A statistical and Wiener filtering algorithm based on the curvelet transform for SAR images

Synthetic aperture radar (SAR) images contain many kinds of noise. Speckle noise is multiplicative noise generated by the coherent imaging processes involved in SAR images and brings a great hindrance to the interpretation and application of SAR images, so it is considered the first major kind of noise in SAR images. SAR images also contain other incoherent additive noises generated by other factors, such as Gaussian noise, which are all considered the second major kind of noise. In order to reduce the impact of noise as much as possible, after an in-depth study of SAR imaging and noise-generating mechanism, curvelet transform principle, and Wiener filtering characteristic, a novel filtering method, here called the statistical and Wiener based on curvelet transform (SWCT) method is proposed. The SWCT algorithm processes two different kinds noise based on their properties. Specifically, it establishes a two-tiered filtering framework. For the first kind of noise, the algorithm uses the curvelet transform to decompose the SAR image and uses the statistical characteristics of the SAR image to generate an adaptive filtering threshold of the coefficients of decomposition to recover the original image. Then it filters every sub-band image at each decomposed scale and performs the inverse curvelet transform. The second kind of noise is directly filtered using the Wiener filter in the SWCT algorithm. Using the two-tiered filtering model and fully exploiting statistical characteristics, the SWCT algorithm not only reduces the amount of coherent speckle noise and incoherent noise effectively but also retains the edges and geometric details of the original SAR image. This is very good for target detection, classification, and recognition. Qualitative and quantitative tests were performed using simulated speckle noise, Gaussian noise, and real SAR images. The proposed SWCT algorithm was found to remove noise effectively and the performance of the algorithm was tested and compared to the mean filter, enhanced gamma-MAP (maximum a posterior probability) filter, wavelet transform filter, Wiener filter, and curvelet transform filter. Experiments carried out on real SAR images confirmed that the new method has a good filtering effect and can be used on different SAR images.     

Application of special-purpose artificial neural networks for speckle reduction in SAR images

Synthetic aperture radar (SAR) is used extensively for remote-sensing applications due to its ability to operate under all weather conditions and provide high-resolution images. However, high-resolution images constructed from SAR data often suffer from speckle, which makes identification and classification of edges/boundaries a difficult task. Speckle noise is multiplicative in nature and is a result of constructive and destructive interference of signals from randomly distributed scatterers in a resolution cell illuminated by a coherent signal. Usually, speckle is reduced by incoherent averaging of high-resolution image pixels that degrade resolution. The principal goal in all speckle-reduction algorithms is to reduce speckle with minimum loss of resolution. In this investigation, we used specially trained and validated artificial neural networks (ANNs) for speckle reduction in images generated with a radar-depth sounder/imager and compared their performance to the conventional adaptive filtering and Speckle Reducing Anisotropic Diffusion (SRAD) algorithm. We show that by training different ANNs to reduce speckle noise at different levels of signal-to-noise ratio (SNR), rather than training one ANN to operate at all levels of SNR, improved performance in speckle reduction can be obtained. Real SAR images and synthetic noise are used in this research to compare the performance of the proposed ANN-based approaches with that obtained from conventional methods. This investigation shows that on combining the results from a set of properly trained and validated neural networks, the SNRs of the output images improve beyond those obtained from conventional approaches when the input SNRs are greater than or equal to 4 dB. For input SNRs greater than 0 dB, however, the ANNs provide better performance in edge preservation compared with conventional methods. We also found that once a set of ANNs is properly trained to reduce speckle from an image, these ANNs can be used in de-speckling other images without any further training. The merits and demerits of different configurations of the ANNs are studied to find useful speckle noise-tolerant ANN architectures.     

一种改进的自适应窗口滤波的SAR图像去噪算法

SAR的广泛应用及其距离、方位上的高分辨率,使其受到人们越来越多的重视。但是SAR图像中的斑点噪声却严重地制约了它的进一步的应用。根据SAR图像的成像过程提出了一种改进的抑制SAR图像中斑点噪声的算法-自适应窗口空间域平滑算法。它根据窗内像素点的统计特征自适应调节窗口大小,并通过门限来决定是否需要改变窗的尺寸,达到在同性质区增大窗口来抑制斑点噪声,同时在异性质区减小窗口以最大限度地保护图像细节的目的。对实际SAR图像的验证,说明它在抑制斑点噪声和保存图像细节信息方面较之原方法有了一定的改进和提高。     

一种改进的基于非局部均值的极化SAR相干斑抑制算法

贝叶斯形式的非局部均值模型在极化SAR图像相干斑抑制中有良好的应用,在实现抑制相干斑的同时较地保持了边缘细节和点目标。本文通过分析SAR图像多视数据的空间统计分布,结合贝叶斯形式的非局部均值模型,得出了在该模型下多视与单视SAR图像中像素间相似性度量函数一致性的结论,并对该相似性度量函数进行了修正,使之满足对称性;最后针对算法全局使用一个固定滤波参数影响滤波效果的问题,提出了一种根据像素间相似程度自适应选取滤波参数的方法。实验结果验证了本文算法的有效性。     

改进的基于非局部均值的极化SAR相干斑抑制

贝叶斯形式的非局部均值模型在极化SAR图像相干斑抑制中有良好的应用,在实现抑制相干斑的同时较好地保持了边缘细节和点目标.通过分析合成孔径雷达(SAR)图像多视数据的空间统计分布,结合贝叶斯形式的非局部均值模型,得出在该模型下多视与单视SAR图像中像素间相似性度量函数一致性的结论,并对该相似性度量函数进行了修正,使之满足对称性;最后针对算法全局使用一个固定滤波参数影响滤波效果的问题,提出一种根据像素间相似程度自适应选取滤波参数的方法.实验结果验证了本文算法的有效性.     

一种新型的空域SAR图像相干斑抑制方法

为了有效抑制SAR强度图像中的相干斑噪声,提出一种改进Sigma滤波并结合Gamma MAP滤波的空域相干斑抑制方法。首先利用阈值判断法判断并保留强点目标,然后结合SAR图像分布模型和MMSE准则判断Sigma区间,其中可以根据图像局部统计特性自适应调整窗口尺寸,最后选择Sigma区间内像素进行Gamma MAP滤波。实验结果表明:对于星载和机载SAR图像,在相干斑噪声抑制和边缘纹理细节信息保持方面,该方法较其他常用的空域相干斑抑制方法具有明显的优越性,能极大地提高SAR图像判读和目标识别能力。     

A novel multi-scale level set method for SAR image segmentation based on a statistical model

To overcome the problems of large data volumes and strong speckle noise in synthetic aperture radar (SAR) images, a multi-scale level set approach for SAR image segmentation is proposed in this article. Because the multi-scale analysis of SAR images preserves their highest resolution features while additionally making use of sets of images at lower resolutions to improve specific functions, the proposed method is useful for removing the influence of speckle and, at the same time, preserving important structural information. The Gamma distribution is one of the most commonly used models employed to represent the statistical characteristics of speckle noise in a SAR image and it is introduced to define the energy functional. Moreover, based on the multi-scale level set framework, an improved multi-layer approach is introduced for multi-region segmentation. To obtain a fast and more accurate result, a novel threshold segmentation result is used to represent the initial segmentation curve. The experiments with synthetic and real SAR images demonstrate the effectiveness of the new method.     

基于惩罚系数自适应修正的SAR图像滤波新算法

合成孔径雷达(SAR)图像存在较强的相干斑点噪声,严重地影响了地物信息的提取与SAR图像的应用效果。提出了一种新的SAR图像斑点噪声滤波算法,该算法以一种基于膜模型的M arkov随机场的近似最优迭代滤波算法(TSPR)为基础,考虑了邻域空间关系对势能函数的影响,并通过在迭代过程中自适应修正惩罚系数,来达到更好的斑点噪声滤波效果。通过对含不同强度斑点噪声的退化图像的对比试验结果来看,该算法在提高处理后图像的信噪比方面,能够取得较TSPR算法更佳的效果。     

Speckle reduction for the forest mapping analysis of multi-temporal Radarsat-1 images

As the number of satellite-borne synthetic aperture radar (SAR) systems increases, both the availability and the length of multi-temporal (MT) sequences of SAR images have also increased. Previous research on MT SAR sequences suggests that they increase the classification accuracy for all applications over single date images. Yet the presence of speckle noise remains a problem and all images in the sequence must be speckle filtered before acceptable classification accuracy can be attained. Several speckle filters designed specifically for MT sequences have been reported in the literature. Filtering in the spatial domain, as is usually done, reduces the effective spatial resolution of the filtered image. MT speckle filters operate in both the spatial and temporal dimensions, thus the reduction in resolution is not likely to be as severe (although a comparison between MT and spatial filters has not been reported). While this advantage may be useful when extracting spatial features from the image sequence, it is not quite as apparent for classification applications. This research explores the relative performance of spatial and MT speckle filtering for a particular classification application: mapping boreal forest types. We report filter performance using the radiometric resolution as measured by the equivalent number of looks (NL), and classification performance as measured by the classification accuracy. We chose representative spatial and MT filters and found that spatial speckle filters offer the advantage of higher radiometric resolution and higher classification accuracy with lower algorithm complexity. Thus, we confirm that MT filtering offers no advantage for classification applications; spatial speckle filters yield higher overall performance.     

基于级联CNN的SAR图像舰船目标检测算法

针对合成孔径雷达(SAR)图像中舰船目标稀疏的特点,提出一种基于级联卷积神经网络(CNN)的SAR图像舰船目标检测方法.将候选区域提取方法BING与目标检测方法Fast R-CNN相结合,并采用级联CNN设计,可同时兼顾舰船检测的准确率和速度.首先,针对SAR图像中相干斑噪声影响梯度检测的问题,在原有梯度算子的基础上增加平滑算子,并对图像尺寸个数和候选框个数进行适应性改进,使其提取到的候选窗口更快更准;然后,设计级联结构的Fast R-CNN检测框架,前端简单的CNN负责排除明显的非目标区域,后端复杂的CNN对高概率候选区域进行分类和位置回归,整个结构可以保证快速准确地对舰船这种稀疏目标进行检测;最后,设计一种联合优化方法对多任务的目标函数进行优化,使其更快更好地收敛.在SAR图像舰船检测数据集SSDD上的实验结果显示,所提出的方法相比于原始Fast R-CNN和Faster R-CNN检测方法,检测精度从65.2%和70.1%提高到73.5%,每张图像的处理时间从2235ms和198ms下降到113ms.     

基于描述方法的SAR图像分割*

针对减少SAR图像分割中自由参数的问题,提出了基于最小描述长度的SAR图像分割方法。该方法经对数变换将SAR图像乘性噪声转换为加性噪声,对其建立描述模型,在描述长度最短意义上计算出重建图像,在假设SAR图像各区域实际地物后向散射特性对应的像素值恒定的前提下,该重建图像即为SAR图像的分割结果。该方法在分割的同时很好地抑制了SAR图像的相干斑噪声,保留了原始SAR图像的区域边界,并且不需要参数调节,整个分割过程自动完成,是一种非监督SAR图像分割方法。给出了该方法的具体实现步骤,实验结果验证了该方法的有效性。     

SAR与可见光图象匹配方法的研究

由于SAR和可见光成象传感器图象的物理特征不同,因此进行匹配难度很大。本文在深入分析了这两种传感器图象物理特征的基础上,提出了一种图象匹配的新方法。该方法运用形态学滤波方法去除SAR图象斑点噪声,利用图象的边缘特征进行匹配,并采用多分辨率分级搜索技术减少计算量,在对实验结果进行分析的基础上提出了搜索真实匹配位置的原则,大大提高了匹配的准确率。通过实验对SAR图象斑点噪声滤波和SAR与可见光图象匹配算法进行了验证,实验证明本算法的SAR图象去噪效果明显优于传统的Frost方法,图象匹配精度高,稳定性好。     

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.     

SAR图像目标识别的卷积神经网模型

目的 合成孔径雷达图像目标识别可以有效提高合成孔径雷达数据的利用效率。针对合成孔径雷达图像目标识别滤波处理耗时长、识别精度不高的问题,本文提出一种卷积神经网络模型应用于合成孔径雷达图像目标识别。方法 首先,针对合成孔径雷达图像特点设计特征提取部分的网络结构;其次,代价函数中引入L2范数提高模型的抗噪性能和泛化性;再次,全连接层使用Dropout减小网络的运算量并提高泛化性;最后研究了滤波对于网络模型的收敛速度和准确率的影响。结果 实验使用美国运动和静止目标获取与识别数据库,10类目标识别的实验结果表明改进后的卷积神经网络整体识别率（包含变体）由93.76%提升至98.10%。通过设置4组对比实验说明网络结构的改进和优化的有效性。卷积神经网络噪声抑制实验验证了卷积神经网络的特征提取过程对于SAR图像相干斑噪声有抑制作用,可以省去耗时的滤波处理。结论 本文提出的卷积神经网络模型提高了网络的准确率、泛化性,无需耗时的滤波处理,是一种合成孔径雷达图像目标识别的有效方法。     

改进的基于结构检测的SAR图像去斑方法

合成孔径雷达图像固有的相干斑噪声严重降低了图像的可解译程度,影响了后续目标检测、分类和识别等应用.因此,SAR图像的相干斑抑制问题一直是SAR图像应用的重要课题之一.一个理想的去斑算法应该在平滑的同时保持图像的边缘等细节不受损失,目前存在各种各样的算法,但没有一种方法能够完美的满足这一要求.为此该文提出了一种改进的结构检测的SAR图像去斑算法.利用概率迭代方法分割图像并检测边缘,结合强点检测图,将SAR图像标为结构区和非结构区,在非结构区域内进行Lee滤波以平滑噪声,对结构区直接保留原值,获得了非常好的去斑效果.利用RADARSAT实测图像进行实验,并对实验结果作充分分析,证明了本算法的有效性.     

Water body segmentation of Synthetic Aperture Radar image using Deep Convolutional Neural Networks

Deep Convolutional Neural Networks are finding their way into modern machine learning tasks and proved themselves to become one of the best contenders for future development in the field. Several proposed methods in image segmentation and classification problems are giving us satisfactory results and could even perform better than humans in image recognition tasks. But also at the cost of their performance, they also require a huge amount of images for training and huge amount of computing power and time that makes them unrealistic in some situations where obtaining a large dataset is not feasible. In this work, an attempt is made for segmentation of Synthetic Aperture Radar (SAR) images which are not usually abundant enough for training, and are heavily affected by a kind of multiplicative noise called speckle noise. For the segmentation task, pre-defined filters are first applied to the images and are fed to hybrid CNN that is resulted from the concept of Inception and U-Net. The outcome of our proposed method has been examined for their effectiveness of application in a complete set of SAR images that are not used for training. The accuracy has also been compared with the manually annotated SAR images.     

SAR image processing using adaptive stack filter

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into several binary images according to a set of thresholds. Each binary image is filtered by a Boolean function. The Boolean function that characterizes an adaptive stack filter is optimal and is computed from a pair of images consisting of an ideal noiseless image and its noisy version. In this work the behavior of adaptive stack filters on synthetic aperture radar (SAR) data is evaluated. With this aim, the equivalent number of looks for stack filtered data are calculated to assess the speckle noise reduction capability of this filter. Then a classification of simulated and real SAR images is carried out on data filtered with a stack filter trained with selected samples. The results of a maximum likelihood classification of these data are evaluated and compared with the results of classifying images previously filtered using the Lee and the Frost filters.     

一种多光谱和SAR遥感图象的配准方法

针对现有配准方法在用于多光谱图象与ＳＡＲ遥感图象配准时,存在受ＳＡＲ图象斑纹噪声影响大,手工选取配准控制点（ＲＣＰ）精度低,利用图象景物特征配准时获取区域和边沿困难等缺点,以Ｌａｎｄｓａｔ ＴＭ图象与ＪＥＲＳ－１ ＳＡＲ图象配准为例,提出了一种利用分类图象形成的二值图象相关寻求配准控制点,并应用表面样条插值以提高ＲＣＰ精度的多光谱与ＳＡＲ感图象配准方法。由于在ＳＡＲ图象分类中利用了斑纹噪声的纹理特     

Comparison of different speckle-reduction techniques in SAR images using wavelet transform

Speckle noise is always present in Synthetic Aperture Radar (SAR) images. Many methods that reduce speckle noise while preserving texture and detail have been presented previously. In this paper, a comparison of different methods using wavelet decomposition is performed and new improvements for traditional methods are introduced. These techniques are: Wiener filtering, classical soft threshold, a new adaptive soft threshold and Bayesian reconstruction. First, speckle noise in a SAR image was analysed statistically. Then, a simulated image following these characteristics was created in order to evaluate noise reduction. The mean squared error was classified depending on the spatial characteristics of a local region. This tool gave valuable information for algorithm assessment. In the comparison, the new adaptive soft threshold method provided excellent results concerning noise reduction and detail preservation compared with classical soft threshold and Wiener methods. In addition, it gave as much noise reduction as the most sophisticated Bayesian method, but much more efficiently. Hence, the adaptive version of soft thresholding outperformed the other techniques. This study also presents a rigorous framework for speckle noise simulation and noise reduction evaluation.     

基于形态Haar小波的SAR图像斑点噪声抑制方法

针对现有相干斑抑制算法不能在去除斑点噪声和保持图像边缘、细节信息之间做到很好的折中,提出了一种新的基于形态Haar小波变换的合成孔径雷达(SAR)图像斑点噪声抑制方法。该方法首先对SAR图像进行二维形态Haar小波分解,图像的边缘、细节和纹理信息在低频子带中得到了更好的保留,噪声主要分布在高频子带;然后,根据各高频子带噪声的特点,分别对高频子带进行均值和中值滤波达到去除斑点噪声的目的;最后,再对低频子带和处理后的高频子带进行形态Haar小波精确重构得到去斑图像。实验证明:该算法不仅大大改善了原始SAR图像的画面质量,同时很好地保持了原始SAR图像的纹理特性和细节信息;该算法去斑性能指标总体优于传统的Lee滤波、Frost滤波、Kuan滤波和小波软阈值法。