Neural network directed Bayes decision rule for moving targetclassification

In this paper, a new neural network directed Bayes decision rule is developed for target classification exploiting the dynamic behavior of the target. The system consists of a feature extractor, a neural network directed conditional probability generator and a novel sequential Bayes classifier. The velocity and curvature sequences extracted from each track are used as the primary features. Similar to hidden Markov model scheme, several hidden states are used to train the neural network, the output of which is the conditional probability of occurring the hidden states given the observations. These conditional probabilities are then used as the inputs to the sequential Bayes classifier to make the classification. The classification results are updated recursively whenever a new scan of data is received. Simulation results on multiscan images containing heavy clutter are presented to demonstrate the effectiveness of the proposed methods     

利用神经网络的海杂波幅度分布参数估计方法

海杂波是制约对海雷达探测性能的主要因素之一,掌握其特性,具有十分重要的意义。经典海杂波统计模型在参数估计方法上以传统统计学理论为基础,在样本数较少的情况下,估计结果往往较差,导致建模准确度下降。此外,在复杂非均匀探测背景下,难以实现海杂波模型参数的准确实时估计。针对该问题,文章将深度神经网络模型引入海杂波参数估计领域,通过构建合理的模型,使其具备海杂波幅度分布模型的高精度参数估计能力。该方法采用直方图统计的方法进行数据预处理,合理划分输入数据标签的分组区间,构建数据集训练神经网络,并利用测试数据得到神经网络估计结果。仿真数据和X波段IPIX雷达实测数据验证结果表明,与传统数理统计估计方法相比,该算法明显提升了海杂波统计模型参数估计精度。     

基于OTHR与纯角度传感器群数据关联的模式辨识与定位精度提升

 天波超视距雷达(OTHR)目标跟踪面临着"三低"(低检测概率、低数据率和低测量精度)和"多径"(多条传播路径)的挑战,因此传播模式的准确辨识与目标定位精度提升是改善跟踪能力的关键。首先利用纯角度传感器群获得目标地理位置的初步估计,然后采用极大似然估计建立了OTHR的传播模式和杂波模式的辨识规则,进而利用最小方差估计准则实现OTHR和纯角度传感器群的量测融合。仿真结果表明,此算法的模式辨识正确率很高,能明显提升方位角的测量精度,但是不能明显提升径向距的精度。     

Neural network learning of low-probability events

In the problem of stationary target identification (STI) via millimeter wave (MMW) seeker radars in heavy clutter environments, it is often necessary to use nonparametric identification procedures, as detailed parametric models of clutter and target returns are generally unavailable. Neural networks provide an attractive approach to perform nonparametric identification. However, when identifying low-probability events, the computational overhead associated with training a neural network can become excessive. This is because low-probability events must be adequately represented in the training sample. We present a modified backpropagation training algorithm based on a likelihood ratio weighting function (LRWF) to train the neural network using a much smaller training set than that required using the standard backpropagation algorithm This algorithm is closely related to the importance sampling technique used in digital communication systems to obtain probability of error estimates by using a much smaller number of simulation runs than what is required with standard Monte Carlo simulation. The modified backpropagation technique results in a significant reduction in computational overhead in training the network, resulting from a substantial reduction in the size of the training set required to achieve a given level of performance. We demonstrate the performance of the algorithm on simulated data for the STI problem in MMW radar     

STAP for clutter suppression with sum and difference beams

A unique approach for airborne radar clutter rejection is developed and evaluated. This spatial and temporal adaptive approach employs the sum and difference beams of an antenna, which has significant practical advantages because it can be implemented with no/little change to the front-end electronics of airborne systems where sum and difference beams already exist for other reasons. The low sidelobe implementation of many sum and difference beam systems and the low gain of the difference beam in the direction of the target gives this approach the potential in many radars for a more predictable response pattern. The impact of these factors is shown in an airborne clutter rejection demonstration where the performance of this approach is compared with that of the factored approach (FA) using additional spatial channels and that of conventional pulse-Doppler (PD) processing. Reliable detection of an injected target is only achieved by this approach     

A localized adaptive MTD processor

The problem of achieving the optimum moving target indicator (MTI) detection performance in strong clutter of unknown spectrum when the set of data available to the estimation of clutter statistics is small due to a severely nonhomogeneous environment is studied. A new adaptive implementation, called the Doppler domain localized generalized likelihood ratio processor (DDL-GLR), is proposed, and its detection performance is studied in detail. It is shown that the DDL-GLR is a data-efficient implementation of the high-order optimum detector and has several advantages of practical importance over the adaptive processors     

Robust space-time adaptive processing for airborne radar in nonhomogeneous clutter environments

Space-time adaptive processing (STAP) holds tremendous potential for the new generation airborne surveillance radar, in which the phased array antennas and pulse Doppler processing mode are adopted. A new STAP approach using the multiple-beam and multiple Doppler channels is presented here for airborne phased array radar. The approach with space-time multiple-beam (STMB) architecture is robust to array errors and has very low system degrees of freedom (DOFs). Hence, it has low sample support requirement and it is very suitable for the practical planar phased array radar under nonhomogeneous clutter environments. Meanwhile, a new nonhomogeneous detector (NHD) based on the correlation dimension (CD) is also proposed here, which is used as an effective method to screen tracing data prior to detection processing. It can further improve the performance of the STAP approach in the severely nonhomogeneous clutter environments. Therefore, a scheme that incorporates the correlation dimension nonhomogeneity detector (CD-NHD) with the STMB is recommended, which we term CD-NHD-STMB. The experimental simulation results indicate that: 1) the STMB processor is robust to array element error and has high performance under nonhomogeneous clutter environments; 2) the CD-NHD is also effective on the nonhomogeneous clutter. As a result, the CD-NHD-STMB scheme is robust to array element error and nonhomogeneous clutter, and therefore available for airborne phased array radar applications.     

Multiple target detection using modified high order correlations

This work is concerned with the problem of multiple target track detection in heavy clutter. Using the “modified high order correlation” (HOC) process and a track scoring mechanism a new method is developed to perform data association and track identification in the presence of heavy clutter. Using this new scheme any number of very close, crossing or splitting target tracks can be resolved without increasing the computational complexity of the algorithm. The applicability of the method for continuous detection of target tracks that can originate and terminate at any scan is also demonstrated, In addition, the operating characteristics as a function of the clutter density are also provided. Simulation results on all the cases are presented     

Nonlinear clutter cancellation and detection using a memory-basedpredictor

In this paper, a nonlinear prediction (NLP) method is proposed as an alternative to the conventional linear prediction (LP) method for clutter cancellation. Because of the nonlinearity and non-Gaussianity of a clutter process, a nonlinear predictor is therefore needed to suppress clutter optimally. A memory-based predictor which uses a table look-up strategy to perform NLP is used in this work. The advantages of the memory-based approach are fast learning, algorithmic simplicity, robustness and suitability for parallel implementation. The memory-based predictor is then used as an adaptive detector for small surface target detection embedded in clutter. The effectiveness of the new method is demonstrated using real sea clutter data, and the results show improvement when compared with the conventional LP techniques     

Adaptive Optical Target Detection Using Correlated Images

A method for target detection that achieves clutter rejection by the use of multiple observations of the same target scene is developed. Multiple scene observations can be obtained by processing separate frequency bands of the same target scene or by recursively processing sequential observations in time. Optimal detection algorithms are developed, based on the assumption that the image intensity can be modeled as a variable mean spatial Gaussian process. Several fast detection algorithms are derived which make use of the fact that the covariance matrices of many optical and infrared (IR) images can be accurately approximated by diagonal matrices. These algorithms provide efficient solutions to the problem of processing multiple correlated scenes or multiple sequential imaging. Computer simulations based on actual optical and IR image data were used for checking the theoretical results. The new detection algorithms achieved performance improvement in detection signal-to-noise ratio of up to 10 dB over conventional target correlation methods.     

STOCHASTIC NEURAL NETWORK AND ITS APPLICATION TO MULTI－MANEUVERING TARGET TRACKING

ＳＴＯＣＨＡＳＴＩＣＮＥＵＲＡＬＮＥＴＷＯＲＫＡＮＤＩＴＳＡＰＰＬＩＣＡＴＩＯＮＴＯＭＵＬＴＩ－ＭＡＮＥＵＶＥＲＩＮＧＴＡＲＧＥＴＴＲＡＣＫＩＮＧＪｉｎｇＺｈｏｎｇｌｉａｎｇ；ＤａｉＧｕａｎｚｈｏｎｇ；ＴｏｎｇＭｉｎｇａｎ；ＺｈｏｕＨｏｎｇｒｅｎ（Ｄ...     

Adaptive imaging for forward-looking ground penetrating radar

Most of the current forward-looking ground-penetrating radar (FLGPR) systems use conventional delay-and-sum (DAS) based methods to form radar images for detection of the target (such as a landmine). However, DAS is a data-independent approach which is known to suffer from low resolution and poor interference and clutter rejection capability. We present a data-adaptive imaging approach for FLGPR image formation based on APES (amplitude and phase estimation) and rank-deficient RCB (robust Capon beamforming). Due to the data-adaptive nature of both APES and RCB, our approach has better resolution and much better interference and clutter rejection capability than the standard DAS-based imaging methods. The excellent performance of the proposed method is demonstrated using experimental data collected via two FLGPR systems recently developed by PSI (Planning Systems, Inc.) and SRI (Stanford Research Institute).     

Neural network-based fault diagnosis for spacecraft with single-gimbal control moment gyros

This paper proposes a neural network-based fault diagnosis scheme to address the problem of fault isolation and estimation for the Single-Gimbal Control Moment Gyroscopes(SGCMGs) of spacecraft in a periodic orbit. To this end, a disturbance observer based on neural network is developed for active anti-disturbance, so as to improve the accuracy of fault diagnosis.The periodic disturbance on orbit can be decoupled with fault by resorting to the fitting and memory ability of neural network. Subsequ...     

Analysis of CA-CFAR processors for linear-law detection

A method for evaluating the performance of cell-averaging constant false alarm rate (CA-CFAR) processors which use the amplitude of echo signals rather than their squared amplitude is presented. Results for the case of Rayleigh clutter/noise statistics are given. Detection probabilities are evaluated for the case of a Rayleigh fluctuating target embedded in Rayleigh clutter/noise for linear-law CA-CFAR processors. These results are observed to be practically identical to those of square-law CA-CFAR processors for which analytical expressions are readily available. These observations are verified using Monte Carlo simulations. The same conclusion is reached in the case of a nonfluctuating target embedded in Rayleigh clutter/noise for which only simulation results are presented     

两种自适应方向图峰值副瓣控制方法比较

自适应阵列（或称自适应波束形成）目前已广泛应用到雷达、声纳和通信领域中用来抑制各种干扰（有意的干扰，杂波干扰和多用户干扰等）。在雷达应用中，为了减轻脉冲欺骗式干扰或旁瓣目标并利用单脉冲雷达来准确测量目标波达方向．要求自适应方向图具有低副瓣和稳定的主瓣形状。在实际应用中，各种失配误差将降低自适应阵列的性能．这些误差包括由于目标的波达方向不精确引起的信号指向误差，由通道失配和位置扰动引起的阵列校准误差和由小样本教引起的协方差矩阵估计误差。在此情况下，自适应波束形成的性能大大下降（干扰抑制性能变差。主瓣失真和高的副瓣）。已提出了一种基于二次约束的集成峰值副瓣控制（integrated peak sidelobe control，简称IPSC）方法。该方法可以精确地控制峰值副瓣电平并产生具有稳定的主瓣形状的自适应方向图。研究IPSC中目标信号的影响和信号消除方案以进一步提高IPSC的性能。并将IPSC方法和最新提出的基于二阶锥规划（second-order cone programming，简称SOCP）的分布式峰值副瓣控制（distfibuted peak sidelobe control，简称为DPSC）新方法在性能上进行了比较。仿真结果表明。在干扰抑制性能和方向图控制质量方面IPSC比DPSC性能优越。此外IPSC比DPSC计算高效。     

基于Hilbert谱脊线粗糙度的微弱目标检测算法

为检测海杂波中的微弱目标,文中采用实测数据分析了海杂波的Hilbert谱脊线及其粗糙度,研究了目标对其Hilbert谱脊线及其粗糙度的影响。研究发现,目标的出现将导致海杂波Hilbert谱脊线起伏趋予平滑,Hilbert谱脊线粗糙度减小,在此基础上,文中提出了采用Hilbert谱脊线粗糙度检测微弱目标的方法。仿真结果表...     

Sum-difference Reduced-dimensional Processing in SAR Image Domain and Statistical Analysis for Ground Moving Target Indication

In this article, a new reduced-dimensional adaptive processing algorithm based on joint pixels sum-difference data for clutter rejection is proposed. The sum-difference data are obtained by orthogonal projection of the joint pixels data of different synthetic aperture radar (SAR) images generated by a multi-satellite radar system. In the sense of statistical expectation, the sum-differ- ence data contain the common and different information of the SAR images. Therefore, the objective of clutter cancellation can be achieved by adaptive processing. Moreover, based on the residual image after clutter rejection, statistical analysis of constant false-alarm rate (CFAR) detection of moving targets is also presented. Simulation results demonstrate the effectiveness and robustness of the proposed algorithm even with heterogeneous clutter and image co-registration error.     

Track-While-Scan Algorithm in a Clutter Environment

A track-while scan (TWS) algorithm is developed for targets in a clutter environment. The problem has been studied using only the position measurements [1, 5-8], but the simulation results have not been satisfactory. Modern processing techniques (FFT processor) ) in air traffic control and surveillance radar receivers provide both position and radial velocity. The radial velocity measurement may be conveniently used in the target-track correlation process, which will reduce the association ambiguity in the clutter environment. t. In the clear environment the algorithm using the position and radial velocity measurements has been treated in [3, 4]. A TWS algorithm, using both position and radial velocity measurements for targets in a clutter environment, is presented here. The algorithm obtained is nonlinear and adaptive. In order to evaluate the improvement due to radial velocity measurement a simulation has been performed on a digital computer. The algorithm was run with and without radial velocity measurements to compare its performances. An improvement was noted especially when the target path included an accelerated portion.     

基于相位相关的部分可辨编队精细起始算法

针对部分可辨条件下编队目标的精细起始难题,提出了一种基于相位相关的部分可辨编队精细起始算法。首先,采用基于坐标映射距离差分的快速群分割与基于编队中心点的预互联对雷达量测进行预处理;然后,利用图像匹配中相位相关特性,将相邻时刻编队结构进行补偿对准,解决了低目标发现概率情况下的编队结构对准问题;最后,采用增加虚拟量测并后验判决的方式,结合最近邻法做编队航迹精细互联,在填补航迹缺失、增加正确航迹的同时抑制虚假航迹的产生。经仿真验证,与修正的逻辑法、基于相对位置矢量的灰色编队精细起始算法相比,本文所提算法在提高航迹正确起始率、抑制虚假航迹方面性能优势显著,且对环境杂波与雷达精度具有较好的鲁棒性,对目标发现概率具有较好的适应性。     

基于神经网络预测模型的歼击机结构故障检测方法

提出了一种基于预测神经网络的歼击机结构故障检测新方法 ,与传统的基于模型的非线性系统的故障检测方法相比 ,神经网络方法有着非线性逼近能力强和故障检测实时性好等优点。给出了基于预测神经网络的故障检测方案 ,以及多步直接预测算法和阈值选取原则 ,最后以某型歼击机为例进行了仿真验证 ,仿真结果表明本方法能有效地检测出歼击机的各种结构故障。