Unsupervised change detection in SAR images based on locally fitting model and semi-EM algorithm

Change detection in synthetic aperture radar (SAR) images has become increasingly important along with the development of SAR techniques. In this study, a novel locally fitting and expectation-maximization (EM) approach is proposed for unsupervised change detection tasks in SAR images. A difference image is generated first, and an in-depth study of the inherent characteristics of the histogram of the difference image is then made. Thus, the new approach is proposed corresponding to these characteristics. In this approach, the locally fitting model orientated to deal with the unchanged class is put forward to reach a best fit, and the semi-EM algorithm for the changed class is used to tackle the phenomenon of overlapping. Then, through the Bayesian decision rule, the optimal threshold is determined. Our contributions lie in two aspects. First, in the locally fitting model, the location of the optimal threshold can be determined, which leads to an accurate fit over a short interval. Second, the use of the semi-EM algorithm not only retains the efficacy of the EM algorithm to cope with overlapping for the changed class but also simplifies the computing process. Experiments on real data sets confirm the effectiveness of the proposed approach, which results in final maps very similar to the ground truth and is more effective in determining the optimal threshold in comparison with others. The experimental results also demonstrate its effectiveness when the changed areas are of different geometrical shapes.     

Unsupervised segmentation of dual-polarization SAR images based on amplitude and texture characteristics

A new approach for the unsupervised segmentation of dual-polarization Synthetic Aperture Radar (SAR) images based on statistics of both the amplitude variations and the textural characteristics of the data is presented. A co-polarized amplitude image and a cross-polarized amplitude image are used in this study. It is a two-step process. In the first step, these images are filtered once to suppress the speckle noise while preserving the contrast associated with edges and subtle details. The feature vector composed of the two filtered image pixels is assumed to have a joint Gaussian distribution. A scanning window is used to discover clusters at each position. A merging procedure follows to combine these clusters based on the Mahalanobis distance measure, into a number appropriate for the image. A Bayes maximum likelihood classifier is then applied. In the second step, we adopt the second-order Gaussian Markov random field (GMRF) models for image textures in the original un-filtered images. Segments assigned to each class in the first step are examined for possible sub-division into groups, based on textural characteristics. Two segments are considered texturally similar if the ratio of the pseudo-likelihoods of the image before and after merging is close to one.     

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.     

基于第2代Curvelet的非监督式纹理缺陷分割

针对纹理缺陷分割问题,将曲波变换与均值漂移理论相结合,形成有效的纹理分割新方法。首先,通过曲波变换将图像分解到各通道,对各通道的图像进行非线性变换得到特征图像;然后,用均值漂移算法对各通道特征图像进行自适应聚类,找到各通道的奇异点;最后,对所有通道滤波后的图像进行重构,使缺陷凸显并通过阈值法二值化。该方法不需要学习样本,可以快速、精确地定位到多目标物边界,对旋转、亮度变化、噪声、弱边界具有很强的鲁棒性。通过MATLAB进行仿真实验,验证了该方法的有效性。     

Unsupervised multi-class segmentation of SAR images using triplet Markov fields models based on edge penalty

Non-Gaussian triplet Markov random fields (TMF) model is suitable for dealing with multi-class segmentation of nonstationary and non-Gaussian synthetic aperture radar (SAR) images. However, the segmentation of SAR images utilizing this model still fails to resolve the misclassifications due to the inaccuracy of edge location. In this paper, we propose a new unsupervised multi-class segmentation algorithm by fusing the traditional energy function of TMF model with the principle of edge penalty. Through the introduction of the penalty function based on local edge strength information, the new energy function could prevent segment from smoothing across boundaries. Then we optimize the objective function that stems from the new energy function to obtain an iterative multi-region merging Bayesian maximum posterior mode (MPM) segmentation equation for the new segmentation algorithm. The effectiveness of the proposed algorithm is demonstrated by application to simulated data and real SAR images.     

Unsupervised multi-class segmentation of SAR images using fuzzy triplet Markov fields model

Triplet Markov fields (TMF) model proposed recently is suitable for nonstationary image segmentation. For synthetic aperture radar (SAR) image segmentation, TMF model can adopt diverse statistical models for SAR data related to diverse radar backscattering sources. However, TMF model does not take into account the inherent imprecision associated with SAR images. In this paper, we propose a statistical fuzzy TMF (FTMF) model, which is a fuzzy clustering type treatment of TMF model, for unsupervised multi-class segmentation of SAR images. This paper contributes to SAR image segmentation in four aspects: (1) Nonstationarity of the statistical distribution of SAR intensity/amplitude data is taken into account to improve the spatial modeling capability of fuzzy TMF model. (2) Mean field theory is generalized to deal with planar variables to derive prior probability in fuzzy TMF model, which resolves the problem in Gibbs sampler in terms of computation cost. (3) A fuzzy objective function with regularization by Kullback–Leibler information of fuzzy TMF model is constructed for SAR image segmentation. The introduction of fuzziness for the belongingness of SAR image pixel makes fuzzy TMF model be able to retain more information from SAR image. (4) Fuzzy iterative conditional estimation (ICE) method, as an extension of the general ICE method is proposed to perform the model parameters estimation. The effectiveness of the proposed algorithm is demonstrated by application to simulated data and real SAR images.     

差异特征融合的无监督SAR图像变化检测

针对Siamese网络忽略不同层级差异特征之间的关联导致检测精度有限的问题,提出了基于差异特征融合的无监督SAR(synthetic aperture radar)图像变化检测算法。首先,利用对数比值算子和均值比值算子构建两幅信息互补的差异图,通过引入能量矩阵对差异图进行像素级融合以提高其信噪比;其次,设计了一种基于差异特征融合的Siamese网络(difference feature fusion for Siamese,DFF-Siamese),该网络能够通过差异特征提取模块在决策层综合衡量不同层级特征之间的差异程度,从而有效增强网络的特征表达能力;最后,利用模糊聚类算法对融合结果进行分类构建“伪标签”,用于训练DFF-Siamese网络以实现高精度SAR图像变化检测。在3组真实遥感数据集上的实验结果表明,本文提出的算法与其他对比算法相比具有更高的检测精度和更低的错误率。     

基于敏感特征向量的SAR图像灾害变化检测技术

为了解决阴雨云雾条件下光学遥感图像的应用局限性问题,针对典型的四类地表变化（堰塞湖、滑坡泥石流、部分倒塌建筑和严重倒塌建筑）分析SAR图像灰度和纹理特征的敏感程度,并提出敏感特征向量的概念;以综合利用了灰度差值和纹理差值的敏感特征向量作为评判因子,结合主成分分析技术和K均值聚类技术,提出了新的SAR图像灾害变化检测算法。该方法算法简单,检测效果好,并用两组ALOS SAR实验数据进行了证实。     

贝叶斯框架下基于曲波特征加权的SAR影像分割

为了探究各特征在SAR影像分割中的作用规律,提出一种贝叶斯框架下基于曲波特征加权的SAR影像分割方法.首先,利用曲波变换提取像素的多尺度光谱特征,构成像素特征矢量,为了探究提取的多尺度光谱特征在SAR影像分割中的作用规律,赋予该矢量中的每个特征分量不同的贡献权重,并利用上述特征和贡献权重定义特征加权影像;然后,划分影像域,并在贝叶斯框架下构建基于曲波特征加权的SAR影像分割模型;同时利用马尔可夫链蒙特卡罗(Markov Chain Monte Carlo, MCMC)算法和最大期望值(expectation maximization, EM)算法实现影像分割和权重估计;最后,利用所提出方法和4种对比方法对SAR影像进行分割实验,通过其定性及定量评价结果验证所提出方法不仅能够自适应地确定特征在影像分割的作用,还能有效提高SAR影像分割精度,表明所提出方法在SAR影像多特征分割中的优势.     

Unsupervised segmentation of textured images by edge detection inmultidimensional feature

An algorithm for unsupervised texture segmentation is developed that is based on detecting changes in textural characteristics of small local regions. Six features derived from two, two-dimensional, noncausal random field models are used to represent texture. These features contain information about gray-level-value variations in the eight principal directions. An algorithm for automatic selection of the size of the observation windows over which textural activity and change are measured has been developed. Effects of changes in individual features are considered simultaneously by constructing a one-dimensional measure of textural change from them. Edges in this measure correspond to the sought-after textural edges. Experiments results with images containing regions of natural texture show that the algorithm performs very well     

基于多尺度随机模型的SAR图像无监督分割

合成孔径雷达（synthetic aperture radar,SAR）是一种基于相干原理的成像系统,在SAR图像中存在严重影响图像质量的斑点噪声,使得SAR图像的可靠分割非常困难。〖BP）〗根据SAR图像的成像机理,利用两种多尺度随机模型,即多尺度自回归（Multiscale Autoregressive,MAR）模型和多尺度自回归滑动平均（Multiscale Aautoregressive Moving Average, MARMA）模型,分别来描述同一场景不同分辨率SAR图像像素间的统计相关性,并构造了相应的多分辨混合算法实现SAR图像的无监督分割。试验结果表明,提出的两种无监督分割方法是可行的,且MARMA模型比MAR模型能够更精确地捕捉SAR图像多尺度序列中不同类型地形的统计信息,使分割质量具有明显的改进。     

整型推理量化CNN的SAR图像跨域变化检测

目的 合成孔径雷达（synthetic aperture radar,SAR）特有的成像优势使得SAR图像变化检测在民用和军事领域有着广泛的应用场景,但实际应用中对SAR图像的变化区域进行标注既耗时又昂贵,而且现有的变化检测方法复杂度较高,无法满足实时、快速检测的需求。对此,提出了一种基于整型推理量化卷积神经网络的SAR图像跨域变化检测方法（integer inference-based quantization convolutional neural network,IIQ-CNN）。方法 该方法研究了不同场景之间的跨域变化检测问题,即利用已有标记的源域数据对未知的目标域数据进行检测;设计了同时使用时相图和差异图的样本构建方法,既避免了检测结果对差异图的过分依赖,又能充分利用差异信息和时相图与差异图之间的共享信息,提高检测精度;并且在变化检测任务中首次引入整型推理量化技术,对深度网络模型进行模拟量化,减小模型复杂度并加速推理时间。结果 在４组真实的SAR图像数据集上进行实验,从检测性能上看,IIQ-CNN与其他CNN方法相比,Kappa系数提高了4.23%～9.07%;从量化能力上看,对IIQ-CNN分别进行16、8和4位量化,仅在4位量化时检测结果有较明显下降,在16和8位量化时,模型都保持了较好的检测性能,并且推理时间明显减少。结论 本文方法有效解决了伪标签质量对变化检测性能的影响,实现了加速推理的同时较好地保持模型检测精度的目的,促进了变化检测算法在嵌入式设备中的应用。     

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。     

Unsupervised change detection based on robust chi-squared transform for bitemporal remotely sensed images

Chi-squared transform (CST)-based methods are simple and effective methods for detecting changes in remotely sensed images that have been registered and aligned. The methods operate directly on information stored in the difference image. However, the estimated mean and covariance matrix of the Gaussian distribution that describes the unchanged pixels can be biased when the changed pixels (outliers) are also included. To overcome this issue, we propose a pixel-based unsupervised change detection method that gives robust estimates of these parameters. The method is iterative but requires only a small number of iterations. In addition, we also design an algorithm to automatically search for the optimal threshold that is needed for classifying changed versus unchanged pixels. This algorithm finds the optimal threshold where the mean and covariance matrix of the change detection result most agree with those statistics obtained from the above-mentioned robust algorithm. We refer to our change detection method as the robust CST (RCST) method. The proposed method has been evaluated on two image data-sets and compared with four state-of-the-art methods. The effectiveness of RCST is confirmed by its low overall errors (OE) and high kappa coefficients on both data-sets.     

Unsupervised statistical segmentation of nonstationary images using triplet Markov fields

Recent developments in statistical theory and associated computational techniques have opened new avenues for image modeling as well as for image segmentation techniques. Thus, a host of models have been proposed and the ones which have probably received considerable attention are the hidden Markov fields (HMF) models. This is due to their simplicity of handling and their potential for providing improved image quality. Although these models provide satisfying results in the stationary case, they can fail in the nonstationary one. In this paper, we tackle the problem of modeling a nonstationary hidden random field and its effect on the unsupervised statistical image segmentation. We propose an original approach, based on the recent triplet Markov field (TMF) model, which enables one to deal with nonstationary class fields. Moreover, the noise can be correlated and possibly non-Gaussian. An original parameter estimation method which uses the Pearson system to find the natures of the noise margins, which can vary with the class, is also proposed and used to perform unsupervised segmentation of such images. Experiments indicate that the new model and related processing algorithm can improve the results obtained with the classical ones.     

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.     

A scheme for ship detection in inhomogeneous regions based on segmentation of SAR images

Ship detection in inhomogeneous regions using synthetic aperture radar (SAR) imagery is usually confronted with the severe heterogeneities of the oceans; this paper proposes a new detection scheme to overcome this problem. At first, an object‐oriented segmentation algorithm is employed to partition the whole SAR image into several uniform regions. Then, for each partitioned region within water areas, the Kolmogorov–Smirnov test is applied to select the optimal background distribution model, and ship detection is carried out using the adaptive constant false alarm rate (CFAR) detector based on the selected probability density function. Finally, the detection results of each region are merged. An experiment based on an ENVISAT ASAR image of the Yangtze estuary show that the proposed strategy can effectively deal with heterogeneous scenarios in inhomogenous regions and greatly improves the detection results.