利用多视极化白化滤波(MPWF)抑制极化SAR图像的相干斑,得到反映地物辐射特征的纹理SAR图像,然后利用小波变换(WT)提取不同分辨率的纹理信息,在最低分辨率级利用Akaik信息准则(AIC)自动估计图像中的纹理类数,进而在各个分辨率级利用马尔可夫随机场(MRF)模型表征各像素间的空间关联信息,并分别利用最大似然(ML)方法和循环条件模式(ICM)进行自动的模型参数估计和最大后验概率(MAP)分类,最后应用NASA/JPL机载L波段极化SAR数据验证了本文所提分类方法的有效性和优越性。     

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．     

基于邻域一致性的极化SAR图像仿射配准

极化SAR图像的配准是极化SAR图像处理的基础,需要具备较高的精度与速度。基于深度学习的极化SAR图像配准大多数是结合图像块特征的匹配与基于随机抽样一致性的参数迭代估计来实现的。目前尚未实现端到端的基于深度卷积神经网络的一步仿射配准。该文提出了一种基于弱监督学习的端到端极化SAR图像配准框架,无需图像切块处理或迭代参数估计。首先,对输入图像对进行特征提取,得到密集的特征图。在此基础上,针对每个特征点保留k对相关度最高的特征点对。之后,将该4D稀疏特征匹配图输入4D稀疏卷积网络,基于邻域一致性进行特征匹配的过滤。最后,结合输出的匹配点对置信度,利用带权最小二乘法进行仿射参数回归,实现图像对的配准。该文采用RADARSAT-2卫星获取的德国Wallerfing地区农田数据以及PAZ卫星获取的中国舟山港口地区数据作为测试图像对。通过对升降轨、不同成像模式、不同极化方式、不同分辨率的极化SAR图像对的配准测试,并与4种现有方法进行对比,验证了该方法具有较高的配准精度与较快的速度。