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.     

Radiometric calibration stability assessment for the RISAT-1 SAR sensor using a deployed point target array at the Desalpar site,Rann of Kutch,India

Synthetic aperture radar (SAR) data used for quantitative temporal and/or spatial analysis requires calibration to ensure that observed pixel values of amplitude and phase can be related to the geophysical parameters of interest. The process of radiometric calibration of SAR images involves comparison of the backscattered radar reflectivity signal from a ground resolution element containing a calibration target of known signal response, such as a corner reflector. In this study, absolute radiometric calibration of RISAT-1 intensity data of fine resolution stripmap-1 (FRS-1) and medium resolution ScanSAR (MRS) mode was carried out by utilizing array of standard point targets of various types (triangular trihedral, square trihedral, and dihedral) with known radar cross-section deployed prior to satellite overpass with precise azimuth and elevation angles in Desalpar, Rann of Kutch in western India. The derived calibration constants using the integral method were then compared with the values provided in the header file. Deviations in the results are reported in this article. The results obtained show that the difference between the estimated average calibration constants for FRS-1 and MRS mode data with the provided value was found to be within the absolute radiometric accuracy specification of Radar Imaging SATellite (RISAT-1). Near-range to far-range difference of 0.1–0.2 dB for HH (Horizontal transmit, Horizontal receive) polarization and 0.1–0.3 dB for HV (Horizontal transmit, Vertical receive) polarization was estimated for the same scene using distributed target analysis indicating the stability of calibration for the same scene. This study also concluded that Desalpar site in Rann of Kutch has the potential of being an operational SAR calibration site.     

Calibration and modelling of MAESTRO 1 polarimetric SAR data of a forest area in Les Landes,France

Abstract. The results of an analysis of polarimetric P, Land C-band SAR data from the JPL AIRSAR of a forest area of maritime pine in Les Landes, southwest France, are described and discussed. The data were acquired in connection with the MAESTRO I Campaign organized by ESA and JRC/lspra. Cross-talk and channel imbalance distortions are removed in a calibration process using the SAR data itself and trihedral corner reflectors positioned at the scene. Two calibration methods have been implemented and compared: the iterative Klein algorithm and the non-iterative Quegan algorithm. Quegan's method shows the largest reduction of the cross-talk, and the most stable and easily interpreted results. Also, absolute calibration using the integral method has been performed. The results presented show that P band (and to some extent L band) is very sensitive to trunk biomass using single-polarization radar data, at least at the incidence angles in the range from 38° to 52°, whereas C band is less sensitive. Also, the cylinder model by Durden et al. of the baekseattering from a forest has been implemented and the results show good agreement with the SAR data. The dominant scattering mechanisms have been determined using the model at P and L bands.     

Whitt点目标极化定标算法的实验研究

将Whitt等人提出的通用的点目标极化定标算法应用到SIR-C系统获取的L波段多极化数据中,进行定标实验。利用所获取的SIR-C合成孔径雷达图像中存在的点目标,将它们经过SIR-C定标组定标的极化数据作为理论值看待,运用Whitt算法来定标整幅没有定标的图像。最后将实验获取的结果与SIR-C定标组定标结果互相比较,可以看出这个算法具有良好的性能。     

Polarimetric SAR statistical analysis using alpha-stable distribution and its application in optimal despeckling

In this article, the statistical model of the polarimetric synthetic aperture radar (SAR) single-look complex image is analysed using alpha-stable distribution. It is better to use alpha-stable distribution than Gaussian distribution to represent the statistical characteristics of the polarimetric SAR image. A polarimetric SAR covariance matrix estimation method based on fractional lower-order statistics (FLOS) is proposed. Based on this model, an adaptive polarimetric SAR optimal despeckling method based on FLOS is developed. This algorithm adaptively estimates the characteristic exponents of each channel and uses these estimated alphas to calculate the parameters for the optimal despeckling adaptively. The experiments using polarimetric SAR data demonstrate that the proposed method not only reduces the blurs that occur in the area of impulsive reflectors in the result of the original optimal despeckling method, but also maintains the speckle reduction ability (equivalent number of looks).     

Improving SAR data processing with polarimetric reference functions in the range Doppler algorithm

Synthetic aperture radar (SAR) is a form of radar that can be used to create images of objects and landscapes. The main important application of the polarimetric SAR can be found in surface and target decomposition process of its image processing. In this article, we propose a method of polarimetric SAR data processing using two new polarimetric reference functions of canonical targets with the intention to apply in coherent decompositions. Our experiment uses polarimetric backscatter characteristics of the dihedral and trihedral reflectors as the targets under a ground-based SAR geometry to create the polarimetric reference functions for azimuth compression in the SAR data processing. We process the data using Pauli decomposition to investigate the effect of our functions on the RGB (red, green, and blue) properties of the processed images. The results show that Pauli decomposition using our functions produces images with different distribution and intensity of RGB colours in the image pixels with some signs of improvement over the traditional range Doppler algorithm. This demonstrates that our polarimetric reference function can be used in the decomposition steps of the traditional SAR data processing and can potentially be used to reveal some useful quantitative physical information of target points of interest and improve image and surface classification.     

Improved airborne PolSAR calibration algorithm based on time-variant attitude compensation

The polarimetric synthetic aperture radar (PolSAR) usually has to be calibrated before practical application, so as to compensate for polarimetric distortion. The varying platform attitude is one of the factors causing distortion but has rarely been considered in existing polarimetric calibration algorithms. With the resolution of PolSAR systems improving and the synthetic aperture time prolonging, this factor cannot simply be ignored. The varying attitude will distort the polarimetric information by rotating the polarimetric orientation angle, and such distortion changes with azimuth time. In this article, we modified the conventional polarimetric system model to take account of the time-variant impact of the unstable platform attitude. A calibration algorithm is proposed to compensate the time-variant attitude impact on the raw return data. The proposed calibration algorithm is tested on the data collected by Institute of Electronics, Chinese Academy of Sciences P-band PolSAR system. Results show that it can achieve better performance by reducing crosstalk error than two conventional methods.     

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.     

基于快速检测和AdaBoost的车辆检测

为给激光雷达三维点云目标检测提供一种更智能、更稳健的信息处理算法,提出一种基于激光雷达获取的点云数据的车辆目标检测算法。采用局部高程对地面进行拟合,对目标场景进行预分类;根据目标的几何尺寸建立ROI(感兴趣区域),对该区域内的点云数据进行聚类分析,大致检测出目标物体。由于现实场景中往往存在与目标高程相近的物体,采用基于Harr-like特征的AdaBoost分类器对ROI进行复核,划定检测目标。实验结果表明,在目标遮挡率为50%的情况下,算法的检测准确率也能将近90%。     

极化MIMO雷达隐身目标检测性能研究*

多输入多输出(MIMO)雷达使用了远距分布的阵元,它利用了信号的空间分集增益来获取更多的目标信息。极化是另一种可以提高雷达系统性能的分集方式。当应对隐身目标时,传统的极化雷达在某些观测角度会遭受到较大的目标雷达截面积(RCS)衰减,而无法获得较好的检测性能。而在一个雷达系统中同时利用这两种分集增益,可以得到一种比传统极化雷达更具优势的新雷达检测系统——极化统计MIMO雷达,它可以更好地应对隐身目标检测。给出了相应的模型,并推导出了该雷达系统的检测性能解析式。将其与传统相控阵及非极化统计MIMO雷达比较,可以看到极化统计MIMO雷达的检测性能更佳。联系到隐身目标的特性,极化MIMO雷达的检测器特性应对它时具有显著优势。最后,以上方法通过仿真得到了验证。     

基于实时地形校正的InSAR图像匹配算法

针对侧视雷达/可见光图像匹配制导系统中由于雷达图像地形畸变引起的误匹配问题,提出了一种基于干涉合成孔径雷达（InSAR）的实时地形校正图像匹配算法。该算法以侧视雷达成像几何构象为基础,利用InSAR获取的实时地形数据对获取的SAR景象数据进行实时几何校正,生成无畸变的SAR景象数据,然后利用校正后的SAR景象数据与提前安装的可见光基准数据进行基于去均值归一化互相关模板的图像匹配。实验结果表明,通过实时地形校正,该景象匹配算法在复杂地形区域的匹配概率和匹配精度都大大优于传统SAR景象匹配算法,有效地提高了SAR图像匹配制导技术的适用性。     

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。     

简述极化SAR定标处理技术研究进展

极化定标是极化SAR数据用于图像解译和定量参数反演的关键步骤。综述了国内外极化SAR定标技术及应用研究的主要成果,着重介绍极化SAR定标技术发展以来取得的多种关键算法进展,系统梳理包括点目标定标算法、分布目标定标算法、法拉第旋转校正算法等技术原理介绍、参数定义估计及技术脉略发展分析,并讨论各技术方法在机载及星载SAR系统定标领域取得的应用发展现状,同时逐步分解该技术领域目前面临的技术难点及算法发展。最后探讨分析极化SAR定标技术发展中的未来需求难点和继续需要解决的问题,为研究人员进一步推动极化SAR定标技术发展提供参考。     

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.     

PolSAR image compression based on online sparse K-SVD dictionary learning

we present a novel polarimetric synthetic aperture radar (PolSAR) image compression scheme. PolSAR data contains lots of similar redundancies in single-channel and massively correlation between polarimetric channels. So these features make it difficult to represent PolSAR data efficiently. In this paper, discrete cosine transform (DCT) is adopted to remove redundancies between polarimetric channels, simple but quite efficient in improving compressibility. Sparse K-singular value decomposition (K-SVD) dictionary learning algorithm is utilized to remove redundancies within each channel image. Double sparsity scheme will be able to achieve fast convergence and low representation error by using a small number of sparsity dictionary elements, which is beneficial for the task of PolSAR image compression. Experimental results demonstrate that both numerical evaluation indicators and visual effect of reconstructed images outperform other methods, such as SPIHT, JPEG2000, and offline method.     

基于Krogager分解和SVM的极化SAR图像分类

目标分解包括基于Sinclair矩阵的相干目标分解和基于Mueller矩阵的部分相干目标分解,Krogager分解即属于相干目标分解,它可以将任一对称Sinclair矩阵分解为球散射体、二面角散射体和螺旋体3个分量,这是极化合成孔径雷达(Synthetic Aperture Radar,SAR)图像特征提取的有效途径。把3个分量的分解系数作为极化散射特征,由其组成样本向量,运用基于统计学习理论的支持向量机(Support Vector Machines,SVM)设计多类分类器,提出了一种极化SAR图像分类算法,并对实测极化SAR数据进行分类实验。结果表明,将Krogager分解和SVM分类器结合起来,对极化SAR图像进行分类是可行和有效的,并且选择不同的参数得到的分类结果差别很大,验证了参数选择在SVM分类器中的重要作用。     

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.     

正交极化二元阵雷达的空域极化特性及散射矩阵测量方法

极化测量技术是现代雷达领域的重要发展趋势之一,对目标极化特性的测量是实现极化雷达的关键技术,但在工程实现上存在很大的技术挑战.针对这种情况,提出了一种新体制目标特性测量雷达的理论模型,即正交极化二元阵.初步证明了该式天线具有明显的极化空变特性,进而设计了一种新的极化测量处理算法,仅需一个接收处理通道即可在天线波束扫掠目标时,实现目标极化散射矩阵的测量.通过紧凑场微波暗室对自行搭建的正交极化二元阵进行了全极化宽带动态测量实验,利用实测数据处理验证了上述研究的正确性.研究结果对于挖掘现有雷达装备的极化测量潜力,提升其信息获取与处理能力,具有一定的启发意义.     

Multi-channel SAR imaging based on distributed compressive sensing

The rapid development of compressive sensing(CS)shows that it is possible to recover a sparse signal from very limited measurements.Synthetic aperture radar(SAR)imaging based on CS can reconstruct the target scene with a reduced number of collected samples by solving an optimization problem.For multi-channel SAR imaging based on CS,each channel requires sufficient samples for separate imaging and the total number of samples could still be large.We propose an imaging algorithm based on distributed compressive sensing(DCS)that reconstructs scenes jointly under multiple channels.Multi-channel SAR imaging based on DCS not only exploits the sparsity of the target scene,but also exploits the correlation among channels.It requires significantly fewer samples than multi-channel SAR imaging based on CS.If multiple channels offer different sampling rates,DCS joint processing can reconstruct target scenes with a much more flexible allocation of the number of measurements offered by each channel than that used in separate CS processing.