Unsupervised urban area extraction from SAR imagery using GMRF

A new method is proposed to extract urban areas from SAR imagery using two different Gaussian Markov Random Field (GMRF) models. Firstly, by making an initial segmentation by a watershed algorithm, we adopt a particular GMRF model proposed by Descombes et al. (the model is called RGMRF model, distinguished from the conventional GMRF model) to acquire urban areas. In the first model a part of the urban areas from the SAR image is extracted with some missing detection. Then, taking the first result as a training sample, we use the conventional GMRF model to redo the extraction. In the second model a larger area is detected including all urban areas with some false detection. Finally, we fuse the two results using a region-growing algorithm to form the final detected urban area. Experimental results show that the proposed method can obtain accurate urban areas delineation. The text was submitted by the authors in English.     

Unsupervised classification of polarimetric SAR imagery using large-scale spectral clustering with spatial constraints

Spectral clustering is a very popular approach which has been successfully used in unsupervised classification of polarimetric synthetic aperture radar (PolSAR) imagery. However, due to its high computational complexity, spectral clustering can only be applied to small data sets. This article provides a framework for spectral clustering of large-scale PolSAR data. As computing and processing the pairwise-based affinity matrix is the bottleneck of the spectral clustering approach, we first introduce a representative points-based scheme in which a memory-saving and computationally tractable affinity matrix is designed. The subsequent spectral analysis can be solved efficiently. Second, a simple one-parameter superpixel algorithm is introduced to generate representative points. Through these superpixels, spatial constraints are also naturally integrated into the classification framework. We test the proposed approach on both airborne and space-borne PolSAR images. Experimental results demonstrate its effectiveness.     

Unsupervised building detection in complex urban environments from multispectral satellite imagery

A generic algorithm is presented for automatic extraction of buildings and roads from complex urban environments in high-resolution satellite images where the extraction of both object types at the same time enhances the performance. The proposed approach exploits spectral properties in conjunction with spatial properties, both of which actually provide complementary information to each other. First, a high-resolution pansharpened colour image is obtained by merging the high-resolution panchromatic (PAN) and the low-resolution multispectral images yielding a colour image at the resolution of the PAN band. Natural and man-made regions are classified and segmented by the Normalized Difference Vegetation Index (NDVI). Shadow regions are detected by the chromaticity to intensity ratio in the YIQ colour space. After the classification of the vegetation and the shadow areas, the rest of the image consists of man-made areas only. The man-made areas are partitioned by mean shift segmentation where some resulting segments are irrelevant to buildings in terms of shape. These artefacts are eliminated in two steps: First, each segment is thinned using morphological operations and its length is compared to a threshold which is determined according to the empirical length of the buildings. As a result, long segments which most probably represent roads are masked out. Second, the erroneous thin artefacts which are classified by principal component analysis (PCA) are removed. In parallel to PCA, small artefacts are wiped out based on morphological processes as well. The resultant man-made mask image is overlaid on the ground-truth image, where the buildings are previously labelled, for the accuracy assessment of the methodology. The method is applied to Quickbird images (2.4 m multispectral R, G, B, near-infrared (NIR) bands and 0.6 m PAN band) of eight different urban regions, each of which includes different properties of surface objects. The images are extending from simple to complex urban area. The simple image type includes a regular urban area with low density and regular building pattern. The complex image type involves almost all kinds of challenges such as small and large buildings, regions with bare soil, vegetation areas, shadows and so on. Although the performance of the algorithm slightly changes for various urban complexity levels, it performs well for all types of urban areas.     

Comprehensive urban area extraction from multispectral medium spatial resolution remote-sensing imagery based on a novel structural feature

One of the most important applications of remote sensing is urban area analysis in multispectral images. This article addresses a comprehensive method for urban area extraction in the mentioned images using a combination of classic spectral features and a new structural feature. The spectral features are used for eliminating the non-urban land covers including vegetation, water, shadows, and bright soil. Then the proposed structural feature based on the density of the spectral gradient is utilized for the final separation of urban points (UPs) from non-urban points (NUPs). The proposed method is insensitive to the spectral variation of urban areas caused by variant geographical conditions and coordinates. The proposed approach is applied to a wide variety of geographical areas from Landsat 7 Enhanced Thematic Mapper Plus (ETM+) multispectral data including arid and desert land, mountainous land, and plain area. Furthermore, a reference land-cover map from National Land Cover Data 2001 of USA is used as the ground reference for the accuracy assessment of the proposed method. Results analysis shows better performance of the proposed method in all study sites compared with the other spectral indices and the other methods. In addition, the proposed structural feature has shown promising results compared with the spectral indices when used in its own.     

Quantifying the main urban area expansion of Guangzhou using Landsat imagery

ABSTRACT

This article takes the main urban area of Guangzhou as the study area. Twelve land-use maps were interpreted from Landsat Thematic Mapper images using feature enhancement technology and Naïve Bayes-based weight vector AdaBoost (WV AdaBoost). The study shows that since 1987, with heavily cultivated land being lost and vegetation cover shrinking, the urban area has doubled in size. The effects of human activities on the landscape have become increasingly apparent and complicated. It also finds that the expansion pattern has been transformed from one in which the city’s main urban area engulfed the surrounding residential area to one in which surrounding towns expanded, driven by the development of the main urban area. By analysing the relationship between the social economy, population, and land-use change, we show that the forces driving expansion of the urban area have differed in different periods. The principal driving forces are national policymaking and adjustment, the aggregation and diffusion of population and economic development. Multitemporal land-use maps allow long-term dynamic monitoring of urban land cover in Guangzhou and provide important details of urban expansion and changes in land use. We employed intervals of 2 and 3 years, and our results provide good supporting data for studies of urban extension trends and reasonable urban planning.     

Crop discrimination using multi-temporal SAR imagery

Seven ERS-1 SAR images obtained at different dates during the 1993 crop growing season are used in a study of the potential of multi-temporal SAR for agricultural crop discrimination for an area near Feltwell, Norfolk, UK. The study compares a per-pixel and a per-field approach. Pixel-based classification is based on raw intensity images, temporal subtraction images, filtered images, and texture features. Field-based classification uses the mean back-scatter coefficient derived for each field. Analysis of the contribution of each dataset uses statistical separability measures and confusion matrix methods. The classification algorithms used are maximum likelihood and Kohonen's self-organized feature map (SOM). We find that SAR-based texture features contribute nothing to crop discrimination. Filtered images produce the best result for the per-pixel approach, giving a classification accuracy of around 60%. The use of a SOM for field-based classification produces a classification accuracy greater than 75%. This is not a surprising result, as field-based classifications use averaged data, in which the noise effect is reduced.     

Confusion errors among urban land-cover types on SAR imagery

Urban land-cover maps were produced by interpreting dual-polarized (HH and HV) X-band synthetic aperture radar imagery of Los Angeles, California. These maps were then registered to and compared with an existing 85-category land-use map of the area to determine: (i) specific points of interpretation error (errors of commission) among the types of land cover; and (ii) differences in detectability and misidentification between polarizations. The HH data were much more difficult to interpret than the HV imagery and consequently produced a greater number of errors and types of land-cover confusion. However, there were some land-cover categories which were consistently confused with one another. Those within and between category misidentifications are discussed as they relate to SAR imagery.     

An evaluation of seasat SAR imagery for urban analysis

Digitally processed Seasat SAR imagery of the Denver, Colorado, area is analyzed with regard to the types of urban data that can be detected and/or inferred from satellite-borne L-band systems. Black-and-white images of the scene were generated at three scales to determine the advantages and detail discernible at each level of display. The large-scale imagery was density-sliced to evaluate the feasibility of producing a semiautomated land-cover classification from the SAR data. Gray level classes were assigned colors to aid interpretation and subsequently compared with the black-and-white images to assess the contribution of each technique and benefits of combining the data from both procedures.     

基于多模型融合的SAR图像目标轮廓提取方法

提出一种基于参数活动轮廓模型的多模型融合的合成孔径雷达SAR(Synthetic Aperture Radar)图像目标轮廓提取方法,即在活动轮廓模型Balloon中引入新兴统计分布模型G0分布、基于区域的统计活动轮廓模型和多边缘检测算子模型,获得了一种新的目标轮廓提取方法。基于MSTAR项目的真实SAR图像的实验结果表明,本文所提出的方法能准确地获得SAR图像目标轮廓,可用于执行实际的SAR图像轮廓提取任务,为后续的SAR图像自动识别和特征级图像融合等任务提供了较为优良的输入信息。     

Building detection in an urban area using lidar data and QuickBird imagery

This article presents a hierarchical approach to detect buildings in an urban area through the combined usage of lidar data and QuickBird imagery. A normalized digital surface model (nDSM) was first generated on the basis of the difference between a digital surface model and the corresponding digital terrain model. Then, ground objects were removed according to a height threshold. In consideration of the relief displacement effect in very high resolution remote-sensing imagery, we segmented the nDSM by the region-growing method and used the overlap ratio to avoid over-removing building objects. Finally, the region size and spatial relation of trees and buildings were used to filter out trees occluded by buildings based on an object-based classification. Compared with previous methods directly using the normalized difference vegetation index (NDVI), our method improved the completeness from 85.94% to 90.20%. The overall accuracy of the buildings detected using the proposed method can be up to 94.31%, indicating the practical applicability of the method.     

盲信号分离和序贯滤波的SAR影像水体提取

采用一种新的基于盲信号分离（BSS）和序列非线性滤波方法实现多极化合成孔径雷达（SAR）影像相干斑噪声抑制和水体目标快速提取。SAR影像具有强烈乘性相干斑噪声,影像数据为非高斯分布,但其具体分布形式及参数难以获得。利用基于独立分量分析的盲信号分离方法,不需要知道SAR影像的具体分布,通过对数量化将相干斑噪声转化为与图像数据相互独立的加性噪声,从多极化SAR影像中自动分离出图像数据与相干斑噪声,并自动选择相干斑指数最小的分量为图像分量。针对SAR影像水体目标的亮度及形状分布特征,进一步采用序列非线性滤波处理,从分离出的图像分量中提取出水体目标。利用ENVISAT ASAR多极化影像进行了实验,结果表明该方法可以快速准确地提取多极化SAR影像中的水体目标。     

Road extraction from SAR imagery based on an improved particle filtering and snake model

This article presents an improved approach for road extraction from synthetic aperture radar (SAR) imagery. First, an improved fast road detector is used to obtain road response and direction, as well as to reduce false alarm rates resulting from bright line objects. Particle filtering is then applied in selecting road seed points, and particle weight is designed on the basis of the road characteristics derived from SAR images. Finally, a snake model is used to connect the seed points to form a road. Results show that the proposed method is effective, with enhanced completeness, correctness, and quality even under the influence of high-backscattering context objects near roads.     

Oil spill detection from SAR intensity imagery using a marked point process

This paper presents a new algorithm for the detection of oil spill from SAR intensity images. The proposed algorithm combines the marked point process, Bayesian inference and Markov Chain Monte Carlo (MCMC) technique. In this paper, the candidates of oil spills or dark spots in a SAR intensity image are characterized by a Poisson marked point process. The marked point process is formed by a group of random points (as a point process modelling the locations of oil spills) and a set of parameters including geometric parameters of windows centred at the random points and gamma distribution parameters (as the marks attaching to each point). As a result, the candidates of oil spills are represented by a group of windows, in which the intensities of pixels follow independent and identical gamma distribution with lower mean than that for the identical gamma distribution of the pixels out of windows. Following the Bayesian paradigm, the posterior distribution, which characterizes the locations and statistical distributions of oil spills, can be obtained up to a normalizing constant. In order to simulate from the posterior distribution and to estimate the parameters of the posterior distribution, the Revisable Jump MCMC (RJMCMC) algorithm is used. The optimal locations and sizes of dark spots are obtained by a maximum a posteriori (MAP) algorithm. The proposed approach is tested using Radarsat-1 SAR images with oil spills indicated by human analysts. The results show that the proposed approach works well and is very promising.     

基于高分辨率SAR图像的道路提取算法

针对合成孔径雷达(synthetic aperture radar,SAR)图像中道路边缘的特点,提出了一种基于多条件加权法的高分辨率SAR图像道路提取算法。该算法使用FROST滤波抑制相干斑噪声,并使用OSTU算法对高分辨率SAR图像进行二值化,对二值化后的SAR图像进行膨胀与腐蚀,再使用五邻居边缘检测器与多条件加权法提取道路的一个边缘,最终使用桥连接模式提取出完整的道路边缘。实验结果表明,该算法可以消除噪声,消除障碍物的干扰,有效的提取道路边缘。     

Symbolic target detection in SAR imagery via rotationally invariant-weighted feature extraction

This article introduces the application of a physics-based symbolic image partitioning method to detect targets in synthetic aperture radar (SAR) imagery. ‘Targets’ in this case refer to vehicular objects which produce a distinct radar return pattern, and have spatial characteristics that are known a priori. The proposed Rotationally Invariant Symbolic Histogram (RISH) detection method co-analyses both target and speckle statistics, and significantly reduces computational requirements by partitioning the data into a discrete number of state representations. RISH requires only one pass for robust detection, unlike other SAR detection methods which rely on difference metrics calculated using multiple passes. To improve performance in high-resolution data, RISH uses a weighted feature extraction algorithm to avoid the common requirement of processing each pixel of the image equally. The weighted structure extracts geometrically undefined and rotationally invariant target features. This article details the analysis of 24 experimentally obtained very high-frequency (VHF)-band SAR magnitude images using this novel approach to SAR target detection. In localizing small (~8.4 m²) foliage-concealed targets, without the aid of pre-processing, this method results in high performance characteristics (90% true positive) with a low Type-II error rate of 6.4 false alarms per 1 × 10⁶ m². With the addition of change detection, RISH lowers the error rate by 85%.     

Single versus stereo ERS-1 SAR imagery for planimetric features extraction

This Letter compares two conventional methods for the extraction of planimetric features: the monoscopic method, using an image and a digital elevation model to generate an ortho-image; and the stereoscopic method, using two images for the three-dimensional reconstruction of the stereoscopic model of the terrain.Feature extraction then occurs in mono or stereoscopic viewing,depending on the method used. When compared with the topographic data, accuracies of the lake shoreline extraction from ERS-1 SAR images show 22m versus 17 m root mean square accuracies with 66 per cent confidence for the monoscopic and stereoscopic methods, respectively. More consistency is also achieved with the stereoscopic method.     

Unsupervised classification of SAR images using normalized gamma process mixtures

We propose an image prior for the model-based nonparametric classification of synthetic aperture radar (SAR) images that allows working with infinite number of mixture components. In order to enclose the spatial interactions of the pixel labels, the prior is derived by incorporating a conditional multinomial auto-logistic random field into the Normalized Gamma Process prior. In this way, we obtain an image classification prior that is free from the limitation on the number of classes and includes the smoothing constraint into classification problem. In this model, we introduced a hyper-parameter that can control the preservation of the important classes and the extinction of the weak ones. The recall rates reported on the synthetic and the real TerraSAR-X images show that the proposed model is capable of accurately classifying the pixels. Unlike the existing methods, it applies a simple iterative update scheme without performing a hierarchical clustering strategy. We demonstrate that the estimation accuracy of the proposed method in number of classes outperforms the conventional finite mixture models.     

Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery

In using traditional digital classification algorithms, a researcher typically encounters serious issues in identifying urban land cover classes employing high resolution data. A normal approach is to use spectral information alone and ignore spatial information and a group of pixels that need to be considered together as an object. We used QuickBird image data over a central region in the city of Phoenix, Arizona to examine if an object-based classifier can accurately identify urban classes. To demonstrate if spectral information alone is practical in urban classification, we used spectra of the selected classes from randomly selected points to examine if they can be effectively discriminated. The overall accuracy based on spectral information alone reached only about 63.33%. We employed five different classification procedures with the object-based paradigm that separates spatially and spectrally similar pixels at different scales. The classifiers to assign land covers to segmented objects used in the study include membership functions and the nearest neighbor classifier. The object-based classifier achieved a high overall accuracy (90.40%), whereas the most commonly used decision rule, namely maximum likelihood classifier, produced a lower overall accuracy (67.60%). This study demonstrates that the object-based classifier is a significantly better approach than the classical per-pixel classifiers. Further, this study reviews application of different parameters for segmentation and classification, combined use of composite and original bands, selection of different scale levels, and choice of classifiers. Strengths and weaknesses of the object-based prototype are presented and we provide suggestions to avoid or minimize uncertainties and limitations associated with the approach.     

从高分辨率遥感影像中提取城市道路的新方法

在综合几种现有算法优点的基础上,提出一种新的道路提取策略。首先以角度纹理特性法分割原始影像;接着利用直线匹配原理剔除初始分割结果中的非道路地物,得到更为规则的道路条带;然后通过形态学手段获得道路中心线,并将每条中心线拆分为多段直线;结合上下文知识的马尔可夫模型被用于组织道路段的中心线,从而恢复完整道路网。实验结果表明：新方法具有良好的性能,可以从高分辨IKONOS遥感影像中提取出复杂的城市道路。