SAR Image Classification Research Articles

Characterization of the Texture of Digital Images by Variography Approach: An Application to the Classification of SAR Images

Characterization of the Texture of Digital Images by Variography Approach: An Application to the Classification of SAR Images This paper presents a method of texture modelling using geostatistic theory. From variographics abacus and variogram proprieties, fractal and exponential models have been used to characterize Brodatz textures. In this approach, a texture is modelled by a vector called feature vector whose components are parameters characterizing the experimental variogram, notably the “Slope”, the “Range”, the “Landing” and the “Fractal Dimension (FD)”.

Classification of SAR Images Based on Entropy

SAR image classification is the progression of separating or grouping an image into different parts. The good feat of recognition algorithms based on the quality of classified image. The good recital of recognition algorithms depend on the quality of classified image. The proposed classification method is hierarchical: classes which are difficult to distinguish are grouped.An important problem in SAR image application is accurate classification. In this paper, we developed a new methodology of SAR image Classification by Entropy. The severance between different groups or classes is based on logistic and multi-nominal regression, which finds the best combination of features to make the separation and at the same time perform a feature selection depending on Grouped -Entropy value.

Unsupervised Amplitude and Texture Classification of SAR Images With Multinomial Latent Model

In this paper, we combine amplitude and texture statistics of the synthetic aperture radar images for the purpose of model-based classification. In a finite mixture model, we bring together the Nakagami densities to model the class amplitudes and a 2-D auto-regressive texture model with t-distributed regression error to model the textures of the classes. A non-stationary multinomial logistic latent class label model is used as a mixture density to obtain spatially smooth class segments. The classification expectation-maximization algorithm is performed to estimate the class parameters and to classify the pixels. We resort to integrated classification likelihood criterion to determine the number of classes in the model. We present our results on the classification of the land covers obtained in both supervised and unsupervised cases processing TerraSAR-X, as well as COSMO-SkyMed data.

A learning-based target decomposition method using Kernel KSVD for polarimetric SAR image classification

In this article, a learning-based target decomposition method based on Kernel K-singular vector decomposition (Kernel KSVD) algorithm is proposed for polarimetric synthetic aperture radar (PolSAR) image classification. With new methods offering increased resolution, more details (structures and objects) could be exploited in the SAR images, thus invalidating the traditional decompositions based on specific scattering mechanisms offering low-resolution SAR image classification. Instead of adopting fixed bases corresponding to the known scattering mechanisms, we propose a learning-based decomposition method for generating adaptive bases and developing a nonlinear extension of the KSVD algorithm in a nonlinear feature space, called as Kernel KSVD. It is an iterative method that alternates between sparse coding in the kernel feature space based on the nonlinear dictionary and a process of updating each atom in the dictionary. The Kernel KSVD-based decomposition not only generates a stable and adaptive representation of the images but also establishes a curvilinear coordinate that goes along the flow of nonlinear polarimetric features. This proposed approach was verified on two sets of SAR data and found to outperform traditional decompositions based on scattering mechanisms.

THE LOW BACKSCATTERING TARGETS CLASSIFICATION IN URBAN AREAS

Abstract. The Polarimetric and Interferometric Synthetic Aperture Radar (POLINSAR) is widely used in urban area nowadays. Because of the physical and geometric sensitivity, the POLINSAR is suitable for the city classification, power-lines detection, building extraction, etc. As the new X-band POLINSAR radar, the china prototype airborne system, XSAR works with high spatial resolution in azimuth (0.1 m) and slant range (0.4 m). In land applications, SAR image classification is a useful tool to distinguish the interesting area and obtain the target information. The bare soil, the cement road, the water and the building shadow are common scenes in the urban area. As it always exists low backscattering sign objects (LBO) with the similar scattering mechanism (all odd bounce except for shadow) in the XSAR images, classes are usually confused in Wishart-H-Alpha and Freeman-Durden methods. It is very hard to distinguish those targets only using the general information. To overcome the shortage, this paper explores an improved algorithm for LBO refined classification based on the Pre-Classification in urban areas. Firstly, the Pre-Classification is applied in the polarimetric datum and the mixture class is marked which contains LBO. Then, the polarimetric covariance matrix C3 is re-estimated on the Pre-Classification results to get more reliable results. Finally, the occurrence space which combining the entropy and the phase-diff standard deviation between HH and VV channel is used to refine the Pre-Classification results. The XSAR airborne experiments show the improved method is potential to distinguish the mixture classes in the low backscattering objects.

Random Forests as a tool for estimating uncertainty at pixel-level in SAR image classification

It is widely acknowledged that model inputs can cause considerable errors in the model output. Since land cover maps obtained from the classification of remote sensing data are frequently used as input to spatially explicit environmental models, it is important to provide information regarding the classification quality of the produced map. Map quality is generally assessed at the global or class-specific level, using standard methods based on the confusion matrix. Unfortunately, these accuracy measures do not provide information regarding the spatial variability in classification quality. In this paper, we introduce Random Forests for the probabilistic mapping of vegetation from high-dimensional remote sensing data and present a comprehensive methodology to assess and analyze classification uncertainty based on the local probabilities of class membership. We apply this method to SAR image data in order to investigate whether multi-configuration in the dataset decreases the local uncertainty estimates. Polarimetric L- and C-band EMISAR data, acquired in April, May, June and July of 1998, and covering the agricultural Foulum test site in Denmark, are used. Results show that multi-configuration in the dataset decreases the classification uncertainty for the different agricultural crops as compared to the single-configuration alternative. Furthermore, the uncertainty assessment reveals lower confidence for the classification of (mixed) pixels at the field edges, and for some fields an uncertainty pattern is observed which is hypothesized to be caused by field preparation practices and cropping system. This study demonstrates that uncertainty assessment provides valuable information on the performance of land cover classification models, both in space and time. Moreover, uncertainty estimates can be easily assessed when using the Random Forests algorithm.

Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification

In this paper, we propose a novel scheme of polarimetric synthetic aperture radar (PolSAR) image classification. We apply Laplacian eigenmaps (LE), a nonlinear dimensionality reduction (NDR) technique, to a high-dimensional polarimetric feature representation for PolSAR land-cover classification. A wide variety of polarimetric signatures are chosen to construct a high-dimensional polarimetric manifold which can be mapped into the most compact low-dimensional structure by manifold-based dimensionality reduction techniques. This NDR technique is employed to obtain a low-dimensional intrinsic feature vector by the LE algorithm, which is beneficial to PolSAR land-cover classification owing to its local preserving property. The effectiveness of our PolSAR land-cover classification scheme with LE intrinsic feature vector is demonstrated with the RadarSat-2 C-band PolSAR data set and the 38th Research Institute of China Electronics Technology Group Corporation X-band PolInSAR data set. The performance of our method is measured by the separability in the feature space and the accuracy of classification. Comparisons on the feature space show that the LE intrinsic feature vector is more separable than different original feature vectors. Our LE intrinsic feature vector also improves the classification accuracy.

Multi-temporal SAR Images Classification Using Case-based Reasoning for Application of Land Use and Land Cover Change

In this paper,we investigate a case-based reasoning(CBR) method for the classification of multi-temporal SAR images with the aid of ancillary information.Our scheme for the problem of multi-temporal SAR images classification comprises four main steps,including SAR image processing,construction of case library,case-based classification and post-classification processing.During the construction of case library,we employ a spatial-temporal analysis technique to remove fake cases,which can guarantee cases with high credibility.In the implementation of case-based classification,we propose a stratified similarity assessment and use it for the case-based matching.After that,we investigate an object-oriented post-classification method which takes the shape of land use region into account,as a result,it leads to a more meaningful classification,and the regenerate land use image or map can be easier compared and combined with usual GIS data.A series of multi-temporal SAR images for 2000 and 2004 are used for our experiments,the results show the classification accuracy can achieve up to 85%~90%.

Application of K-means Under Probability Model in Classification of SAR Image

遥感图像分类是将图像所有的像元按其性质分为若干个类的技术过程。常用的分类方法有监督分类和非监督分类。监督分类需要有足够的先验知识; 非监督算法是按照某种相似性准则对样本进行合并或分类, 所以并不需要有先验知识。但是传统的非监督分类算法存在着分类精度较低, 分类结果比较粗糙等缺点。例如K-means 算法、isodata 算法等。提出一种基于高斯分布和瑞利分布两种概率模型的K-means 算法, 从结果可以看出, 分类效果要明显优于传统的K-means 算法。

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.

Agricultural crop-type classification of multi-polarization SAR images using a hybrid entropy decomposition and support vector machine technique

This article presents the application of a hybrid classification technique of entropy decomposition and support vector machine (EDSVM) for crop-type categorization. It takes the advantage of the desired parameters from the entropy decomposition (ED) method and the statistical learning method based on the support vector machine (SVM) method that determines the optimal separation between classes in a higher dimensional feature space to improve on the existing classification results. ED is capable of extracting valuable decomposed parameters of entropy H and alpha α for image interpretation with analysis of the underlying scattering mechanisms. H demonstrates the randomness of the underlying scattering mechanisms and α is used to define the type of scattering mechanisms. However, in the application of agricultural crops where the scattering mechanisms of the crops are quite similar to each other, the distribution of the H and α in the H–α feature space overlaps from one class to another. Moreover, the drawback of ED is the arbitrariness of the boundaries for each class. To overcome this issue, SVM classifier is deployed to determine the decision boundaries by projecting the training sets of the classes into higher dimensional feature space. Hence, the hybrid EDSVM is developed to provide an alternative solution to improve the classification accuracy. In this article, EDSVM classifier is applied on a multi-crop field Airborne Synthetic Aperture Radar (AIRSAR) image of Flevoland in the Netherlands and the robustness of the classifier is evaluated. The classification is done with the purpose of separating the different types of crops with the characteristics of the scattering mechanism. At the same time, a hybrid entropy decomposition and neural network (EDNN) classifier method is developed to validate the effectiveness of the EDSVM classifier. As a result, EDSVM is proved to be robust and to yield a superior result compared with neural network (NN), SVM and EDNN classifiers.

Iterative Classification of Polarimetric SAR Image Based on Freeman Decomposition and Scattering Entropy

该文提出了一种基于Freeman分解与散射熵的极化SAR图像迭代分类新方法。该方法首先通过Freeman分解提取3种散射机理成分的功率，同时通过H/ 分解提取地物的散射熵；再利用这4个表征地物特性的参数将极化SAR图像中的地物划分为9个初始类，最后使用Wishart分类器对初始类进行迭代分类得到最终的结果。该方法合理利用了地物的极化散射信息，能够取得较好的分类效果，同时运算量也比较小。实测极化SAR数据的实验结果验证了该方法的有效性。

Feature Selection and Classification of Polarimetric SAR Images Using SVM

该文提出一种新的利用SVM的特征选择算法，并将其融入到极化SAR图像分类过程中，构成一种新的基于SVM的分类方法。其中，特征选择算法利用支持向量个数作为特征评估指标，并以顺序后退法作为搜索策略。真实数据的实验结果表明，该分类方法能有效降低SVM分类器对自身参数的敏感性，与利用原始特征集和经典的RELIEF-F的分类方法相比，该方法能以更少(或相当)的特征个数，在更广泛的SVM参数取值范围内获得更高的分类精度。

Polarimetric SAR Image Classification with High Frequency Component Derived from Wavelet Multi Resolution Analysis: MRA

A method for polarimetric Synthetic Aperture Radar: SAR image classification with high frequency component derived from wavelet Multi-Resolution Analysis: MRA is proposed. Although it is well known that polarization signature derived from fully polarized SAR data is useful for SAR image classifications, it is still unknown how to utilize the polarization signature in the image classification. High frequency component of the polarization signature calculated with the fully polarized SAR data is taken as one of the features utilizing in the classification into account. Thus improvement of classification performance is achieved for the proposed classification method of which such feature is included in the feature space for the Maximum Likelihood based classification method.

Extraction and Geometrical Accuracy of Double-bounce Lines in High Resolution SAR Images

In TerraSAR-X spotlight data features of man-made objects in urban areas become visible. In a case study, this paper presents results of a precision and geometrical accuracy investigation of extracted double-bounce lines in SAR images. Two TerraSAR-X (TSX) acquisitions of a complex urban scene are compared to simulated SAR images. Using a new line detection method, double-bounce lines are extracted from simulated and real imagery with sub-pixel accuracy. The deviation of an extracted double-bounce line polygon with regard to both an interpolated line and ground truth is analyzed and discussed. First, it is shown that Gaussian functions model the deviation of the interpolated line from the polygon sufficiently well. Second, the absolute geometrical accuracy of the extracted double-bounce lines is evaluated with respect to ground truth. Results of the case study confirm that double-bounce lines provide reliable geometrical information, for instance, for building extraction and SAR image classification.

Classification of Polarimetric SAR Image Based on Support Vector Machine Using Multiple-Component Scattering Model and Texture Features

The classification of polarimetric SAR image based on Multiple-Component Scattering Model (MCSM) and Support Vector Machine (SVM) is presented in this paper. MCSM is a potential decomposition method for a general condition. SVM is a popular tool for machine learning tasks involving classification, recognition, or detection. The scattering powers of single-bounce, double-bounce, volume, helix, and wire scattering components are extracted from fully polarimetric SAR images. Combining with the scattering powers of MCSM and the selected texture features from Gray-level cooccurrence matrix (GCM), SVM is used for the classification of polarimetric SAR image. We generate a validity test for the proposed method using Danish EMISAR L-band fully polarimetric data of Foulum Area (DK), Denmark. The preliminary result indicates that this method can classify most of the areas correctly.

Polarimetric SAR Image Classification Using Multifeatures Combination and Extremely Randomized Clustering Forests

Terrain classification using polarimetric SAR imagery has been a very active research field over recent years. Although lots of features have been proposed and many classifiers have been employed, there are few works on comparing these features and their combination with different classifiers. In this paper, we firstly evaluate and compare different features for classifying polarimetric SAR imagery. Then, we propose two strategies for feature combination: manual selection according to heuristic rules and automatic combination based on a simple but efficient criterion. Finally, we introduce extremely randomized clustering forests (ERCFs) to polarimetric SAR image classification and compare it with other competitive classifiers. Experiments on ALOS PALSAR image validate the effectiveness of the feature combination strategies and also show that ERCFs achieves competitive performance with other widely used classifiers while costing much less training and testing time.

THE APPLICATION OF THE WAVELET TEXTURE METHOD TO THE CLASSIFICATION OF SINGLE-BAND, SINGLE-POLARIZED AND HIGH-RESOLUTION SAR IMAGES

This paper has classified the high-resolution SAR images obtained along the Huaihe River in July 2003. The authors first analyzed the high-resolution SAR image and pointed out the disturbing factors. After filtering the noise, the SAR image was decomposed with wavelet transform and the energy of the textures was computed by selecting a small window. Finally, the BP algorithm was used to classify the textures. The results indicate that, with the wavelet texture classification method, the high classification precision for the single-band, single-polarized and high-resolution SAR images can be obtained. This paper has also analyzed the shortages of the texture classification method for high-resolution SAR images and pointed out the research direction of the high-resolution SAR image classification.

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.

Improving hydrological information acquisition from DEM processing in floodplains

AbstractExtraction of hydrological information from digital elevation models (DEMs) is a required step when conducting any spatially distributed hydrological modelling. In particular, automated methods are proposed to extract the drainage structure from the DEM. However, a realistic river network is not always derived from conventional DEM processing methods. Indeed, inaccuracy occurs in flat areas corresponding to floodplains. In these areas, additional sources of information are required to extract the correct drainage direction from the DEM. In this study, it is demonstrated that traditional approaches of DEM‐preprocessing such as the commonly known ‘stream burning’ fail to provide correct maps of drainage directions and catchment areas when the extension of flat areas is large. A new method is proposed to take advantage of available imagery data. This method is based on a ‘double DEM burning’ process: DEM is first burned in the main rivers using the channel network, and then in the floodplain using the spatial distribution of floodplains provided by classified satellite images. In this sense, the method has been referred to as the floodplain burning approach (or simply FB approach). Spatial distribution of floodplains is derived from a multitemporal SAR image classification. A system of equations is used to vary the elevation offset required to be ‘burnt’ in each cell representing the floodplain, according to the minimal distance from the channel network, which is calculated by a distance transformation. The FB approach was applied to a sub‐basin located within the larger Amazon River basin. The region is characterized by large floodplain extensions. Basin delineation maps derived from the new method were compared with those obtained from the traditional stream burning method and highlighted more realistic results. Copyright © 2008 John Wiley & Sons, Ltd.