A New Ship Target Detection Algorithm based on SVMin High Resolution SAR Images

The characteristics of ocean background and target in the high resolution synthetic aperture radar (SAR) images are analyzed.Aiming at the requirements of ship detection in high-resolution synthetic aperture radar (SAR) image,the detection accuracy,intelligence level,real-time and processing efficiency,we put forward a high resolution SAR images ship detection algorithm based on support vector machine.The algorithm designs a pre-training support vector machine (SVM) classifier and complete the screening of the ship target block area,then the algorithm of optimal entropy thresholds proposed by Kapur,Sahoo,Wong(KSW) will be used on the target area selected for fine detection of ship targets.In this paper,several commercial satellite data,such as TerraSAR-X,are used to verify the experiment.Comparing with the classical CFAR detection algorithm,Experimental results show that the algorithm can improve the false alarm caused by the speckle noise and ocean clutter background inhomogeneity.At the same time,the detection speed is also increased by 20% to 35%.     

机场场面监视雷达目标检测新方法

机场场面监视 雷达可得到高分辨率实孔径图像,常规的雷达目标检测方法难以检测出其中的目标。本文首 先分析了场面监视雷达目标检测中的问题,然后根据场面监视雷达回波信号的特点,提出了 一种基于数字图像处理思想的目标检测新方法。给出了算法处理的基本流程和主要模块的具 体实现方法。国内机场实测数据的处理结果表明本文算法可靠地检测出目标区域,目标团簇 凝聚处理可有效消除孤立虚警点并填充目标区域内部漏警块。本文提出的方法对于场面监视 雷达系统的研制有一定借鉴意义。     

自动警戒圈的目标检测算法

针对雷达/ARPA模拟器的特点,利用现代图像处理技术,将前后两个扫描周期的回波图像转化为二值图像,根据自动警戒圈的特点,采用使用逻辑运算和区域生长的方法,提出了目标检测算法,该算法不需要引入复杂的运算,并能较好地去除噪声对目标检测的干扰,实验表明该算法适用于当前的雷达/ARPA模拟器的目标检测。     

一种基于连通分析的UWB SAR目标检测算法

由于超宽带合成孔径雷达(UWB SAR)具有较强的穿透性而被广泛用于探测叶簇覆盖目标,但目前针对此种目标的检测尚未有系统完整的检测算法提出,多数研究机构在对基于UWB SAR的叶簇覆盖目标进行检测时,均沿用美国Lincoln实验室提出的三级结构检测流程,该通用检测算法在对高波段、高分辨率全极化SAR数据进行目标检测时,虽表现出良好的检测和识别性能,但用于UWB SAR叶簇覆盖目标检测时,则存在诸多不适用性。该文在对通用检测算法用于UWB SAR目标检测时存在的问题进行分析的基础上,提出了一种适用的新算法,该新算法通过滑窗平均、低门限恒虚警(CFAR)检测以及连通分析降低了算法对检测环境的要求,从而增强了算法的适用性和稳健性,最后给出了采用通用检测算法和新算法对UWB SAR图像中叶簇覆盖目标进行检测的结果,并验证了新算法在UWB SAR叶簇覆盖目标检测中的有效性。     

Simulation of radar with a knife-like antenna beam using precipitation radar data

The concept of radar using a knife-like antenna beam is discussed and compared with precipitation radar (PR). An example of PR data processing is given. Two approaches are used to retrieve variance of slope: point-to-point algorithms and a linear angular algorithm. The algorithm for the PR data transformation into data of radar with a knife-like antenna beam has been developed. Transformation of real satellite data into data of radar with a knife-like antenna beam enables one for the first time to simulate measurements of future space radar qualitatively. Transformed data are used to validate the retrieval algorithms developed for radar with a knife-like antenna beam. Numerical simulation is also used to test the retrieval algorithms. The noise effect on the precision of slope variance retrieval for the PR and radar with a knife-like antenna beam is considered. Data processing confirms that the precision of radar with a knife-like antenna beam is significantly higher than the precision of PR. Numerical simulation is also used to explore the possibility of sea-surface slope imaging. The obtained results confirm that only radar with a knife-like antenna beam can be employed to retrieve real images of the processes occurring on sea-surface slopes.     

SAR目标检测中的聚类算法改进

合成孔径雷达(简称SAR)自动目标识别(简称ATR)算法是一个标准的目标检测算法,该算法分为3级:Prescreener、Discriminator和Classifier,处于Prescreener级和Discriminator级之间的聚类算法对于检测算法的整体性能有重要的影响。为此首先介绍了常规聚类算法的聚类步骤,然后针对实际应用情况分析了常规算法在聚类过程中存在的问题,并从图像数据读取顺序和准聚类中心计算方法两个方面对聚类算法进行了改进,基于两幅实际SAR图像得到的聚类结果验证了聚类算法改进的有效性。     

A versatile hardware architecture for a constant false alarm rate processor based on a linear insertion sorter

Constant False Alarm Rate (CFAR) algorithms are used in digital signal processing applications to extract targets from background in noisy environments. Some examples of applications are target detection in radar environments, image processing, medical engineering, power quality analysis, features detection in satellite images, Pseudo-Noise (PN) code detectors, among others. This paper presents a versatile hardware architecture that implements six variants of the CFAR algorithm based on linear and nonlinear operations for radar applications. Since some implemented CFAR algorithms require sorting the input samples, a linear sorter based on a First In First Out (FIFO) schema is used. The proposed architecture, known as CFAR processor, can be used as a specialized module or co-processor for Software Defined Radar (SDR) applications. The results of implementing the CFAR processor on a Field Programmable Gate Array (FPGA) are presented and discussed.     

A deformable template approach to detecting straight edges in radarimages

This paper addresses the problem of locating two straight and parallel road edges in images that are acquired from a stationary millimeter-wave radar platform positioned near ground-level. A fast, robust, and completely data-driven Bayesian solution to this problem is developed, and it has applications in automotive vision enhancement. The method employed in this paper makes use of a deformable template model of the expected road edges, a two-parameter log-normal model of the ground-level millimeter-wave (GLEM) radar imaging process, a maximum a posteriori (MAP) formulation of the straight edge detection problem, and a Monte Carlo algorithm to maximize the posterior density. Experimental results are presented by applying the method on GLEM radar images of actual roads. The performance of the method is assessed against ground truth for a variety of road scenes     

机载脉冲多普勒雷达DBS成像实验研究

脉冲多普勒雷达是现代战斗机普遍采用的一种典型雷达体制。多普勒波束锐化（DBS）已成为机载脉冲多普勒雷达在空／地工作模式中对地面进行高分辨成像的有效途径,因而受到了国内外广泛的重视。本文首先分析了DBS技术的基本原理及其实现步骤,针对载机惯导参数误差较大的实际情况,应用本文提出的新的多普勒质心估计算法－－“曲线拟合相位较正叠代算法”,对某型脉冲多普勒雷达的实测数据进行了成像处理实验研究,给出了实测数据的DBS成像结果,证明了处理过程的有效性。     

一种合成孔径雷达图像阴影和目标检测的方法

提出了一种进行高分辨率SAR(synthetic aperture radar)图像阴影和目标检测的新思路.首先给出了基于等效视数模型的图像RCS(radar cross section)重构算法进行阴影检测,然后通过非线性积累,达到目标检测的目的.与CFAR(constant false alarm rate)检测相比,能够检测到阴影和更多感兴趣的目标.     

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。     

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.     

Fast algorithm based on triplet Markov fields for unsupervised multi-class segmentation of SAR images

Non-Gaussian triplet Markov fields (TMF) model is suitable for dealing with multi-class segmentation of non-stationary and non-Gaussian synthetic aperture radar (SAR) images.Considering the complexity of the model and algorithm,as well as the requirement of real-time,and robust and efficient processing of SAR images,a fast algorithm based on TMF for unsupervised multi-class segmentation of SAR images is proposed in this paper.For the speckle noise in SAR images,numerical characteristic,threshold selection a...     

A novel method for speckle noise reduction and ship target detection in SAR images

It is very difficult to detect small targets when the scattering intensity of background clutter is as strong as the targets and the speckle noise is serious in synthetic aperture radar (SAR) images. Because the scattering of man-made objects lasts for a longer time than that of background clutter in azimuth matching scope, it is much easier for man-made objects to produce strong coherence than ground objects. As the essence of SAR imaging is coherent imaging, the contrast between targets and background clutter can be enhanced via coherent processing of SAR images. This paper proposes a novel method to reduce speckle noise for SAR images and to improve the detected ratio for SAR ship targets from the SAR imaging mechanism. This new method includes the coherence reduction speckle noise (CRSN) algorithm and the coherence constant false-alarm ratio (CCFAR) detection algorithm. Real SAR image data is used to test the presented algorithms and the experimental results verify that they are feasible and effective.     

Optimal estimation of interferometric phase for measuring surface deformation

In recent times, time-series interferometric synthetic aperture radar (InSAR) methods are developed to retrieve the deformation signal in non-urban areas from distributed scatterers (DS). Phase triangulation algorithm (PTA), an important step in these methods for filtering decorrelation noise from DS, aims at optimal estimation of the filtered wrapped interferometric phase values using InSAR data stack. The uniqueness of this research work lies in the incorporation of one such PTA only to provide an optimal set of wrapped interferometric phase values before phase unwrapping in the open source StaMPS processing environment. The proposed methodology, when adapted to measure surface deformation in Tehri reservoir rim region, Uttarakhand, India using Environmental Satellite (Envisat) C-band advanced synthetic aperture radar images, works efficiently and has enhanced the spatial coverage of measurement pixels compared to standalone PS-InSAR processing. It is also revealed from the one-dimension-line of sight velocity map that resulted velocity estimates are congruent with standalone PS-InSAR processing.     

基于统计与结构信息的SAR图像水上目标检测

设计了基于图像分析理论，根据SAR图像特点形成水上目标轮廓的检测算法。该算法的实现分为3步：(1)基于数理统计的目标检测方法，形成目标区域；(2)用加权统计滤波算子和去除孤立点算法消除噪声，规范需要检测的水上目标；(3)提取目标轮廓。系统在不同的SAR图像上，取得了良好的检测结果。     

相控阵PD雷达目标检测的实时空间滤波算法

针对弹载相控阵PD制导雷达的目标搜索与检测应用,建立了回波信号模型以及基于子阵的信号处理模型;提出了一种旁瓣杂波区位置估计以及在旁瓣杂波区检测目标的实时空间滤波新算法。该算法采用方位、俯仰方向上的分步降维处理,以一定的滤波性能损失换取运算开销的显著降低;通过理论分析比较了该算法与常规最优空间滤波算法的运算复杂度;通过计算机仿真实验比较了该算法与常规PD雷达的信号积累算法、相控阵PD雷达的最优空间滤波算法的杂波抑制性能。     

Texture Analysis through a Markovian Modelling and Fuzzy Classification: Application to Urban Area Extraction from Satellite Images

Herein we propose a complete procedure to analyze and classify the texture of an image. We apply this scheme to solve a specific image processing problem: urban areas detection in satellite images. First we propose to analyze the texture through the modelling of the luminance field with eight different chain-based models. We then derived a texture parameter from these models. The effect of the lattice anisotropy is corrected by a renormalization group technique coming from statistical physics. This parameter, which takes into account local conditional variances of the image, is compared to classical methods of texture analysis. Afterwards we develop a modified fuzzy Cmeans algorithm that includes an entropy term. The advantage of such an algorithm is that the number of classes does not need to be known a priori. Besides this algorithm provides us with further information, i.e. the probability that a given pixel belongs to a given cluster. Finally we introduce this information in a Markovian model of segmentation. Some results on SPOT5 simulated images, SPOT3 images and ERS1 radar images are presented. These images are provided by the French National Space Agency (CNES) and the European Space Agency (ESA).Grant from CNES     

River detection algorithm in SAR images based on edge extraction and ridge tracing techniques

This article presents a novel river detection algorithm in synthetic aperture radar (SAR) images. It is based on edge extraction in the wavelet domain followed by ridge tracing to merge the water region. The edge detection is approached by direct spatial correlation of wavelet transform data at several adjacent scales. For the ridge tracing algorithm, the concept used in fingerprint identification is introduced to complete riverbank linking and connecting based on a greyscale image. This improvement avoids the disadvantages of the widely used snake model in coastline connection. As indicated by the river detection results from the real SAR images, our river detection algorithm is efficient and robust in detecting the river in complicated suburb and nature water areas.     

基于视觉显著性的无人车图像检测及分割方法

障碍物检测与分割是地面无人车辆环境感知领域中一项重要的任务。针对传统障碍物检测与分割算法的计算量大、分割精度较差等问题,提出了一种基于显著性分析的障碍物检测、分割优化算法。首先,利用基于频率调谐的方法生成场景图像的显著图;然后,通过单目摄像机与激光雷达的联合标定将雷达反射点映射到显著图上;最后,结合单目摄像机和激光雷达两种传感器信息,通过改进的图像区域分割算法,实现障碍物的检测与分割。为了验证所提出算法有效性,采集多幅包含障碍物的典型越野场景图像,对该算法进行实验与仿真验证,结果证明了该算法的有效性。