合理尺度纹理分析遥感影像分类方法研究

纹理分析是提高遥感影像分类精度的重要手段之一。纹理特征与地物类别尺度密切相关,应用纹理特征进行遥感影像分类, 关键在于纹理尺度的确定。对于灰度共生矩阵纹理分析来说,就是选择大小合适的纹理窗口。根据样本半变异值在较小范围内有较 大变化的特性,研究遥感影像相邻像素之间的空间关系,将半变异值开始趋于恒值时所对应的步长作为纹理分析的窗口大小,并在 纹理特征提取过程中针对每一个像素,在最大似然分类结果的约束下,适时改变其窗口大小,提取纹理特征,提出一种合理尺度纹 理分析的遥感影像分类方法。最后,选择北京市昌平区2006年SPOT 5遥感影像,利用TitanImage二次开发环境实现了该方法。实践 证明,该方法能有效提高遥感影像的分类精度。     

A Neural Network Landuse Classifier for SAR Images Using Textural and Fractal Information

Abstract

Artificial neural networks (ANN) have recently been popularly used in image classification. Input features to most ANNs are extracted based on a one class per pixel basis. This requires a large number of training samples and thus a slow training rate. In this paper, we describe the use of a windowing technique to extract textural features such as average intensity, second moment of intensity histogram and fractal surface dimension from an image. This method of image characterization reduces the number of training samples efficiently, yet retains a reasonable overall classification accuracy. The ANN is trained based on the back‐error propagation algorithm. The method is applied for landuse classification of Synthetic Aperture Radar (SAR) images. An example is given for a site in Kedah State, Malaysia. The SAR images (HH,HV,VV) were taken by the Canadian Centre for Remote Sensing (CCRS) CV‐580 airborne C‐band SAR system in November 1993 during their GlobeSAR mission in Malaysia. These multi‐polarization SAR images are co‐registered with a Landsat Thematic Mapper (TM) channel 5 image from same area. An overall classification accuracy of about 86.95% is achieved using windowing technique, as compared to 68.22% based on one class per pixel approach. This shows that through fractal and textural information, the windowing technique when applied in an ANN classifier has a great potential in remote sensing applications.     

基于纹理特征的遥感影像监督分类

影像分类技术是遥感影像分析与解译的重要基础。纹理特征是影像的重要特征,本文主要实现基于纹理特征的遥感影像监督分类。首先对地物样本进行提取,通过样本训练统计各类地物纹理特征向量,建立纹理特征库;然后以各类地物的特征向量作为基准,采用最短距离分类器对影像进行分类;最后采用混淆矩阵对分类结果进行精度评定,并与ERDAS专业软件分类结果进行对比分析。实验证明,本分方法取得了与ERDAS软件相当的分类效果,从而验证本文方法的可靠性。     

Ann Based Robust LULC Classification Technique Using Spectral, Texture and Elevation Data

Albeit the advent of fast computing facilities, digital image classification of remotely sensed data is still remain the topic of research. This might be due to the reason that the ancillary information such as texture and topography is absent in image classification. Since two decades, texture is widely applied in image classification but there is no explicit icon in most popularly used remote sensing software. Hence the aim of this study is to classify the Landsat ETM+ captured in 2000 using spectral information, topographic information and texture information. This study helps to throw light into statistical texture analysis i.e., the effect window size i.e., 3?×?3 to 9?×?9, on image classification. The ability of Grey Run Length Matrix (GRLM), which is computationally complex compared to industrially well-known Grey Level Co-occurrence Matrix (GLCM) but encompasses greater potential to discriminate between two classes, is explored. Eight spectral bands, 11 texture parameters extracted from Landsat ETM+ data and elevation, slope, aspect extracted from DEM data are classified individually using Artificial Neural Network (ANN) and the individually classified information is integrated using endorsement theory. Validations of classified results are performed using Google Maps and Landmap services updated in 2009. The results are compared with Maximum Likelihood classification (MLC) and hence all the evidence (spectral, texture and topography) with 5?×?5 texture window provided maximum classification accuracy of 70.44 %.     

基于纹理特征的SAR影像各拉丹冬冰川信息提取

冰川面积是监测冰川变化信息的重要参数。本文以各拉丹东地区为例,根据冰川区域特有的纹理特征,选取时间间隔为35天的ENVISAT ASAR干涉对,利用灰度共生矩阵提取纹理特征,通过波段组合进行监督分类,进而提取研究区冰川面积。同时以Landsat TM光学影像为依据,评价利用纹理特征提取结果的精度。研究表明:基于纹理特征并利用SAR影像提取冰川面积的方法是可行的,为提取冰川信息提供了又一可靠手段。     

广义马尔可夫随机场及其在多光谱纹理影像分类中的应用

在二维马尔可夫随机场模型的基础上，提出顾及波段间的空间相关性，发展了一种适用于多光谱纹理影像分类的广义马尔可夫随机场模型。鉴于广义马尔可夫随机场模型的复杂性，利用最大伪似然法建立了求解模型参数的简化方程式，实现了纹理特征的快速提取。结合提取的纹理特征影像和光谱特征影像，采用概率松弛算法实现影像的分类。实验证明，提出的基于广义马尔可夫随机场的多光谱纹理影像分类算法克服了传统的基于光谱特征的分类算法的局限性，提高了纹理影像的分类精度。     

面向对象的高分辨率遥感影像建筑物震害信息提取

建筑物的倒损信息是震后灾害评估的一项重要指标。文中应用震后高分辨率遥感影像数据,采用面向对象分类方法,以最优分割参数对影像进行分割,构建多尺度影像对象层次结构。通过影像对象的光谱、形状、纹理等特征及空间拓扑关系建立分类规则库,提取基本完好、受损和完全倒塌三类破坏等级的建筑物震害信息。结果表明,面向对象分类方法能够实现提取三类等级的建筑物震害信息,从而满足地震灾害快速评估要求。     

基于ERDAS的遥感影像分类方法研究

为了提高遥感影像分类精度,对传统的非监督分类、监督分类和专家分类进行机理分析,提出将影像中的纹理信息作为专家知识改进分类精度的技术方案。以胶州市QuickBird遥感影像作为试验数据,基于ERDAS IMAG-INE 8.6软件平台,对非监督分类、监督分类和专家分类进行实验数据比较分析,实验数据表明改进的专家分类方法分类精度最高,由于纹理信息参与专家分类,可较好地解决“同谱异物”和“同物异谱”对分类的干扰,优化分类后的影像,提高信息提取的准确度。     

The Utility of Very High Spatial Resolution Images to Identify Urban Objects

Abstract

Landsat MSS, TM and SPOT XS imageries were used in conjunction with unsupervised, supervised and hybrid classilication techniques to classify land cover types in semi‐arid savannas of Mathison Pastoral Station in the Katherine region of northern Australia. Accuracy assessment was based on field data from 246 ground survey sites over a 745‐km² study area. Of 14 land cover classes identified by traditional mapping means, all combinations of imageries and classification techniques differentiated at least seven land cover types. The overall accuracy for these classifications ranged between 43% and 67%. SPOT XS image delivered the best accuracy followed by TM and MSS; unsupervised classification performed better than supervised and hybrid methods. User's and producer's accuracy of individual land units ranged from 0% to 100%. Riparian woodlands, woodland on limestone slopes, shrubland on clay plains, woodland on limestone plains and shadows were the best‐mapped classes. The land units that were associated with undulating hills were not mapped accurately. However, incorporation of a digital elevation model (DEM) in a GIS improved the overall accuracy. The user's and producer's accuracy of dominant land cover types were also enhanced. The classification results and the efficacy of the techniques at Mathison were similar to those found for a nearby semi‐arid area (Kidman Springs) about 200 km from Mathison. However, the overall accuracy was lower at Mathison than at Kidman Springs. Spectral classification masks were developed from the SPOT XS and TM imageries at Kidman Springs, and were applied to classify SPOT XS and TM imageries at Mathison. Initial results showed that the classification mask could be successfully extrapolated to map dominant land cover types but only with moderate accuracy (50%).     

基于GMRF-SVM的高分辨率遥感影像目标区域划分方法

高分辨率遥感影像数据量大、细节丰富并呈现出一定的尺度依赖性,单一尺度遥感影像分割难以同时兼顾影像的宏观和微观特征,这成为制约遥感信息自动化提取技术发展的瓶颈之一。对此本文提出了基于特征的多尺度高分辨率遥感信息提取技术框架,并分析了其对于大尺度海量数据信息提取与目标识别工作具有的理论及实践意义。根据影像光谱或纹理等特征,提出采用GMRF-SVM方法在大尺度上进行分类的目标区域划分方法。从大尺度信息提取的角度来看,该方法综合了GMRF纹理分类和SVM少量样本模式识别的优势,便于先验知识的融合,无论从花费时间还是分类处理效果上,都远远优于直接采用GMRF进行分割所取得的效果,对于后面的信息提取和目标识别来说更具有实际意义。     

Multiple band digital orthophoto quadrangle data: A source for generating land use maps

Abstract

The purpose of this study was to investigate the use of color infrared‐digital orthophoto quadrangle (CIR‐DOQ) data to generate land use/land cover (LULC) maps and to incorporate them as data layers in geographic information systems (GIS) involving various resource management scenarios. The Danville 7.5‐minute quadrangle located in the southern part of Limestone and Morgan counties, Alabama, was used as the study site. Data for the special CIR‐DOQ were generated by scanning four 9x9 inch CIR aerial photographs at a uniform pixel sample grid of 25 microns resulting in 2 meters ground sample resolution. One‐half of the quadrangle was used to identify training sites for performing a supervised classification of the data and the other half to verify the accuracy of the classification. The CIR‐DOQ data were found to be adequate for using a supervised classification algorithm to differentiate major LULC classes, resulting in a classification accuracy of 93 percent. The superior spatial quality of the data over commençai satellite data affords resource managers an opportunity to more effectively study land cover and surface hydrological properties of an area, soil moisture and surface soil textures, as well as differentiate among vegetation species, using remote sensing techniques. However, caution must be exercised when using multispectral classification techniques to classify mosaicked CIRDOQ data because of the image enhancements used to generate the final product. In its present form, there are some limitations to the use of the data for performing spectral classifications. Hozvever, the high spatial resolution of the data enables even the novice resource planner to effectively use the data in visual interpretations of major LULC classes.     

极化SAR参数优化与光学波谱相结合的面向对象土地覆盖分类

提出一种基于极化参数优化的面向对象分类方法。该方法结合光学和SAR数据,有效提高了对地物的识别能力。本文方法的关键在于:在■分解中,使用光学影像指导SAR影像选择同质点,使其更精确地估计极化参数并结合光学波谱信息作为输入特征;使用面向对象的分类方法,仅将光学影像作为分割输入,避免SAR噪声引起的分割错误。以美国Bakersfield地区的Sentinel-1/2数据为例,确定7种地物类型,对比分析不同输入与不同分类器对分类结果的影响。研究表明,优化输入参数在纹理丰富区域能够有效提高分类精度;面向对象的分类结果更加稳定并较好地维持地表几何特征;改进分类方法较传统分类方法总体精度提高了近10%,达到92.6%。     

SPOT5影像纹理特征提取与土地利用信息识别方法

本文以太湖流域西苕溪上游安吉地区SPOT5影像600像元×600像元为试验区,首先采用主成分分析对SPOT5影像进行数据压缩和几何信息增强,再采用小波分析方法对影像进行滤波和噪音处理,利用灰度共生矩阵对高分辨率图像的纹理信息进行分析,以对比度和熵为统计指标,确定对比度和熵的最佳阈值,进行边界匹配和图像的分割,将此分割结果与NDVI阈值法分类结果进行叠合,得到最终的分类结果。试验结果表明:将纹理分析方法应用于图像分类中可区分光谱混淆的地物,光谱与纹理特征结合得到的分类精度高于单纯依靠光谱特征进行分类和单纯依靠纹理分类的分类精度。     

引入商空间粒度计算的全极化SAR影像分类

为了充分利用不同极化特征信息,并将其有效地结合,提出一种结合粒度计算的全极化合成孔径雷达（synthetic aperture radar,SAR）影像分类方法。在不同极化目标分解特征组合的基础上引入影像纹理信息,利用光滑支持向量机（smooth support vector machine,SSVM）对不同特征组合进行类别划分获得粗粒度空间,采用商空间对粗粒度进行合并;根据全极化SAR影像分布特性,以相干矩阵作为新的特征矢量,利用Wishart测度代替传统欧氏距离对差异粒度进行推理,通过合并推理结果与合成论域,获得精细分类结果。采用L波段San Francisco地区和荷兰Flevoland地区的全极化SAR影像进行分类试验,结果表明:利用SSVM算法对全极化SAR影像进行粗粒度划分,并采用Wishart距离对差异粒度推理综合,总体分类效果优于结合纹理信息的Cloude及Yamaguchi4分类结果,且优于基于线性特征融合进行监督分类方法。     

一种适用于多类别遥感图象分类的新方法——复合神经网络分类方法

该文提出一种由多层神经网络与自组织神经网络相结合进行类别遥感图象分类的复合神经网络分类方法。第１步半训练样本按其统计特征分成若干组，用不同级别的训练样本分别训练ＢＰ网络。第２步将这些训练好的ＢＰ网络并联构成有监督分类器，对遥感图象进行有监督分类。第３步用ＢＰ网络的分类结果对Ｋｏｈｏｎｅｎ网络进行自组织训练，用训练好的Ｋｏｈｏｎｅｎ网络构造无监督分类器，对遥感图象进行细分。通过对ＳＰＯＴ遥感图象的分     

A simple cleaning procedure for improvement of training site statistics

For improving the effectiveness of supervised training, a simple cleaning procedure which operates by selectively dropping training site pixels based on the Mahalanobis distance and class probability has been proposed. The method is iterative and takes into account the spectral overlap in all image bands with all the user specified classes. The procedure results in greater classification accuracy with narrower confidence interval. On the test data, Bhattacharrya distance measure of class separability unproved front an average value of 1.9373 to 1.9797 with a maximum change for a class pair from 1.2671 to 1.9052. The overall classification accuracy increased from 94.74 ±0.64 to 99.63 ± 0.19.     

The Nature and Classification of Unlabelled Neurons in the Use of Kohonen's Self-Organizing Map for Supervised Classification

Kohonen's Self‐Organizing Map is a neural network procedure in which a layer of neurons is initialized with random weights, and subsequently organized by inspection of the data to be analyzed. The organization procedure uses progressive adjustment of weights based on data characteristics and lateral interaction such that neurons with similar weights will tend to spatially cluster in the neuron layer. When the SOM is associated with a supervised classification, a majority voting technique is usually used to associate these neurons with training data classes. This technique, however, cannot guarantee that every neuron in the output layer will be labelled, and thus causes unclassified pixels in the final map. This problem is similar to but fundamentally different from the problem of dead units that arises in unsupervised SOM classification (neurons which are never organized by the input data). In this paper we specifically address the problem and nature of unlabelled neurons in the use of SOM for supervised classification. Through a case study it is shown that unlabelled neurons are associated with unknown image classes and, most particularly, mixed pixels. It is also shown that an auxiliary algorithm proposed here for assigning classes to unlabelled neurons performs with the same success as that experienced with Maximum Likelihood.     

Comparison and Integration of Radar and Optical Data for Land Use/Cover Mapping

Abstract

This study examined the complementarity of spaceborne radar and optical data for surface feature identification. RADARSAT data sets were assessed independently and in combination with Landsat Thematic Mapper (TM) multispectral data. The primary methodology was spectral signature extraction and the application of a statistical decision rule to classify the surface features for a site near Kericho, Kenya. Relative accuracy of the resultant classifications was established by digital integration and comparison to reference information derived from field visitation. Speckle filtering was a great improvement over the poor results achieved with the unfiltered, original radar data but still not adequate for accurate land cover classification. The extraction and use of Variance texture measures was found to be very advantageous. The overall results were not significant improvements over speckle removal (6% increase) but several individual classes, forest and urban, had excellent results with texture. Combinations of radar with Landsat TM greatly improved results, achieving near perfect classification of all individual classes. The highest overall accuracy was achieved with a merger that included the best individual texture image and six reflectance bands of the TM data. The systematic strategy of this study, determination of the best individual method before introducing the next procedure, was effective in managing a very complex, almost infinite set of analysis possibilities.     

利用SVM的全极化、双极化与单极化SAR图像分类性能的比较

支持向量机(SVM)以其在小训练样本时良好的分类性能,目前已广泛应用于多个领域.本文在极化SAR图像特征提取基础上,将SVM应用于极化SAR图像分类,定性和定量地比较了全极化、双极化和单极化SAR图像的分类性能,分析了不同的极化组合对分类结果的影响,并根据地物极化散射特性分析了分类精度差异的成因.实测极化SAR数据的实验结果表明,全极化数据能获得最好的分类性能,双极化次之,单极化最低,且在某些情况下,双极化与全极化分类性能接近.     

深度学习的半监督遥感图像检索

遥感图像数据的海量性、多样性和复杂性等特点对遥感图像检索的速度和精度提出了更高的要求,其中特征提取是影响遥感图像检索效果的关键。本文方法首先对遥感图像进行预处理,然后基于稀疏自动编码的方法在大量未标注的遥感图像上进行特征学习得到特征字典,基于卷积神经网络的思想,使用训练出来的特征字典对遥感图像进行卷积和池化得到每幅图像的特征图;接下来使用特征图训练Softmax分类器;最后对待检索图像分类,在同一类别中计算特征间的距离,进而实现遥感图像的检索。实验结果表明,该方法能够有效提高遥感图像检索的速度和准确度。