基于云模型和改进D-S证据理论的目标识别决策方法

在目标识别决策系统中,多探测器多源信息融合的模糊性和不确定性以及各探测周期所得信息的冲突互斥会造成目标识别决策不精准。为解决这一问题,提出基于云模型和改进D-S （Dempster-Shafer）证据理论的目标识别决策方法。首先,将目标识别准确性这一语言评价值划分为不同评价区间等级,以不同评价等级标准云为参照将各探测器各探测周期所得信息转化为云决策矩阵,得出各周期各等级隶属度,进而构建出基本概率分配函数（mass函数）;其次,基于证据理论引入冲突度、差异度、离散度3类衡量冲突大小的参数,定义了一种新的证据冲突参数,同时改进证据冲突融合算法,对各探测器各周期证据体进行修正并融合;再次,结合各探测器权重加权得出各目标综合识别决策的mass函数对目标进行决策;最后,结合算例,验证该方法的适用性,并与其他方法相对比验证了本文方法的优越性。     

无人机载多传感器图像融合评述

为了能为作战指挥系统提供清晰的局部战场信息,提高对局部战场低可观测目标的检测概率、定位精度及识别概率,迫切需要对无人机载SAR、可见光传感器、红外探测器等图像信息及其他非图像信息融合处理。提出了无人机载多传感器图像融合技术需要研究的内容,如: 图像融合新方法研究;无人机载SAR图像的非平稳性处理;基于图像融合目标检测和处理技术; 无人机载图像和非图像信息的融合问题;无人机载多传感器图像融合的实现及评估;多无人机载合成孔径雷达的协同成像;用图像融合的方法实现对运动目标检测等。分析了所提出研究内容的可行性,剖析了其中的关键技术,拟定了可能的技术路线。     

基于PTE的多雷达航迹融合算法

针对杂波背景下的多雷达航迹融合时局部估计误差互协方差矩阵未知的问题，提出基于目标存在概率（PTE）的航迹融合算法，提升了正确航迹率和跟踪精度。首先，通过综合概率数据关联得到单接收站的目标航迹估计集合和对应的目标存在概率。然后，在局部估计误差互协方差矩阵未知的条件下，基于PTE信息提出不带记忆的综合广义凸组合航迹融合算法。进而将前一帧的融合状态进行反馈，提出带记忆的综合广义凸组合航迹融合算法。仿真验证了所提算法的有效性。     

Application of Road Information in Ground Moving Target Tracking

A new algorithm is developed to achieve accurate state estimation in ground moving target tracking by means of using road information. It is an adaptive variable structure interacting multiple model estimator with dynamic models modification （DMM VS-IMM for short）. Firstly, road information is employed to modify the target dynamic models used by filter, including modification of state transition matrix and process noise. Secondly, road information is applied to update the model set of a VS-IMM estimator. Predicted state estimation and road information are used to locate the target in the road network on which the model set is updated and finally IMM filtering is implemented. As compared with traditional methods, the accuracy of state estimation is improved for target moving not only on a single road, but also through an intersection. Monte Carlo simulation demonstrates the efficiency and robustness of the proposed algorithm with moderate computational loads.     

Detection and range/Doppler estimation for colocated sensors

The problem of multisensor detection and high resolution signal state estimation using joint maximum a posteriori detection and high order nonlinear filtering techniques is addressed. The model-based fusion approach offers the potential for increased target resolution in range/Doppler/azimuth space. The approach employs joint detection/estimation filters (JDEF) for target detection and localization. The JDEF approach segments the aggregate nonlinear model over the entire target resolution space into a number of localized nonlinear models by partitioning the resolution space into a number of resolution subcells. This partitioning leads to extremely accurate state estimation. The proposed JDEF approach has a built-in capability for automatic data alignment from multiple sensors, and can be used for centralized, decentralized, and distributed data fusion.     

An online ensemble semi-supervised classification framework for air combat target maneuver recognition

Online target maneuver recognition is an important prerequisite for air combat situation recognition and maneuver decision-making. Conventional target maneuver recognition methods adopt mainly supervised learning methods and assume that many sample labels are available. However, in real-world applications, manual sample labeling is often time-consuming and laborious. In addition, airborne sensors collecting target maneuver trajectory information in data streams often cannot process information in real time. To solve these problems, in this paper, an air combat target maneuver recognition model based on an online ensemble semi-supervised classification framework based on online learning, ensemble learning, semi-supervised learning, and Tri-training algorithm, abbreviated as Online Ensemble Semi-supervised Classification Framework (OESCF), is proposed. The framework is divided into four parts: basic classifier offline training stage, online recognition model initialization stage, target maneuver online recognition stage, and online model update stage. Firstly, based on the improved Tri-training algorithm and the fusion decision filtering strategy combined with disagreement, basic classifiers are trained offline by making full use of labeled and unlabeled sample data. Secondly, the dynamic density clustering algorithm of the target maneuver is performed, statistical information of each cluster is calculated, and a set of micro-clusters is obtained to initialize the online recognition model. Thirdly, the ensemble K-Nearest Neighbor (KNN)-based learning method is used to recognize the incoming target maneuver trajectory instances. Finally, to further improve the accuracy and adaptability of the model under the condition of high dynamic air combat, the parameters of the model are updated online using error-driven representation learning, exponential decay function and basic classifier obtained in the offline training stage. The experimental results on several University of California Irvine (UCI) datasets and real air combat target maneuver trajectory data validate the effectiveness of the proposed method in comparison with other semi-supervised models and supervised models, and the results show that the proposed model achieves higher classification accuracy.     

Detection and diagnosis of sensor and actuator failures using IMMestimator

An approach to detection and diagnosis of multiple failures in a dynamic system is proposed. It is based on the interacting multiple-model (IMM) estimation algorithm, which is one of the most cost-effective adaptive estimation techniques for systems involving structural as well as parametric changes. The proposed approach provides an integrated framework for fault detection, diagnosis, and state estimation. It is able to detect and isolate multiple faults substantially more quickly and more reliably than many existing approaches. Its superiority is illustrated in two aircraft examples for single and double faults of both sensors and actuators, in the forms of “total”, “partial”, and simultaneous failures. Both deterministic and random fault scenarios are designed and used for testing and comparing the performance fairly. Some new performance indices are presented. The robustness of the proposed approach to the design of model transition probabilities, fault modeling errors, and the uncertainties of noise statistics are also evaluated     

基于红外视觉/激光雷达融合的目标识别与定位方法

近年来,基于可见光图像的目标识别在无人车感知领域得到了广泛应用.然而,可见光图像目标识别无法应用于弱光和黑暗环境.针对于此,提出了一种基于红外视觉/激光雷达融合的目标识别与定位算法.首先,通过基于颜色迁移的数据增强训练方法,提高了红外目标识别算法的泛化性能.继而,提出了一种基于激光雷达修正的单目深度估计方法,通过视觉图像与激光雷达点云的数据融合,实现了基于稠密深度图对目标位置的估计,提高了对小目标的定位能力.试验结果表明,与传统Yolov3目标识别算法相比,该算法平均识别准确率可提升5.8％;此外,相对定位算法将包含小目标在内的物体相对定位精度提高了13.4％.     

Track-to-track fusion with dissimilar sensors

An analysis is described of a kinematic state vector fusion algorithm when tracks are obtained from dissimilar sensors. For the sake of simplicity, it is assumed that two dissimilar sensors are equipped with nonidentical two-dimensional optimal linear Kalman filters. It is shown that the performance of such a track-to-track fusion algorithm can be improved if the cross-correlation matrix between candidate tracks is positive. This cross-correlation is introduced by noise associated with target maneuver that is common to the tracking filters in both sensors and is often neglected. An expression for the steady state cross-correlation matrix in closed form is derived and conditions for positivity of the cross-correlation matrix are obtained. The effect of positivity on performance of kinematic track-to-track fusion is also discussed     

Cardinality compensation method based on information-weighted consensus filter using data clustering for multi-target tracking

In this paper, a cardinality compensation method based on Information-weighted Consensus Filter(ICF) using data clustering is proposed in order to accurately estimate the cardinality of the Cardinalized Probability Hypothesis Density(CPHD) filter. Although the joint propagation of the intensity and the cardinality distribution in the CPHD filter process allows for more reliable estimation of the cardinality(target number) than the PHD filter, tracking loss may occur when noise and clutter are high in the measurements in a practical situation. For that reason, the cardinality compensation process is included in the CPHD filter, which is based on information fusion step using estimated cardinality obtained from the CPHD filter and measured cardinality obtained through data clustering. Here, the ICF is used for information fusion. To verify the performance of the proposed method, simulations were carried out and it was confirmed that the tracking performance of the multi-target was improved because the cardinality was estimated more accurately as compared to the existing techniques.     

Trajectory Estimation with Multi-range-rate System Based on Sparse Representation and Spline Model Optimization

The classic state methods for trajectory estimation in boost phase with multi-range-rate system include method of point-by-point manner and that of spline-model-based manner. Both are deficient in terms of model-approximation accuracy and systematic error determination thus resulting in the estimation errors well beyond the requirements, especially, concerning the maneuvering trajectory. This article proposes a new high-precision estimation approach based on the residual error analysis. The residual error comprises three components, i. e. systematic error, model truncation error and random error. The approach realizes self-adaptive estimation of systematic errors in measurements following the theory of sparse representation of signals to minimize the low-frequency components of residual errors. By taking median- and high-frequency components as indexes, the spline model-approximation is improved by optimizing node sequence of the spline function and the weight selection for data fusion through iteration. Simulation has validated the performances of the proposed method.     

Cubature Kalman filter with closed-loop covariance feedback control for integrated INS/GNSS navigation

Cubature Kalman Filter (CKF) offers a promising solution to handle the data fusion of integrated nonlinear INS/GNSS (Inertial Navigation System/Global Navigation Satellite System) navigation. However, its accuracy is degraded by inaccurate kinematic noise statistics which originate from disturbances of system dynamics. This paper develops a method of closed-loop feedback covariance control to address the above problem of CKF. In this method, the posterior state and its covariance are fed back to the filtering process to constitute a closed-loop structure for CKF covariance propagation. Subsequently, based on the maximum likelihood principle, a control scheme of the prior state covariance is established by using the feedback state and covariance within an estimation window and further adopting a proportional coefficient to amplify the feedback terms in recent time steps for the full use of new information to reflect actual system characteristics. Since it does not directly use kinematic noise covariance, the proposed method can effectively avoid the adverse impact of inaccurate kinematic noise statistics on filtering solutions. Further, it can also guarantee the prior state covariance to be positive semi-definite without involving extra measures. The efficacy of the proposed method is validated by simulations and experiments for integrated INS/GNSS navigation.     

Estimation of Aircraft Target Motion Using Orientation Measurements

A new approach to estimating motion of a highly maneuverable aircraft target in an air-to-air tracking scenario is presented. An interactive filter system is developed that provides an improved estimate of target motion states by conditioning kinematic filter estimates on target aspect angle data. Pattern recognition techniques used with an electrooptical tracker are presumed to provide this target aspect information. A target orientation filter processes the aspect angle measurements by statistically weighting measured aspect angles with the current best estimate of target kinematics. The aerodynamic lift equation is used to relate approximate angle of attack to target velocity and acceleration. A novel statistical model for aircraft target normal acceleration is also developed to represent better the unknown target accelerations. Simulation results of realistic three-dimensional scenarios are presented to evaluate the performance of the interactive filter system.     

A multi-rate sensor fusion approach using information filters for estimating aero-engine performance degradation

Gas-path performance estimation plays an important role in aero-engine health management, and Kalman Filter(KF) is a well-known technique to estimate performance degradation. In previous studies, it is assumed that different kinds of sensors are with the same sampling rate, and they are used for state estimation by the KF simultaneously. However, it is hard to achieve state estimation using various kinds of sensor measurements at the same sampling rate due to a complex network and physical characteristic differences between sensors, especially in an advanced multisensor architecture. For this purpose, a multi-rate sensor fusion using the information filtering approach is proposed based on the square-root cubature rule, which is called Multi-rate Squareroot Cubature Information Filter(MSCIF) to track engine performance degradation. Soft measurement synchronization of the MSCIF is designed to provide a sensor fusion condition for multiple sampling rates of measurement, and a fault sensor is isolated by maximum likelihood validation before state estimation. The contribution of this paper is to supply a novel multi-rate informationfilter approach for sensor fault tolerant health estimation of an aero-engine in a multi-sensor system. Tests are conducted for aero-engine performance degradation estimation with multiple sampling rates of sensor measurement on both digital simulation and semi-physical experiment.Experimental results illustrate the superiority of the proposed algorithm in terms of degradation estimation accuracy and robustness to sensor failure in a multi-sensor system.     

Performance evaluation of track fusion with information matrixfilter

In a multisensor environment, each sensor detects multiple targets and creates corresponding tracks. Fusion of tracks from these, possibly dissimilar, sensors yields more accurate kinematic and attribute information regarding the target. Two methodologies have been employed for such purpose, which are: measurement fusion and state vector fusion. It is well known that the measurement fusion approach is optimal but computationally inefficient and the state vector fusion algorithms are more efficient but suboptimal, in general. This is so because the state vector estimates to be fused obtained from two sensors, are not conditionally independent in general due to the common process noise from the target being tracked. It is to be noted that there are three approaches to state vector fusion, which are: weighted covariance, information matrix, and pseudomeasurement. This research is restricted solely to performance evaluation of the information matrix form of state vector fusion. Closed-form analytical solution of steady state fused covariance has been derived as a measure of performance using this approach. Note that the results are derived under the assumptions that the two sensors are synchronized and no misassociation or merged measurement is considered in the study. Results are compared with those using Monte Carlo simulation, which was used in the past to predict fusion system performance by various authors. These results provide additional insight into the mechanism of track fusion and greatly simplify evaluation of fusion performance. In addition, availability of such a solution facilitates the trade-off studies for designing fusion systems under various operating conditions     

基于多维特征的战场实体目标分群方法

目标分群问题也称为群形成过程，是态势估计中的一个重点和难点问题，属于信息融合中的高层融合范畴。现有的目标分群方法大多是将空间位置相近的目标聚为一类，极少有分群方法考虑到进行战场态势分析所需的位置、速度、航向、属性和类型等多维特征。为此，首先根据海战场态势分析需求，基于目标的特征属性定义了多维度欧式距离；然后综合利用分类与密度聚类两种分析方法，提出了一种战场实体目标分群方法,以综合实现战场实体目标的实时分群处理；最后，将该算法应用于一个军用场景的数据集上进行仿真实验。仿真结果表明了该方法在海战场环境中实现目标分群处理的可行性和有效性。     

Optimal and adaptive reduced-rank STAP

This paper is concerned with issues and techniques associated with the development of both optimal and adaptive (data dependent) reduced-rank signal processing architectures. Adaptive algorithms for 1D beamforming, 2D space-time adaptive processing (STAP), and 3D STAP for joint hot and cold clutter mitigation are surveyed. The following concepts are then introduced for the first time (other than workshop and conference records) and evaluated in a signal-dependent versus signal independent context: (1) the adaptive processing “region-of-convergence” as a function of sample support and rank, (2) a new variant of the cross-spectral metric (CSM) that retains dominant mode estimation in the direct-form processor (DFP) structure, and (3) the robustness of the proposed methods to the subspace “leakage” problem arising in many real-world applications. A comprehensive performance comparison is conducted both analytically and via Monte Carlo simulation which clearly demonstrates the superior theoretical compression performance of signal-dependent rank-reduction, its broader region-of-convergence, and its inherent robustness to subspace leakage     

Low observable target motion analysis using amplitude information

In conventional passive and active sonar system, target amplitude information (AI) at the output of the signal processor is used only to declare detections and provide measurements. We show that the AI can be used in passive sonar system, with or without frequency measurements, in the estimation process itself to enhance the performance in the presence of clutter where the target-originated measurements cannot be identified with certainty, i.e., for “low observable” or “dim” (low signal-to-noise ratio (SNR)) targets. A probabilistic data association (PDA) based maximum likelihood (ML) estimator for target motion analysis (TMA) that uses amplitude information is derived. A track formation algorithm and the Cramer-Rao lower bound (CRLB) in the presence of false measurements, which is met by the estimator even under low SNR conditions, are also given. The CRLB is met by the proposed estimator even at 6 dB in a cell (which corresponds to 0 dB for 1 Hz bandwidth in the case of a 0.25 Hz frequency cell) whereas the estimator without AI works only down to 9 dB. Results demonstrate improved accuracy and superior global convergence when compared with the estimator without AI. The same methodology can be used for bistatic radar     

多传感器融合状态估计方法综述

随着传感器网络技术的发展，多传感器融合状态估计凭借其鲁棒性、灵活性、可扩展性以及便于故障检测等优点，长期受到国内外学者的广泛关注，并取得了大量研究成果。数据融合的方法为融合状态估计奠定了理论基础，也是早期研究的主要方向，从20世纪70年代到20世纪末，相继发展出了集中式和分散式滤波架构及相应算法。无线通信技术的成熟以及一致性算法的出现使得分布式状态估计的研究进入了快车道，自2005年以来，大量基于一致性的分布式滤波算法被提出，其中不乏实用的经典方法和优秀的开创性方法。旨在梳理多传感器融合状态估计的发展，探究从数据融合到分布式滤波的内在联系，并对一些经典方法进行了总结。     

Nonparametric methods for clutter removal

Methods of clutter rejection are discussed which furnish an inherent counterpart of target tracking and detection algorithms. We describe how nonparametric curve estimation methods reduce the original sensor data to a “signal-plus-noise” model which is well suited for various hypotheses testing and dynamical filtering algorithms. We also verify a “white noise” assumption for the model of residuals