Incorporating global-local a Priori knowledge into expectation-maximization for SAR image change detection

Speckle is one of the inevitable obstacles related to synthetic aperture radar (SAR) image change detection; it increases the overlap between changed and unchanged pixels in the histogram of a difference image. This makes the selection of a statistic model more difficult for describing opposite classes. To address this issue, this article developed an unsupervised change-detection approach for multitemporal SAR images that specifies a priori knowledge about the spatial characteristics of the classes through Dempster-Shafer evidence theory and embeds it into the Expectation-Maximization (EM) iteration process. It is based on the consideration that each pixel in the difference image is unique due to its neighbourhood, although some of them may have the same pixel value. Thus, under the hypothesis that local and global a priori knowledge are independent sources, a global-local a priori model is developed through Dempster-Shafer evidence theory. The EM algorithm allows one to estimate the statistical parameters of the opposite classes associated with this a priori model. As a consequence, the change-detection result can be obtained within the framework of Bayes. Visual and quantitative results obtained on real multitemporal SAR image data sets confirm the effectiveness of the proposed method compared with state-of-the-art ones for SAR image change detection.     

Satellite radar and optical remote sensing for earthquake damage detection: results from different case studies

In case of a seismic event, a fast and draft damage map of the hit urban areas can be very useful, in particular when the epicentre of the earthquake is located in remote regions, or the main communication systems are damaged. Our aim is to analyse the capability of remote sensing techniques for damage detection in urban areas and to explore the combined use of radar (SAR) and optical satellite data. Two case studies have been proposed: Izmit (1999; Turkey) and Bam (2003; Iran). Both areas have been affected by strong earthquakes causing heavy and extended damage in the urban settlements close to the epicentre. Different procedures for damage assessment have been successfully tested, either to perform a pixel by pixel classification or to assess damage within homogeneous extended areas. We have compared change detection capabilities of different features extracted from optical and radar data, and analysed the potential of combining measurements at different frequency ranges. Regarding the Izmit case, SAR features alone have reached 70% of correct classification of damaged areas and 5 m panchromatic optical images have given 82%; the fusion of SAR and optical data raised up to 89% of correct pixel‐to‐pixel classification. The same procedures applied to the Bam test case achieved about 61% of correct classification from SAR alone, 70% from optical data, while data fusion reached 76%. The results of the correlation between satellite remote sensing and ground surveys data have been presented by comparing remotely change detection features averaged within homogeneous blocks of buildings with ground survey data.     

Multi-sensoral and automated derivation of inundated areas using TerraSAR-X and ENVISAT ASAR data

During recent years, synthetic aperture radar (SAR) data have been increasingly used for flood mapping. New radar satellites especially, such as TerraSAR-X, Radarsat-2 and COSMO-SkyMed, provide high-resolution data with high potential for fast and reliable detection of inundated areas. This article compares three simple approaches to derive water areas from SAR data in relation to the German–Vietnamese project, Water-related Information System for the Sustainable Development of the Mekong Delta (WISDOM). Two methods are pixel based and use histogram-based grey-level thresholds, as well as a homogeneity criterion for classification. The third approach is object based and applies characteristic attributes of water objects such as grey value, texture and relations to neighbouring objects. Further discussed are the influence of a variation of the thresholds and the challenges to validate water masks derived from active remote-sensing data. We implemented one of the introduced approaches for surface water derivation in a water mask processor for automatic water mask calculation from radar satellite imagery (WaMaPro). This fully automatic processing chain was developed to process TerraSAR-X and Environmental Satellite Advanced Synthetic Aperture Radar (ENVISAT ASAR) imagery in order to meet the demands for automatic flood monitoring.     

Integration of panchromatic and SAR features into multispectral SPOT images using the ‘à trous’ wavelet decomposition

A method is described for integrating panchromatic (P) and synthetic aperture radar (SAR) features into multispectral (XS) images using conjointly the modified Brovey transform (MBT) and the ‘à trous’ wavelet decomposition (ATDW). The MBT is based on the local modulation of each multispectral image by the ratio of the new and initial intensity components to produce new multispectral images directly. The ATWD allows extraction of features from P and SAR images, which are combined through a feature selection rule to integrate into the initial intensity component. For evaluating the effect of each feature selection on new XS images, experimental results are conducted on SPOT (XS, P) and Radarsat (SAR) images using both visual inspection and many refined statistical measures.     

Environmental monitoring of natural disasters using synthetic aperture radar image multi-directional characteristics

Synthetic aperture radar (SAR) imaging can penetrate rain, snow, fog, and mist, providing an effective precipitation detector under a wide range of atmospheric conditions. This powerful technique operates under any weather conditions and can detect environmental changes or help in the evaluation of natural disasters. Multi-temporal change detection is important for monitoring disasters, but commonly applied wavelet transforms are not ideal for capturing change information. This paper presents a new multi-directional change detection (MDCD) method designed to improve the change detection accuracy using multiple SAR images. This method employs double-density dual-tree complex wavelet transforms (DDDT-CWT) theory, which allows the capture of multi-directional information. The MDCD method can provide information for 16 directions at any decomposed scale, which allows for change detection in multiple SAR images collected over time. We used the MDCD algorithm method to analyse SAR images from actual natural disasters and successfully identified environmental changes over time using SAR images.     

结合空间邻域信息的SAR图像变化检测

SAR图像变化检测可以通过对差异图的分类来实现,由于SAR图像容易受到相干斑噪声的干扰,从而影响变化检测效果。提出了一种基于空间邻域信息模糊聚类的SAR图像变化检测方法,根据对数比法和均值比法的各自特点,构造了一种新的差异图生成方法,并通过对传统的模糊聚类算法结合像素的空间邻域信息进行改进,来实现SAR图像的变化检测。实验结果表明,与传统的阈值法、模糊聚类算法以及局部邻域信息模糊C均值算法相比,提出的算法具有较高的检测精度,不但能有效地抑制噪声影响,同时能较好地保留图像细节信息。     

Unsupervised change detection in SAR images based on frequency difference and a modified fuzzy c-means clustering

Change detection for synthetic aperture radar (SAR) images is a key process in many applications exploiting remote-sensing images. It is a challenging task due to the presence of speckle noise in SAR imaging. This article investigates the problem of change detection in multitemporal SAR images. Our motivation is to avoid using only one detector to measure the change level of different features which is usually considered by classical methods. In this article, we propose an unsupervised change detection approach based on frequency difference in wavelet domain and a modified fuzzy c-means (FCM) clustering algorithm. First, the proposed method extracts high-frequency and low-frequency components using wavelet transform, and then constructs high-frequency and low-frequency difference images using different detectors. Finally, inverse wavelet transform is carried out to obtain the final difference image. In addition, inspired by manifold structure constraint, we incorporate weighted local information into the FCM to reduce the influence of speckle noise. Experimental results performed on simulated and real SAR images show the effectiveness of the proposed method, in terms of detection performance, compared with the state-of-the-art methods.     

结合结构相似度的自适应多尺度SAR图像变化检测

目的 结合高斯核函数特有的性质,提出一种基于结构相似度的自适应多尺度SAR图像变化检测算法。方法 本文提出的算法包括差异图像获取、高斯多尺度分解、基于结构相似性的最优尺度选择、特征矢量构造以及模糊C均值分类。首先,通过对多时相SAR图像进行对数比运算获取差异图像,然后,利用基于图像的结构相似度估计高斯多尺度变换的最优尺度,继而在该最优尺度参数下逐像素构建变化检测特征矢量,最后通过模糊C均值聚类方法实现变化像素与未变化像素的分离,生成最终的变化检测结果图。结果 在两组真实的SAR图像数据上测试本文算法,正确检测率分别达到0.9952和0.9623,Kappa系数分别为0.8200和0.8540,相比传统算法有了较大的提高。结论 本文算法充分利用了尺度信息,对噪声的鲁棒性有所提高。实测SAR数据的实验结果表明,本文算法可以智能获取最优分解尺度,显著提高了SAR图像变化检测性能。     

基于静态小波分解的多尺度SAR图象滤波

由于雷达回波的相干性 ,合成孔径雷达 (SAR)图象上存在着斑点噪声 ,因此 ,为消除这种噪声 ,提出了一种基于静态小波分解的硬阈值滤波方法 ,该方法首先将 SAR图象分解至静态小波域 ,然后在静态小波域中将噪声的小波系数收缩至零 .将此算法应用于 ERS- 1SAR图象斑点噪声滤波 ,并与基于 Mallat分解的滤波算法和另外 3种典型的 SAR图象滤波算法进行比较 ,结果表明 ,该方法不仅可以有效地去除斑点噪声 ,并且可以保持 SAR图象的精细纹理结构     

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%.     

基于超像素分割和多方法融合的SAR图像变化检测方法

针对基于像素的合成孔径雷达(Synthetic Aperture Radar,SAR)图像变化检测会造成虚警较高、结果破碎的问题,提出一种基于超像素分割和多方法融合的SAR图像变化检测方法。首先引入基于简单线性迭代聚类(Simple Linear Iterative Clustering,SLIC)的超像素分割方法,通过对主辅图像进行联合分割,得到符合实际地物边界的超像素分割结果;同时,利用3种基于像素的变化检测方法获取初始变化检测结果;接着,利用超像素分割结果和初始变化检测结果进行两个层次的众数投票,去除检测结果中由于噪声引起的虚警和连通域中的孔洞。选取两个时相的苏州Radarsat-2单极化SAR图像开展变化检测实验,实验结果表明该算法在保持较高检测率和有效边界的基础上,能够显著降低虚警。     

基于静态小波分解的多尺度SAR图像滤波

由于雷达回波的相干性，合成孔径雷达（SAR）图象上存在着斑点噪声，因此，为消除这种噪声，提出了一种基于静态小波分解的硬阈值滤波方法，该方法首先将SAR图象分解至静态小波域，然后在静态小波域中将噪声的小波系数收缩至零，将此算法应用于ERS－1 SAR图象斑点噪声滤波，并与基于Mallat分解的滤波算法和另外3种典型的SAR图象滤波算法进行比较，结果表明，该方法不仅可以有效地去除斑点噪声,并且可以保持SAR图象的精细纹理结构。     

Pointwise SAR image change detection based on stereograph model with multiple-span neighbourhood information

In this article, a novel pointwise approach is proposed for change detection in bi-temporal synthetic aperture radar (SAR) images using stereograph model. Due to the fact that SAR image suffers from the speckle noise, a pointwise approach based on a set of characteristic points only, not on the whole pixels, seems to be more efficient. Moreover, the correlations of neighbourhood points which have different locations in bi-temporal SAR images should be studied to repress the speckle in change detection. Therefore, the stereograph model, which extends the graph model to three-dimensional space, is designed to connect the local maximum pixels on bi-temporal SAR images and can be used to capture the multiple-span neighbourhood information from the edges. Furthermore, a specialized change measure function is presented to quantify the neighbourhood information from stereograph model, and thus, a novel nondense difference image (NDI) is generated. Finally, a traditional classification method is used to analyse the NDI into changed class and unchanged class. Experiments on real SAR images show that the proposed NDI can improve separability between changed and unchanged areas, and the final results possess high accuracy and strong noise immunity for change detection tasks with noise-contaminated SAR images.     

Suitability of SAR imagery for automatic flood mapping in the Lower Mekong Basin

Flood detection and inundation mapping are amongst the most important applications for remote-sensing data. Space-borne radar systems, synthetic aperture radar (SAR) in particular, and its application for waterbody mapping have recently been subject to research in many publications. Although very good results have been achieved with such data, in some cases automatic waterbody classification based on SAR data is not feasible. Factors influencing the applicability are, e.g., local environmental conditions, roughening of water surfaces due to wind, or the satellite observation geometry. In this study, a measure for the usability of SAR imagery for flood mapping was investigated. Additionally, a method for permanent waterbody mapping was introduced. The study is based on Envisat ASAR wide swath mode (150 m spatial resolution) data of the Mekong River Basin. For the usability measure, the concept of ‘high-contrast tiles’ was established, which allows an a priori estimation of the expected accuracy of a waterbody classifier. The SAR-based permanent waterbody map was used for the validation of the approach. It was found that, for the test site, the new SAR usability measure allows the identification of unsuitable scenes with a certainty of more than 90%. The method is expected to be very useful for near-real-time flood mapping applications where human interaction is neither desired nor feasible when large regions and large data volumes are considered.     

Target recognition in SAR imagery based on local gradient ratio pattern

Due to weather- and illumination-independent characteristics, synthetic aperture radar (SAR) has become an important tool for target recognition. Using analysis of existing methods, a new feature of SAR imagery and a valid target recognition strategy are proposed. We first extract the gradient ratio pattern for each pixel based on Weber’s law and the local gradient ratio pattern histogram (LGRPH) is then computed. Next, multiscale LGRPH is constructed for dimensionality reduction. Finally, the similarity is obtained by utilizing K–L discrepancy to measure the distance of MLGRPH. The proposed method is theoretically proven to be insensitive to speckle noise, and the adaptability to local gradient variation is also discussed. Experimental results show that the proposed approach is robust in regard to local gradient variation and speckle noise.     

Change detection in synthetic aperture radar images based on non-local means with ratio similarity measurement

Image change detection is of widespread interest due to a large number of applications in diverse disciplines. In this study, a novel change detection approach for synthetic aperture radar (SAR) images based on a non-local means algorithm is proposed. A non-local means technique is introduced to generate a difference image by using complete information from a pair of observed images. To take the characteristics of SAR images into account, a new ratio-based relativity measurement between two speckled SAR image patches based on a ratio distance is proposed. Theoretical analysis indicates that the ratio distance is valid for SAR images. The probability density function of the ratio distance is deduced to map the distance into a relativity value. Furthermore, the ratio distance and the probability density function are both parameter-free. The new non-local means technique is successfully applied to extend the classical mean-ratio detector for SAR image detection. Experimental results on real SAR images show that the proposed approach is robust to speckle noise and effective for the detection of change information between multitemporal SAR images.     

Sparse SAR imaging based on L1/2 regularization

In this paper,a novel method for synthetic aperture radar(SAR)imaging is proposed.The approach is based on L1/2 regularization to reconstruct the scattering field,which optimizes a quadratic error term of the SAR observation process subject to the interested scene sparsity.Compared to the conventional SAR imaging technique,the new method implements SAR imaging effectively at much lower sampling rate than the Nyquist rate,and produces high-quality images with reduced sidelobes and increased resolution.Also,over the prevalent greedy pursuit and L1 regularization based SAR imaging methods,there are remarkable performance improvements of the new method.On one hand,the new method significantly reduces the number of measurements needed for reconstruction,as supported by a phase transition diagram study.On the other hand,the new method is more robust to the observation noise.These fundamental properties of the new method are supported and demonstrated both by simulations and real SAR data experiments.     

Novel class-relativity non-local means with principal component analysis for multitemporal SAR image change detection

One of the main problems for change detection in multitemporal synthetic aperture radar (SAR) images is the presence of speckle noise, since it degrades the image quality significantly and may hide important details in the image. In this article, we investigate a novel class-relativity non-local means (CRNLM) algorithm that reduces the effect of speckle noise in the principal component analysis (PCA) feature space for SAR image change detection. Note that the non-local means averaging process is particularly true when the assumed noise model is additive. Thus, we adopt the difference image produced by the ratio image expressed in logarithmic scale and then transform it onto PCA space. This is done so that its signal energy is concentrated, and the noise spreads over the whole PCA space and is additive. A task-dependent CRNLM algorithm is applied to the PCA transformed data set so as to combine local and non-local geometries and capture the robustness to noise. The idea is based on the assumption that non-local similar patches have similar class structures. Visual and quantitative results obtained on real multitemporal SAR image data sets confirm the effectiveness of this method as compared with several state-of-the-art techniques.     

Change detection of isolated housing using a new hybrid approach based on object classification with optical and TerraSAR-X data

Optical and microwave high spatial resolution images are now available for a wide range of applications. In this work, they have been applied for the semi-automatic change detection of isolated housing in agricultural areas. This article presents a new hybrid methodology based on segmentation of high-resolution images and image differencing. This new approach mixes the main techniques used in change detection methods and it also adds a final segmentation process in order to classify the change detection product. First, isolated building classification is carried out using only optical data. Then, synthetic aperture radar (SAR) information is added to the classification process, obtaining excellent results with lower complexity cost. Since the first classification step is improved, the total change detection scheme is also enhanced when the radar data are used for classification. Finally, a comparison between the different methods is presented and some conclusions are extracted from the study.