A novel approach based on structural information for change detection in SAR images

Structural information, extracted by simulating the human visual system (HVS), is independent of viewing conditions and individual observers. Structural similarity (SSIM), a measure of similarity between two images, has been widely used in image quality assessment. Given the fact that the change detection techniques identify the changed area by the similarity of multi-temporal images, SSIM has significant prospect in change detection of synthetic aperture radar (SAR) images. However, the experimental results show that SSIM performs worse in change detection of multi-temporal SAR images. In this study, we first propose an advanced SSIM (ASSIM) based on a two-step assumption of extracting structural information and a visual attention measure (VAM) model. Then, we propose a novel approach based on ASSIM for change detection in SAR images. SSIM, ASSIM, and state-of-the-art methods are tested on two datasets to compare their performances in change detection of SAR images. Experimental results show that the proposed method can acquire a better difference image than SSIM and other state-of-the-art methods, and improve the accuracy of change detection in SAR images effectively.     

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.     

Dark formation detection using neural networks

Synthetic Aperture Radar (SAR) images are extensively used for dark formation detection in marine environment, as they are not affected by local weather conditions and cloudiness. Dark formations can be caused by man‐made actions (e.g. oil spills) or natural ocean phenomena (e.g. natural slicks and wind front areas). Radar backscatter values for oil spills are very similar to backscatter values for very calm sea areas and other ocean phenomena because they dampen the capillary and short gravity sea waves. Thus, traditionally, dark formation detection is the first stage of the oil‐spill detection procedure and in most studies is performed manually or using a fixed size window in which a threshold value is adopted. In high‐resolution imagery, dark formation detection may fail due to the nonlinear behaviour of the pixel values contained in the dark formation and in the area around it. In this paper, we examine the ability of two feed‐forward neural network families, i.e. Multilayer Perceptron (MLP) and the Radial Basis Function (RBF) networks, to detect dark formations in high‐resolution SAR images. The general objective of this paper is to test the potential of artificial neural networks for dark formation detection using SAR high‐resolution satellite images. Both the type and the architecture of the network are subjects of research. The inputs into the networks are the original SAR images. Each network is called to classify an area of the image as dark area or sea. The group of MLP networks can be recognized as the most suitable group for dark formation detection, as it presents reliable stable results for all the examined accuracies. Nevertheless, in terms of single topology, there is no an MLP topology that performs significantly better than the others.     

High-resolution SAR images segmentation using NSCT denoising and QIGA based parameters selection of PCNN model

The high-resolution synthetic aperture radar (SAR) images usually contain inhomogeneous coherent speckle noises. For the high-resolution SAR image segmentation with such noises, the conventional methods based on pulse coupled neural networks (PCNN) have to face heavy parameters with a low efficiency. In order to solve the problems, this paper proposes a novel SAR image segmentation algorithm based on non-subsampling Contourlet transform (NSCT) denoising and quantum immune genetic algorithm (QIGA) improved PCNN models. The proposed method first denoising the SAR images for a pre-processing based on NSCT. Then, by using the QIGA to select parameters for the PCNN models, such models self-adaptively select the suitable parameters for segmentation of SAR images with different scenes. This method decreases the number of parameters in the PCNN models and improves the efficiency of PCNN models. At last, by using the optimal threshold to binary the segmented SAR images, the small objects and large scales from the original SAR images will be segmented. To validate the feasibility and effectiveness of the proposed algorithm, four different comparable experiments are applied to validate the proposed algorithm. Experimental results have shown that NSCT pre-processing has a better performance for coherent speckle noises suppression, and QIGA-PCNN model based on denoised SAR images has an obvious segmentation performance improvement on region consistency and region contrast than state-of-the-arts methods. Besides, the segmentation efficiency is also improved than conventional PCNN model, and the level of time complexity meets the state-of-the-arts methods. Our proposed NSCT+QIGA-PCNN model can be used for small object segmentation and large scale segmentation in high-resolution SAR images. The segmented results will be further used for object classification and recognition, regions of interest extraction, and moving object detection and tracking.

     

双向特征融合的数据自适应SAR图像舰船目标检测模型

目的 利用合成孔径雷达（synthetic aperture radar,SAR）图像进行舰船目标检测是实施海洋监视的重要手段。基于深度学习的目标检测模型在自然图像目标检测任务中取得了巨大成功,但由于自然图像与SAR图像的差异,不能将其直接迁移到SAR图像目标检测中。针对SAR图像目标检测实际应用中对速度和精度的需求,借鉴经典的单阶段目标检测模型（single shot detector,SSD）框架,提出一种基于特征优化的轻量化SAR图像舰船目标检测网络。方法 改进模型并精简网络结构,提出一种数据驱动的目标分布聚类算法,学习SAR数据集的目标尺度、长宽比分布特性,用于网络参数设定;对卷积神经网络（convolutional neural network,CNN）提取的特征进行优化,提出一种双向高低层特征融合机制,将高层特征的语义信息通过语义聚合模块加成到低层特征中,在低层特征中提取特征平均图,处理后作为高层特征的注意力权重图对高层特征进行逐像素加权,将低层特征丰富的空间信息融入到高层特征中。结果 利用公开的SAR舰船目标检测数据集（SAR ship detection dataset,SSDD）进行实验,与原始的SSD模型相比,轻量化结构设计在不损失检测精度的前提下,样本测试时间仅为SSD的65%;双向特征融合机制将平均精确度（average precision,AP）值由77.93%提升至80.13%,训练和测试时间分别为SSD的64.1%和72.6%;与公开的基于深度学习的SAR舰船目标检测方法相比,本文方法在速度和精度上都取得了最佳性能,AP值较精度次优模型提升了1.23%,训练和测试时间较精度次优模型分别提升了559.34 ms和175.35 ms。结论 实验充分验证了本文所提模型的有效性,本文模型兼具检测速度与精度优势,具有很强的实用性。     

基于空间信息的SAR图像船只交通监测方法

快速准确获得研究区海上船只状态,对海洋交通监测具有重要意义。本文从技术角度提出了基于空间信息的SAR图像海上船只交通监测方法。首先利用已有的空间先验信息对图像进行自动陆地掩膜;建立海面杂波分布模型,对海面船只进行检测;估算船只的长度、面积、中心坐标等参数信息,并对目标进行筛选;最后根据船只信息库结合空间信息平台进行统计与分析,可为海上船只监测以及交通规划等应用提供决策信息。重点介绍了数据处理方法,并以9景ERS2数据进行了实验和详细分析,通过实验,分析了技术的可行性与正确性。     

Capturing what human eyes perceive: A visual hierarchy generation approach to emulating saliency-based visual attention for grid-like urban street networks

Visual hierarchy is an important notion in urban imagery research. As the skeletons of cities, urban streets attract more attention from urban residents and street network hierarchies are important references for urban planning and urban studies. However, due to the characteristic of over-regularization, it is often difficult for humans to differentiate visual salience for grid-like street networks, resulting in the hierarchies of grid-like streets yielded by existing methods being prone to cause visual cognitive confusion. Therefore, in this study, we proposed a novel model to quantify the extent to which a street attracts human visual attention through emulating the visual attention mechanism that can capture the focus of relatively significant elements at different levels of perception. Using the natural street (also known as the stroke) as the sensor unit, the comprehensive visual salience (CVS) index combining the geometric competitive factors of natural streets at the local scale and psychological competitive factors of natural streets at the global scale is designed. Finally, the visual salience of the urban natural streets is ranked by these CVS scores and the visual hierarchy is derived by the head/tail breaks scheme. The model was applied to eight typical grid-like street networks and the results show that the performance of visual discrimination on street hierarchies is greatly improved. Our hierarchy generation method could effectively detect visually prominent streets for grid-like street networks and generate the visual hierarchies of grid-like street networks that conform to the hierarchies perceived by human eyes. These results would provide helpful suggestions in practical urban street network applications.     

尺度自适应的SAR图像显著性检测方法

人类视觉系统能够通过对场景中感兴趣的不同事物进行显著性检测,有效地配置处理资源。基于视觉注意机制的显著性检测方法能够简化遥感影像场景分析、目标解译的复杂程度,节省处理资源。以视觉注意机制为基础,提出了一种尺度自适应的SAR图像显著性检测方法,通过不同尺度下的局部复杂度和自差异性来度量图像的显著性测度,设计显著性尺度确定算法以及融合显著性尺度和显著性测度以生成显著图,完成显著性检测的流程。实验结果表明该方法能够有效应用于SAR图像显著性检测,较之其他主流显著区域检测算法更适用于SAR图像场景分析。     

Soil-moisture estimation from TerraSAR-X data using neural networks

Early prediction of natural disasters like floods and landslides is essential for reasons of public safety. This can be attained by processing Synthetic-Aperture Radar (SAR) images and retrieving soil-moisture parameters. In this article, TerraSAR-X product images are investigated in combination with a water-cloud model based on the Shi semi-empirical model to determine the accuracy of soil-moisture parameter retrieval. SAR images were captured between January 2008 and September 2010 in the vicinity of the city Maribor, Slovenia, at different incidence angles. The water-cloud model provides acceptable estimated soil-moisture parameters at bare or scarcely vegetated soil areas. However, this model is too sensitive to speckle noise; therefore, a pre-processing step for speckle-noise reduction is carried out. Afterwards, self-organizing neural networks (SOM) are used to segment the areas at which the performance of this model is poor, and at the same time neural networks are also used for a more accurate approximation of model parameters’ values. Ground-truth is measured using the Pico64 sensor located on the field, simultaneously with capturing SAR images, in order to enable the comparison and validation of the obtained results. Experimental results show that the proposed method outperforms the water-cloud model accuracy over all incidence angles.     

基于OpenSceneGraph的无人机雷达载荷视景仿真应用研究

为了实现无人机视景仿真训练中合成孔径雷达（Synthetic aperture radar-SAR）载荷的仿真,本文采用开源仿真平台OpenSceneGraph（OSG）,设计一种SAR雷达图像仿真的方法。该方法在OSG的基础上,采用GLSLang（OpenGL Shading Language）渲染技术,解决雷达图像的渲染,并实现雷达图像的地面站显示。最后设计仿真流程并对该方法进行仿真验证。仿真结果表明,本文设计的方法能够实现无人机SAR雷达视景仿真的功能,为无人机雷达载荷视景仿真提供一种新的技术途径,并在某型无人机仿真训练中得到应用。     

基于矩阵分解的海洋SAR图像舰船检测

针对海洋原始图像与低秩和稀疏矩阵分解模型数据结构不一致的问题,本文提出一种新的基于矩阵分解的海洋SAR图像舰船检测方法。首先该方法需对结构化相似的海洋SAR图像进行重组;然后根据重组矩阵特性适应性设计一个分解精度更高、分解速度更快的新矩阵分解模型,并利用增广拉格朗日乘子法求解模型,在不依赖任何杂波模型和检测统计量的前提下,实现代表舰船目标的稀疏成分的提取;最后利用形态学处理进行优化,实现海洋SAR图像舰船目标的检测。基于高分三号SAR卫星数据的实验结果表明,相比已有的基于鲁棒主成分分析的舰船检测方法,本文方法在处理复杂海况时,能更快速度地以较好的形状从海杂波中准确提取舰船目标,具有更好的鲁棒性。     

SAR图象中道路网络提取算法研究

提出了一种利用遗传算法从高分辨率SAR图象中提取道路网络的方法。高分辨率SAR图象中目标背景复杂,同时由于受相干斑噪声的影响,很难直接从原始图象数据中提取道路特征。首先利用模糊C均值对滤波后的图象进行聚类,将道路类象素从图象中分离出来;根据聚类结果及道路特征建立数学模型,利用遗传算法搜索全局最优道路。实验结果表明该方法可以很好地从SAR图象中提取道路网络。     

长度归一化扫描的合成孔径雷达图像船舶尾迹恒虚警率检测

提出一种基于长度归一化扫描的合成孔径雷达(SAR)图像船舶尾迹检测算法.存在距离向运动分量的船舶在SAR图像上会发生方位向偏移,那么尾迹的起点必在方位向上这一偏移量范围内.根据这一物理事实,将尾迹检测的搜索范围限定在可能为尾迹的线段上,从而提高了检测效率.算法通过利用线性积分和长度归一化这两个方法将矩形滑动窗口下的线性特征检测转化为了点特征检测,并通过经典的虚警率(CFAR)检测理论实现检测结果的输出.利用COSMO-SkyMed数据对该算法进行了实验验证,实验结果表明,该算法在尾迹检测上具有检测能力强、速度快的优点,船舶速度反演具有较高精度.     

Change detection in SAR images based on matrix factorisation and a Bayes classifier

Change detection in synthetic aperture radar (SAR) images can be made as a matrix factorisation model, and it can detect the changes based on the foreground information in the image. However, these methods cannot obtain satisfactory results in the change detection of SAR images because reliable background data are often not available. In this article, we propose a matrix factorisation model based on a naïve Bayes classifier to explore the low-rank and sparse information, and then detect the changes in SAR images. The factorisation model of the low-rank and sparse matrix extracts both background and foreground information from images. From the low-rank and sparse matrices, we can get the background and foreground information recovered, respectively. Then by computing the mean and variance matrix of the unchanged and changed region information, we will obtain the statistical features. The statistical features are then used to build a naïve Bayes classifier, which is used to distinguish the change detection results, and all of them are based on the acquired data distribution. The experiments, which are based on four real data sets, indicate that the approach gets a better performance than some other state-of-the-art algorithms.     

基于深度学习的SAR弱小目标检测研究进展

随着合成孔径雷达(SAR)技术的不断进步, 大范围观测和高分辨率成像使得SAR图像中包含了大量特征微弱的小尺寸目标, 通常涵盖飞机、车辆、油罐、船舶等高价值民用目标和关键军事目标, 这类目标尺寸较小、特征微弱、稠密相连、形态多变, 对它们进行精确的检测是当前SAR图像解译的难题. 随着深度学习技术的发展, 研究者们针对SAR弱小目标的成像特性和检测挑战, 通过对深度学习网络的精细调整和优化, 成功地推动了本领域的进步. 本文将全面回顾基于深度学习的SAR图像弱小目标检测, 以数据集和方法为研究对象, 深入分析SAR弱小目标检测任务所面临的主要挑战, 总结最新检测方法的特点和应用场景, 并汇总整理了公开数据集与常用性能评估指标. 最后, 总结本任务的应用现状, 并对未来的发展趋势进行展望.     

基于目标检测的SAR图像变化检测方法

SAR图像变化检测有着广阔的应用前景,但目前的方法普遍以精确的配准为前提,使其适用范围受到限制。针对人造目标在SAR图像上的特点,提出了一种基于目标检测的SAR图像变化检测方法。通过图像中的人造目标之间相对位置关系的相似程度确定图像的变化情况,以此来降低对图像配准精度的要求。实验表明该方法在很宽的配准精度范围内都可获得较满意的结果。     

非下采样Contourlet变换与脉冲耦合神经网络相结合的SAR与多光谱图像融合

由于获取地物波谱信息的波段范围及成像方式的不同,SAR与多光谱图像所得到的信息有很大差异,而且SAR图像会受到严重的相干斑噪声干扰,因此SAR与多光谱图像的融合很难获得满意的效果。考虑到非下采样Contourlet变换(NSCT)相比于其他多尺度几何分析方法的优势,提出了一种NSCT与脉冲耦合神经网络(PCNN)相结合的SAR与多光谱图像融合方法。源图像首先经过NSCT分解获得不同尺度多个方向下的分解系数,将分解系数的高斯拉普拉斯算子能量作为脉冲耦合神经网络模型的输入,具有较大点火频率的系数将被选择作为融合图像的系数,最后经过NSCT重构得到最终的融合图像。实验结果表明,这种算法无论在主观视觉还是在客观指标上都要优于之前的许多算法。     

基于特征融合的高分辨率SAR 图像道路提取

随着机载和星载高分辨率SAR图像得到越来越多的应用, 人们开始研究新的有效的解译工具。虽然一个专业判读人员或许能够通过观察图像上亮的或暗的线性结构来检测道路网, 但是道路的自动检测仍然非常困难。提出一种简单的高分辨率SAR 图像主要道路自动提取方法。该方法分为三步: 第一步, 对原始图像进行预滤波, 分别进行了两个阈值化过程, 目的是去除不感兴趣区域;第二步, 输入第一步结果, 用Hough 变换分别进行道路识别; 最后一步基于特征融合技术, 利用一定的融合方法将检测的结果进行融合。根据对实际图像检测的结果, 证明该方法对于检测高分辨率SAR图像上的主要道路是有效的。     

A biologically inspired object-based visual attention model

A biologically inspired object-based visual attention model is proposed in this paper. This model includes a training phase and an attention phase. In the training phase, all training targets are fused into a target class and all training backgrounds are fused into a background class. Weight vector is computed as the ratio of the mean target class saliency and the mean background class saliency for each feature. In the attention phase, for an attended scene, all feature maps are combined into a top-down salience map with the weight vector by a hierarchy method. Then, top-down and bottom-up salience map are fused into a global salience map which guides the visual attention. At last, the size of each salient region is obtained by maximizing entropy. The merit of our model is that it can attend a class target object which can appear in the corresponding background class. Experimental results indicate that: when the attended target object doesn’t always appear in the background corresponding to that in the training images, our proposed model is excellent to Navalpakkam’s model and the top-down approach of VOCUS.     

结合张量投票和Snakes模型的SAR图像道路提取

目的 Snakes模型对曲线轮廓具有良好的拟合能力,被广泛应用于遥感图像的道路提取。但SAR图像受乘性斑点噪声影响严重,因此利用Snakes模型从SAR图像提取道路时,传统的以图像灰度负梯度为外部能量的方法难以取得理想结果。针对这一问题,利用计算机视觉中的张量投票算法可以从噪声掩盖的图像中提取显著结构特征的特点,将张量投票与Snakes模型结合从SAR图像提取道路。方法 首先利用模糊C均值分割法从SAR图像中分割出道路类,然后对道路类进行张量投票获得每点的曲线显著性值,最后以该曲线显著性值的负值作为Snakes模型外部能量从SAR图像提取道路。在Snakes模型能量最小化阶段,提出了一种优化的拟合策略,一边内插节点一边最小化Snakes模型能量。结果 利用机载和星载不同场景的SAR图像进行实验,与同类的基于Snakes模型的半自动方法相比,本文方法对曲率较大的道路仅需较少控制点即可取得较好的拟合效果;与基于MRF模型的自动方法相比,本文方法对道路提取的完整率、正确率、检测质量都优于基于MRF模型的方法,并且提取的时间远远快于基于MRF模型的方法,对于大范围的道路网提取将更为实用。结论 本文方法充分考虑到道路的几何形态特征,利用张量投票算法对该特征进行量化,并利用优化的拟合策略来最小化Snakes模型能量来提取道路。基于机载和星载SAR图像的实验表明本文方法可以较好地提取不同场景中的主要道路目标和道路网。