PolSAR ship detection based on the contrast enhancement of polarimetric scattering differences

The ship detection in polarimetric synthetic aperture radar (PolSAR) mode is a hot topic in recent years, because of the diversity of polarimetric scattering mechanisms between ship targets and sea clutter. To improve the detection performance of ship targets, this paper mainly develops the ship detection method based on the contrast enhancement utilizing the polarimetric scattering difference. The algorithm first enhances the target signal utilizing the scattering difference of the polarimetric coherency matrix between ship targets and sea clutter, and then a simple threshold is applied to distinguish the ship targets from the sea clutter. Finally, real PolSAR datasets recorded by AirSAR system are used to evaluate the effectiveness of the proposed detection method. Compared with other detection methods, experimental results indicate that the proposed method can effectively improve the detection performance of ship targets.     

基于监督非相干字典学习的极化SAR图像舰船目标检测

提出了一种结构化非相干字典学习算法 (Structured incoherent dictionary learning, SIDL),并将该方法应用于极化SAR (Polarimetric synthetic aperture radar, PoLSAR)图像舰船目标检测. 在字典学习阶段,构建了一个新的目标函数,为了降低子字典对交叉样本的稀疏表示能力, 将子字典对交叉样本的重构能量约束及子字典互相干性约束加入到字典学习目标函数中. 通过这两个约束, 降低了子字典对交叉样本的表示能力,目标和杂波的极化特征矢量在学习获得的字典下具有良好的区分特性. 该方法不依赖于目标后向散射能量,只利用学习获得的极化字典,根据测试样本在极化字典下的稀疏表示进行目标的检测. 实验采用RADARSAT-2数据进行了验证,对比实验结果表明,本文提出的方法可以更好地抑制杂波,对弱小目标实现检测,获得了更好的检测效果.     

Feature selection and weighted SVM classifier-based ship detection in PolSAR imagery

Target decomposition is an important method for ship detection in polarimetric synthetic aperture radar (SAR) imagery. Parameters such as the polarization entropy and alpha angle deduced from the coherency matrix eigenvalue decomposition capture the differences between the target and background from different views separately. However, under the conditions of a relatively high resolution and a rough sea, the contrast between ship and sea reduces in the aforementioned space. Based on the analyses of target decomposition theory and the target’s scattering mechanism, multi-polarization parameters can be used to characterize different scattering behaviours of the ship target and sea clutter. Moreover, each parameter has its own diverse significance in the practical detection problem. This article proposes a feature selection and weighted support vector machine (FSWSVM) classifier-based algorithm to detect ships in polarimetric SAR (PolSAR) imagery. First, the method constructs a feature vector that consists of multi-polarization parameters. Then, different polarization parameters are refined and weighted according to their significance in the support vector machine (SVM) classifier. Finally, ships are classified from the sea background and other false alarms by the classifier. The validation results on National Aeronautics and Space Administration/Jet Propulsion Laboratory (NASA/JPL) airborne synthetic aperture radar (AIRSAR) and Radarsat-2 quad polarimetric data illustrate that the method detects ship targets more precisely and reduces false alarms effectively.     

A PolSAR ship detector based on a multi-polarimetric-feature combination using visual attention

Ship detection can be significantly improved by using polarimetric synthetic aperture radar (PolSAR) imaging. In this article, we propose a PolSAR ship detection method based on the use of multi-featured polarization by using the visual attention model. Three polarimetric features, namely, the polarimetric contrast, the polarimetric scattering, and the polarimetric phase, are selected as the early features, and the pros and cons for each feature are discussed. The visual attention model is a framework that rapidly combines multiple features into one feature, which is improved according to the relationship of the selected features. Validation of the method is performed by analysing the multi-resolution process, the improved multi-feature process, the threshold strategy, the sensibility to the incidence angle of the sensors, and the performance of moving ship detection, which are analysed by Radarsat-2 fine quad images with automatic identification system data. Additionally, the false alarm/non-detection analysis and the computation cost analysis are also considered. In contrast to other ship detectors, the proposed detector is more effective and robust.     

基于多结构形态学的港口船舶检测方法

针对港口监控摄像机与船舶目标距离远,船舶目标成像小,海面噪声干扰大等特点,采用一种基于多结构元素形态学滤波的背景抑制算法.根据船舶的几何特征,采用多组结构元素的加权形态学滤波,将船舶目标与海面背景分离,然后利用基于邻域的自适应快速中值滤波滤除脉冲噪声,最后根据海面杂波在帧间运动不连续且面积较小等特点,利用连通域计算建立船舶的形态特征模型,来排除海面杂波对船舶检测的干扰.实验结果证明,该检测方法在实际港口获取的视频中,可以有效的抑制背景噪声和海面杂波,快速的检测出船舶目标.     

基于多重分形的雷达目标的模糊检测

利用多重分形的概念对海杂波和舰船雷达目标回波进行了分析,并提取出其多重分 形特征用于舰船目标检测.实验表明,广义维数谱具有良好的可分性和稳定性.在检测中,将 待查信号分为两类:海杂波目标和舰船目标,将广义维数谱作为特征矢量,计算其相对于两 类目标的隶属度并作出判断.多组检测实验证明了该方法的有效性和实用性.     

Sequential anomaly detection based on temporal-difference learning: Principles,models and case studies

Anomaly detection is an important problem that has been popularly researched within diverse research areas and application domains. One of the open problems in anomaly detection is the modeling and prediction of complex sequential data, which consist of a series of temporally related behavior patterns. In this paper, a novel sequential anomaly detection method based on temporal-difference (TD) learning is proposed, where the anomaly detection problem of multi-stage cyber attacks is considered as an application case. A Markov reward process model is presented for the anomaly detection and alarming process of sequential data and it is verified that when the reward function is properly defined, the anomaly probabilities of sequential behaviors are equivalent to the value functions of the Markov reward process. Therefore, TD learning algorithms in the reinforcement learning literature can be used to efficiently construct anomaly detection models of complex sequential behaviors by estimating the value functions of the Markov reward process. Compared with other machine learning methods for anomaly detection, the proposed approach has the advantage of simplified labeling process using delayed evaluative signals and the prediction accuracy can be improved even if labeled training data are limited. Based on the experimental results on intrusion detection of host computers using system call data, it was shown that the proposed anomaly detection method can achieve higher or at least comparable detection accuracies than other approaches including SVMs, and HMMs.     

Fully Polarimetric SAR Ship Detection based onPCDM Shannon Entropy#br#

Polarimetric Synthetic Aperture Radar（PolSAR）data contains rich polarization information about the scattering properties of ground objects,having beenwidely used in maritime monitoring and objects detection.The polarization reaction differences between ship targets and sea clutters are analyzed.A ship detection method using the Shannon entropy of the Polarimetric Covariance Difference Matrix (PCDM) is proposed in this paper,which is applied to fully polarimetric SAR images.To enhance the contrast between the ship targets and sea background,the PCDM is generated by calculating the elemental differences between the polarimetric covariance matrix at each pixel and its neighbors.Then the Shannon entropy of SAR images are extracted on the basis of the Shannon entropy calculation formula,and the character difference between the ships and background in the Shannon entropy map is presented for ship detection.The false alarms in the detection result caused by the azimuth ambiguities are removed,based on the displacement distance and energy ratio relationship,between the target and azimuth ambiguity.The Radarsat\|2 Fine Quad data and the Chinese GF\|3 Quad\|Polarimetric Stripmap Ⅰ data are used,to verify the effectiveness of the proposed method,and the SPAN method,HV channel image and polarimetric whitening filter (PWF) method are applied for comparison.The detection and comparison results indicate that the proposed method is able to effectively enhance the ship\|sea contrast,and has higher detection accuracy.     

SAR图像舰船目标检测的信息几何方法

目的 舰船目标检测是合成孔径雷达（SAR）图像在海事监测领域中的一项重要应用。由于海面微波散射的复杂性,SAR图像中海杂波分布具有非均匀性、非平稳性等特点,传统的基于恒虚警率（CFAR）的SAR图像舰船检测算法难以适应复杂多变的海杂波环境,无法实现实时有效的智能检测任务。鉴于此,本文提出了基于信息几何的SAR图像船舰目标检测方法,旨在分析统计流形及其在参数空间中的几何结构,探讨信息几何在SAR图像目标检测应用中的切入点,从新的角度提升该应用领域的理论与技术水平。方法 首先,运用威布尔分布族对SAR图像中的海杂波进行统计建模,利用最大似然方法估计SAR图像局部邻域像素的分布参数,并将不同参数下的统计分布作为威布尔流形上的不同点;其次,融合高斯分布的费歇耳度量来构造威布尔流形空间中概率分布之间的测度,实现目标与背景区域的差异性表征;最后,利用最大类间方差法,实现SAR图像舰船目标检测。结果 实验和分析表明,相比于传统的基于恒虚警率的检测算法,信息几何方法可以有效地区分舰船目标和海杂波背景,降低虚警率,实现舰船目标显著性表示与检测。结论 由于舰船目标的复杂后向散射特性,如何有效地表征这一差异,是统计类检测算法的关键所在。本文依据信息几何理论,将概率分布族的参数空间视为微分流形,在参数流形上构造合适的黎曼度量,对SAR图像中各像素局部邻域进行测度表征,可以显著性表示目标与背景杂波之间的统计差异,实现舰船目标检测。     

多特征融合红外舰船尾流检测方法研究

针对舰船热尾流红外图像易受海杂波干扰、对比度偏低,传统方式无法对其进行识别的问题,提出一种基于Gabor滤波组和局部信息熵特征融合的红外舰船尾流检测算法。首先,应用灰度共生矩阵计算尾流与海面背景的对比度,判断该区域是否存在舰船尾迹,并提取出感兴趣区域以提高算法后续处理速度;其次,将多方向Gabor滤波器和局部信息熵两种纹理进行特征融合,实现舰船尾流特征增强;最后,经阈值分割、Hough变换实现红外舰船尾迹检测。实验结果表明,该方法能够有效地保留舰船尾流的纹理特征和细节,准确地提取完整的尾流边缘,从而大大提高检测率。     

基于改进Faster R-CNN的SAR船舶目标检测方法

合成孔径雷达（Synthetic Aperture Radar, SAR）船舶检测在海洋交通监控中发挥着重要作用,传统SAR目标检测算法一般利用目标与背景杂波之间的对比度差异进行检测,在近岸海域等复杂场景下检测效果较差。为了提高在复杂场景下的检测性能,本文提出一种基于改进Faster R-CNN的船舶检测方法,在分析不同特征分辨率对检测性能影响的基础上,结合VGG的思想与扩张卷积设计一个适用于SAR船舶目标检测的特征提取网络,以提升对小型船舶目标的检测能力。另外,根据sentinel-1A数据集中目标尺寸分布选取小尺寸anchor,并通过去除冗余anchor,将检测速度提升了一倍。在sentinel-1A数据集上的实验证明本文提出的算法能够快速、有效地从复杂场景SAR图像中检测出船舶目标。     

基于改进的S-NMF方法的全极化SAR船舶检测

全极化SAR影像应用于海上船舶检测,如何在不降低检测率的同时,利用极化信息降低虚警率,是一个值得研究的问题。根据SAR极化矩阵3个特征值的非负性和稀疏性,提出了改进的非负矩阵分解S\|NMF(Sparseness-Nonnegative Matrix Factorization)方法:将最大和次优特征值用于NMF分解,因为两者占有目标97%以上的能量,能够保证最大的检测率,分解后所得结果为检测结果I;而强海杂波、“目标鬼影”等虚警在第三特征值上表现较弱,利用第三特征值与结果I相乘,可进一步强化目标弱化虚警。然后采用OS-CFAR算法对相乘后的图像进行检测,输出最终结果。最后用带有AIS数据的Radarsat-2全极化数据对该方法进行验证,并与SPAN方法、HV通道、PWF方法的检测结果进行对比,结果表明:该方法不但能够正确地检测出船舶目标,而且能够有效降低虚警。     

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。     

基于多尺度静态小波分解的改进型CFAR船只检测算法

SAR船只目标检测是实现海上安全监测的有效手段。由于在海杂波较为复杂的情况下,传统CFAR算法对于弱小船只检测效果不佳,本文提出了基于多尺度静态小波分解的改进型CFAR检测算法。首先通过实验选出最优小波基及最佳小波分解级数,再利用幂运算对经多尺度乘性增强的小波系数进行优化,以增强船只与海洋背景的对比度,从而运用简单的CFAR算法即可得到较好的检测效果。最后,以新型星载ALOS-PALSAR数据为例,通过与传统CFAR算法的对比实验,验证本文算法的有效性。实验表明,利用Sym2最优小波基的较强边缘检测能力以及小波多尺度乘性增强,双重强化了船只目标的边缘影像特征,并有效抑制了海杂波噪声,使得本文算法在提高检测率与降低虚警率两方面都优于传统CFAR算法,有利于高海杂波下弱小船只的检测。     

基于特征增强的SAR图像舰船小目标检测算法

针对合成孔径雷达(SAR)图像中小目标舰船检测困难的问题,提出基于单次多盒检测器的一种特征增强小目标检测算法.首先提出一种混合多特征提取模块,采用并行的普通卷积、不同空洞率的空洞卷积以及非对称卷积形成与舰船目标相匹配的感受野,以提高浅层网络对复杂形状小目标的特征提取能力;然后提出一种邻近多特征融合模块,将特征信息进行更科学的深层次融合,对小目标特征进一步增强;最后根据SAR图像单通道的特性,缩减特征提取网络VGG-16的冗余特征通道.在公开的SSDD数据集上与其他检测算法进行对比实验,实验结果表明,所提出方法将平均精确度提升至93.44%,检测速度提升至41.8FPS,参数量减少为18.74M,综合性能优于其他检测算法.     

Parametric detection in non-stationary correlated clutter using a sequential approach

Sequential detection provides a powerful solution to minimize the required number of observations for a given performance. Due to the non-stationary nature of clutter, this problem is recurrent in radar applications. In this paper, we develop a sequential parametric adaptive detection algorithm based on the approximation of clutter as an autoregressive process. Stationary segments are considered where both space and time windows are minimized, respectively, by using one secondary cell on each side of the cell under test and by applying a sequential test. We derive the distributions of the considered test statistic and give a closed form expression for the upper threshold whereas, the lower one is given as a simply numerical solution of a proper equation, rather than use the commonly Monte Carlo method based ones. The proposed approach is compared to an existing method based on a fixed sample size. Results obtained using synthetic and real data show that the proposed scheme reduces substantially the required sample size with detection performance close to that of the fixed sample size method.     

Human–machine interface in bioprosthesis control using EMG signal classification

Abstract: We present a concept of human–machine interface intended for the task of bioprosthesis decision control by means of sequential recognition of the patient's intent based on the electromyography (EMG) signal acquired from his/her body. The EMG signal characteristics, the problem of processing the signals including acquisition and feature extraction and their classification are discussed. The contextual (sequential) recognition via fuzzy relations for the classification of the patient's intent is considered and the implied decision algorithms are presented. In the proposed method, the fuzzy relation is determined on the basis of the learning set as a solution of an appropriate optimization problem and then this relation is used in the form of a matrix of membership degrees at successive instants of the sequential decision process. Three algorithms of sequential classification which differ from one another in the sets of input data and procedure are described. The proposed algorithms were experimentally tested in the recognition of phases of the grasping process of the hand on the basis of the EMG signal, where the real-coded genetic algorithm was used as an optimization procedure. The concept of the measurement stand which was the source of information exploited in the experimental investigations of the algorithms is also described.     

一种基于图像底层特征的隐马尔可夫人体检测方法

提出一种单幅图像中的人体检测方法.该方法用隐马尔可夫模型表示人体,根据给定的人体结构序列估计产生该序列的图像区域,从而将人体检测问题转化为隐马尔可夫解码问题求解.首先对图像进行Mean-Shift分割,并根据颜色信息搜索出属于躯干的区域,然后将明暗度、颜色及边缘3种底层特征相结合,估计特征匹配概率并由此获得四肢部分的候选区域.最后估计候选区域的连接概率并利用隐马尔可夫解码算法找出最优的人体配置区域.实验结果表明,该方法对于复杂背景中具有不同姿态的人体图像可得到较满意的检测结果.和其它检测方法相比,该方法并非单纯地给出矩形近似的人体各个部分,同时还获得较完整分割的人体图像.尤其对于图像分辨率较低、图像中的人体较小且存在运动模糊的情况,该方法能够获得较好的检测结果.     

基于改进YOLOV3-Tiny的海面船舰目标快速检测

为实现海面船舰目标的快速、准确检测,提出一种改进的船舰目标检测算法。在网络结构方面根据船舰目标的特点,对浅层信息进行强化重构以降低小目标的漏检率,同时引入改进的残差网络增加网络深度和降低网络参数计算量,并且采用金字塔网络进行多尺度特征融合,以兼顾图像中大小船舰目标的检测性能。在网络训练中利用迁移学习策略进行网络模型的训练,以克服船舰图像样本集有限的问题。在视频检测中利用帧间图像结构相似度进行选择性网络前向计算,以提高视频帧检测速率。实验结果表明,该算法海面船舰目标检测的准确率达到92.4%,较YOLOV3-Tiny提高7个百分点,召回率达到88.6%,且在CPU平台上船舰目标的检测速度达到12 frame/s。     

Similarity-enhanced target detection algorithm using polarimetric SAR images

Target detection and analysis using polarimetric synthetic aperture radar (PolSAR) images are currently of great interest in synthetic aperture radar (SAR) applications. For a complex target, the scattering characteristics are determined by different independent sub-scatterers and their interaction; therefore, the scattering characteristics should be described by a statistical method due to randomness and depolarization. Furthermore, the inherent speckle in SAR data must be reduced by spatial averaging at the expense of loss of spatial resolution. The polarimetric similarity parameter (PSP) is an effective parameter to analyse target characteristics. In order to describe a complex distributed target, two new methods for calculating PSP are proposed, namely Stokes matrix-based PSP (S-PSP) and multiple PolSAR similarity parameter (MPSP). The characteristics of a target can be described and extracted on the basis of the polarimetric similarity, and then the similarity-enhanced target detection methods using S-PSP and MPSP are implemented and demonstrated with German Aerospace Centre (DLR) experimental SAR L-band multiple temporal PolSAR images of Oberpfaffenhofen test site (DE), Germany. The results confirmed that the proposed methods are effective for detection and analysis of buildings in urban areas.