Textural Classification of Single Band SIR‐B Data over a Part of Brahmaputra Basin,India

Abstract

Texture is an important spatial feature, useful for identfying objects of regions of interest in an image. There are a number of methods for identification of textural parameters e.g. edgeness, frequency domain analysis, gray tone cooccurrence approach etc. Geologic information in radar images of heavily vegetated areas is contained mostly in the depiction of topography in image texture. Single band SIR/ERS‐1 SAR data posses a problem to the analyst for classification of the various land use/geological classes and generally multidate SAR data are used due to paucity of more number of bands. However, the multidate SAR data classification is not an ideal technique. A new technique, namely, spatial frequency band pass classification technique which generates two or more bands in the Fourier domain using the single band SAR data and then classifies various features of interest using their textural properties has been described here. Result shows higher percentage of classification using Maximum‐Likelihood Classifier (MXL) with two split‐band data as compared to the unsupervised classification of all the bands.     

An Analysis of Texture Measures in PCA-Based Unsupervised Classification of SAR Images

In single-band single-polarized SAR images, intensity and texture are the information source available for unsupervised land cover classification. Every textural feature measure identifies texture patterns by different approaches. For efficient land cover classification, textural measures have to be chosen suitably. Therefore, in this letter, the role of various intensity and textural measures is analyzed for their discriminative ability for unsupervised SAR image classification into various land cover types like water, urban, and vegetation areas. To make the algorithm adaptable, these textural features are fused using principal component analysis (PCA), and principal components are used for classification purposes. To highlight the effectiveness of PCA, the difference between PCA- and non-PCA-based classifications is also analyzed. Analysis of the role of texture measures for unsupervised classification of real-world SAR data with application of PCA is presented in this letter. The analysis of how every individual feature measure contributes for classification process is presented, and then, textural measures for a feature set are chosen according to their role in improving classification accuracy. By analysis, it is observed that the feature set comprising mean, variance, wavelet components, semivariogram, lacunarity, and weighted rank fill ratio provides good classification accuracy of up to 90.4% than by using individual textural measures, and this increased accuracy justifies the complexity involved in the process.     

基于分形理论的航空图像分类方法

提出一种基于分形理论和BP神经网络的航空遥感图像有监督分类方法。该方法尝试将航空图像的光谱信息和纹理特征相结合。它首先将彩色航空图像由RGB格式转化为HSI格式，然后，根据亮度计算分数维、多重分形广义维数谱q-D(q)和“空隙”等基于分形的纹理特征，同时加入归一化的色度和饱和度作为光谱特征，采用BP神经网络作为分类器。通过对彩色航空图像的分类实验，结果证实该方法行之有效。     

基于分形理论的航空图像分类方法

提出一种基于分形理论和BP神经网络的航空遥感图像有监督分类方法。该方法尝试将航空图像的光谱信息和纹理特征相结合。它首先将彩色航空图像由RGB格式转化为HSI格式，然后，根据亮度计算分数维、多重分形广义维数谱q-D(q)和“空隙”等基于分形的纹理特征，同时加入归一化的色度和饱和度作为光谱特征，采用BP神经网络作为分类器。通过对彩色航空图像的分类实验，结果证实该方法行之有效。     

Segmentation and classification of high spatial resolution images based on Hölder exponents and variance

Pixel-based or texture-based classification technique individually does not yield an appropriate result in classifying the high spatial resolution remote sensing imagery since it comprises textured and non-textured regions. In this study, Hölder exponents (HE) and variance (VAR) are used together to transform the image for measuring texture. A threshold is derived to segment the transformed image into textured and non-textured regions. Subsequently, the original image is extracted into textured and non-textured regions using this segmented image mask. Afterward, extracted textured region is classified using ISODATA classification algorithm considering HE, VAR, and intensity values of individual pixel of textured region. And extracted non-textured region of the image is classified using ISODATA classification algorithm. In case of non-textured region, HE and VAR value of individual pixel is not considered for classification for significant textural variation is not found among different classes. Consequently, the classified outputs of non-textured and textured regions that are generated independently are merged together to get the final classified image. IKONOS 1 m PAN images are classified using the proposed algorithm, and the classification accuracy is more than 88%.     

傅里叶谱纹理和光谱信息结合的高分辨率遥感影像地表覆盖分类

以高空间分辨率遥感影像为研究对象,将纹理特征与影像的光谱特征结合起来,用于地表覆盖类型分类。设计了一种基于傅里叶谱纹理的分类策略,对主成分分析后的第1、2主分量特征影像,利用径向谱（r-spectrum）提取纹理特征,并将纹理与光谱特征结合起来,构建了不同的分类特征用于支持向量机分类模型。以Salinas数据集和QuickBird影像为例,验证该算法。结果表明,纹理与光谱信息的结合可以明显提高高分辨率遥感影像的分类精度;由傅里叶径向谱提取的纹理特征可以很好的应用到高分辨率遥感影像的分类问题中,分类精度高于基于傅里叶总能量谱和灰度共生矩阵的分类精度;利用该算法对PCA变换后的第1和第2分量提取的纹理特征具有一定的互补性,并且结合多特征图像的纹理特征提取优于单特征图像的纹理特征提取。     

影像融合技术应用于地表分类之探讨

本论文尝试讨论两个主题：主题一为利用主成分分析PCA方法应用于像元阶层资料融合技术的研究。主题二为应用Dempster-Shafer evidence theory方法于特征阶层数据融合技术的研究。在第一个主题中，由于合成孔径雷达的数据具有全偏极特性，在此选取了对植被较为敏感的HV极化合成孔径雷达数据，与具有光谱特性的光学SPOT数据做数据融合处理以利接下来的地物分类。首先，本研究利用小波转换技术来滤除合成孔径雷达斑驳噪声，在接下来融合步骤中，主成分分析出来的第一部分（PCI）是用做完滤除噪声后的合成孔径雷达取代，在数据融合后，进行地物分类是采用最大似然法来分类融合影像。在第二个主题中，利用全偏极雷达数据的极化特性结合SPOT数据的光谱特性，其主要目的是为了增加分类的精确度。首先使用李式滤波器滤除全偏极雷达数据噪声，接下来同样是使用采用最大似然法来分类融合影像，（不同的在于全偏极雷达影像使用Wishart几率分布，在光学影像采用multivariate Gaussian几率分布）将每个类别中每个像元属于某个类别的几率值计算出来，再利用Dempster-Shafer evidence theory来结合这些类别的机率值。最后产生出一张新的分类影像。实验的结果显示分类的精确度比较于未融合的资料都有明显提升的效果，也证明了此两个数据融合方法对于不同数据特性的融合都是很成功的。     

Fractal Genetic Model in Change Detection of SAR images

The paper presents an effective way of detecting the changes of multi-temporal synthetic aperture radar (SAR) images. An accurate unsupervised change detection method that combines the intensity information and the fractal dimension of SAR images is proposed based on the fractal genetic model (FGM). The model computes firstly the local fractal dimension of the SAR images to obtain the fractal image and next a new proposed measure (D) is calculated from the normalized ratio of SAR images and the normalized difference of fractal images. Finally, the change map is derived by minimizing a cost function using a genetic algorithm (GA) on the derived image from the measure. Experimental results of detecting changes from SAR images acquired by ASAR on board ENVISAT and ALOS-PALSAR reveal that the proposed method is an effective and efficient tool for change detection from SAR images.     

Change detection method based on fractal model and wavelet transform for multitemporal SAR images

The interaction is quite complex between a ground object and an electromagnetic wave transmitted by synthetic aperture radar (SAR). In a ground resolution cell illuminated by a radar beam, there are many chaotic scatterers and the whole scattering echo has the chaotic characteristics which is usually described with the fractal theory, and the fractal dimension can be used to detect the change information for multitemporal SAR images. In order to improve the change detection effect with fractal model, this paper proposes a new multitemporal SAR image change detection algorithm based on the fractal model and wavelet transform (called FMWT algorithm). The FMWT algorithm has two advantages. One is insensitive to speckle noise; the other is that the change detection accuracy is improved, comparing with a general fractal change detection (GFCD) algorithm. Since the FMWT algorithm adopts the two-dimensional discrete stationary wavelet transform (TDDSWT) technique, it can obtain different direction sub-images and avoid down-sampling of the discrete wavelet transform (DWT). In the paper, not only the simulative data test has been carried out, but also the real natural disaster SAR images have been checked. Experimental results verify that the FMWT algorithm is feasible for multitemporal SAR image change detection, it is not sensitive to speckle noise of SAR images, and the performance of it is better than that of the GFCD algorithm. At the same time, the size of a sliding window will bring some affection in counting fractal dimensions.     

面向对象的高光谱遥感影像稀疏表示分类

稀疏表示用于高光谱遥感影像分类多是基于像素层次来处理的。文中提出一种面向对象的高光谱遥感影像稀疏表示分类方法。首先从高光谱影像中提取4个波段组成标准的多波段影像,进行面向对象的影像分割;然后计算各对象在各波段上的光谱均值,并选取少量样本进行训练;最后利用基于Fisher字典学习的稀疏表示进行高光谱遥感影像的分类。实验结果表明,该方法可以利用较少的样本得到较好的分类效果,与基于像素层的稀疏分类相比较,分类精度与效率均有所提高,分类结果更接近真实地物,避免了零碎图斑。     

LSSVM算法在极化SAR影像分类中的应用

最小二乘支持向量机(LSSVM)是针对标准支持向量机(SVM)算法训练时间长的问题而提出的一种改进算法。针对SVM算法在极化SAR影像分类时存在效率较低的问题,以目标分解理论为基础,对LSSVM算法应用于极化SAR影像分类的有效性进行了研究。结果表明,对于极化SAR影像分类,LSSVM算法与SVM算法的分类精度相当,但时间效率远优于SVM算法,并且对参数的调整也具有更好的稳定性,同时泛化能力良好。     

利用SAR影像配准偏移量提取地表形变的方法与误差分析

单一的InSAR观测技术可提取地表沿雷达视线方向(LOS)上的一维位移,而利用SAR影像配准过程中的同名像素偏移量可提取地表沿雷达方位向(近南北向)与距离向(近东西向)的二维形变场,与LOS方向的一维形变形成优势互补。本文在分析SAR影像配准偏移量提取地表形变场方法的基础上,推导建立了雷达方位向与距离向形变提取的误差模型,探讨了该方法提取地表形变的主要误差源。以Bam地震ASAR影像和玉树地震PALSAR影像为数据源,分别开展同震形变场的提取与误差分析试验,结果表明,基于SAR像素配准偏移量提取同震形变场的精度主要受匹配窗口尺寸与过采样因子影响,形变提取误差随匹配计算窗口的增大而减小,形变提取精度随过采样因子的增大有适量提高,地形起伏效应在高差较大的SAR影像区域中表现较为显著。     

Toward reduction of artifacts in fused images

Most fusion satellite image methodologies at pixel-level introduce false spatial details, i.e. artifacts, in the resulting fused images. In many cases, these artifacts appears because image fusion methods do not consider the differences in roughness or textural characteristics between different land covers. They only consider the digital values associated with single pixels. This effect increases as the spatial resolution image increases. To minimize this problem, we propose a new paradigm based on local measurements of the fractal dimension (FD). Fractal dimension maps (FDMs) are generated for each of the source images (panchromatic and each band of the multi-spectral images) with the box-counting algorithm and by applying a windowing process. The average of source image FDMs, previously indexed between 0 and 1, has been used for discrimination of different land covers present in satellite images. This paradigm has been applied through the fusion methodology based on the discrete wavelet transform (DWT), using the à trous algorithm (WAT). Two different scenes registered by optical sensors on board FORMOSAT-2 and IKONOS satellites were used to study the behaviour of the proposed methodology. The implementation of this approach, using the WAT method, allows adapting the fusion process to the roughness and shape of the regions present in the image to be fused. This improves the quality of the fused images and their classification results when compared with the original WAT method.     

综合多特征的极化SAR图像随机森林分类算法

为抑制相干斑噪声对极化SAR图像分类结果的干扰,本文提出一种综合多特征的极化SAR图像随机森林分类方法。该方法首先利用简单线性迭代聚类(SLIC)算法生成超像素作为分类单元;然后,基于高维极化特征图像,利用训练好的随机森林模型,统计决策树的分类投票数,计算各超像素的类别概率;最后,利用超像素间的空间邻域特征,采用概率松弛算法(PLR)迭代修正超像素的类别后验概率,并依据最大后验概率(MAP)准则得到分类结果;实现综合利用超像素和空间邻域特征,降低相干斑噪声干扰的极化SAR图像分类方法。实验对比结果表明:本文方法能得有效抑制极化SAR图像中相干斑噪声的干扰,得到高精度且光滑连续的分类结果。     

使用ERS-1/2干涉测量SAR数据生成DEM

干涉合成孔径雷达（ＩＮＳＡＲ）数据已被证明能生产精确的数据高程模型（ＤＥＭ），我们已开发了从单视ＳＡＲ复影像数据自动生成数字高程模型的新软件，基于ＳＡＲ多视强度影像的最小二乘曩像匹配被用于复影像对的配准，达到很高的配准精度（０．０１～０．０５像元精度）。一种新的计算目标点３维坐标（Ｘ，Ｙ，Ｚ）的方程还被提出，卫星轨道，姿态和基线参数以及相位常数被纳入在方程中并被表示了时间的线性函数，利用至少６个地面控制点能够同时估算这些参数，本文还给出了意大利埃特地区ＥＲＳ－１／２ＳＡＲ数据处理结果。     

Two Approaches of Textural Classification for the Location of the Flows of Lava on the Volcanic Site of the Mountain Cameroon

Abstract

This study presents two approaches of textural classification on a synthetic aperture radar (SAR) ERS‐2 image, with the aim of the location of the flows of lava and of the serviced zones around the volcanic site of the Mountain Cameroon. The first approach is a method of progressive supervised classification, where a single class is extracted at the same moment, by using 7 parameters of texture stemming from the run length method. Three classes of texture were extracted by this method and the images from the three classes were merged by the red green blue coloured composition to produce the final map. For purposes of comparison, a not supervised classification was applied to the same image. The applied not supervised classification uses parameters of texture stemming from the co‐occurrence matrix method, and it lays on the detection of the peaks of a histogram. The results obtained by the two methods are coherent, and the validation of the results was made by observations during a recent mission on the site of study.     

Evaluation of diverse classification approaches for land use/cover mapping in a Mediterranean region utilizing Hyperion data

Information on Earth's land surface cover is commonly obtained through digital image analysis of data acquired from remote sensing sensors. In this study, we evaluated the use of diverse classification techniques in discriminating land use/cover types in a typical Mediterranean setting using Hyperion imagery. For this purpose, the spectral angle mapper (SAM), the object-based and the non-linear spectral unmixing based on artificial neural networks (ANNs) techniques were applied. A further objective had been to investigate the effect of two approaches for training sites selection in the SAM classification, namely of the pixel purity index (PPI) and of the direct selection of training points from the Hyperion imagery assisted by a QuickBird imagery and field-based training sites. Object-based classification outperformed the other techniques with an overall accuracy of 83%. Sub-pixel classification based on the ANN showed an overall accuracy of 52%, very close to that of SAM (48%). SAM applied using the training sites selected directly from the Hyperion imagery supported by the QuickBird image and the field visits returned an increase accuracy by 16%. Yet, all techniques appeared to suffer from the relatively low spatial resolution of the Hyperion imagery, which affected the spectral separation among the land use/cover classes.     

Development of a modified neural network-based land cover classification system using automated data selector and multiresolution remotely sensed data

Integrating multiple images with artificial neural networks (ANN) improves classification accuracy. ANN performance is sensitive to training datasets. Complexity and errors compound when merging multiple data, pointing to needs for new techniques. Kohonen's self-organizing mapping (KSOM) neural network was adapted as an automated data selector (ADS) to replace manual training data processes. The multilayer perceptron (MLP) network was then trained using automatically extracted datasets and used for classification. Two hypotheses were tested: ADS adapted from the KSOM network provides adequate and reliable training datasets, improving MLP classification performance; and fusion of Landsat thematic mapper (TM) and SPOT images using the modified ANN approach increases accuracy. ADS adapted from the KSOM network improved training data quality and increased classification accuracy and efficiency. Fusion of compatible multiple data can improve performance if appropriate training datasets are collected. This proved to be a viable classification scheme particularly where acquiring sufficient and reliable training datasets is difficult.     

高分三号影像水体信息提取

国内外针对陆地水体信息提取、洪涝灾害快速响应方面具有较深入的研究,但是多采用发展较早、图像质量可靠的可见光影像及国外星载SAR影像。中国合成孔径雷达（SAR）卫星高分三号（GF-3）已获取了大量多极化、全极化SAR数据,为了将GF-3影像快速应用到环境保护、水资源管理等行业中,本研究分析了水体与其他目标具有的不同后向散射特性,将阈值分割法与马尔可夫随机场（MRF）相结合,发展了一种检测精度较高、自动化程度强的水体信息提取方法。该方法首先通过直方图统计的方法对不同成像模式、不同极化的GF-3影像进行后向散射强度分析,在阈值分割的研究基础上,比较了最大类间方差法（Otsu）和Kittler and Illingworth（KI）二值化法在水体-非水体分类中的效果。然后结合DEM和GF-3轨道参数排除因阴影现象产生的辐射失真对图像概率分布的影响,得到初始的水体信息分布图,再经过Fisher变换和马尔可夫随机场（MRF）的迭代运算,综合利用GF-3影像的多极化信息和空间上下文信息,以最大后验概率准则输出最终的水体分布图。利用了湖南省东北部不同成像模式的两景GF-3影像进行试验,在成像时间接近的光学影像中随机选择检验样点进行精度评价。实验结果表明,KI方法在GF-3水体提取应用中比Otsu方法具有更强的优势,剔除图像阴影区域后,自动化确定的阈值与目视解译阈值更加接近,通过MRF模型优化以后,实现了对水体信息的连贯提取,对图像噪声具有较强的抑制作用。本研究对水体目标的提取精度均达到了85%以上,实验结果精度优于基于光学影像的水体指数法,整个流程需要很少的人工经验参与,具有自动化程度强、检测精度高的优势。     

Local Contrast Based Adaptive SAR Speckle Filter

In this paper, we propose an adaptive filtering technique for Synthetic Aperture Radar (SAR) images. A new windowing technique is introduced where the total window is divided into five equal sized overlapping sub-windows. The pixel to be filtered is a part of each of these sub-windows. A weighted mean of all sub-windows is computed for the pixel under consideration. The weights are accounted from a measure of heterogeneity calculated for each sub-windows. The filter is able to adapt automatically and adjust the speckle suppression strength based on local statistics. This allows the filter to preserve edges while strongly suppressing speckle over homogeneous areas. The proposed filter was compared with some well known SAR filtering techniques in terms of speckle suppression and edge preservation ability. Several experiments were performed on datasets acquired from both air-borne and space-borne SAR platforms. Some well known indices were used for quantitative comparison with other filters. Among the filters compared, the proposed filter shows good speckle suppression ability while still exhibiting reasonable edge preservation ability.