Landmine geo-location using dynamic modeling and target tracking

Geo-location is essential for landmine search using vehicular-mounted sensors. The vehicle and targets were combined into an incorporated model versus a separated model. Colored noise modeling is required for the separated model since the vehicle estimate errors are colored. An inventory is introduced for maintaining information on detected mines. Results from simulations using actual data indicate precision of 0.25 m indicating promise for the method.     

Joint TNT and RDX detection via quadrupole resonance

Quadrupole resonance (QR) technology has been receiving increasing attention for explosive detection in applications including landmine detection. It can be used as a confirming sensor for buried plastic landmine detection by detecting the explosives within the mine. Since a single mine can contain more than one type of explosives (e.g., trinitrotoluene (TNT) and (RDX) compound), a detector designed to detect only one type of explosive may not provide the best detection. We focus herein on the joint detection of TNT and RDX explosives for the landmine detection via the QR sensor. To mitigate the RF interferences (RFIs) associated with the QR measurements, we apply a doubly constrained robust Capon beamformer (DCRCB) to perform the spatial beamforming by exploiting the spatial correlation of the RFIs. Based on the output of the spatial DCRCB, we devise a generalized likelihood ratio test (GLRT) for the joint TNT/RDX detection, which is referred to as the DCRCB-GLRT detector. We show that our detector has the constant false alarm rate (CFAR) property and that the detection variable obeys a x² -mixture distribution in the mine-free scenario. The effectiveness of the proposed DCRCB-GLRT detector is demonstrated with the experimental data collected by Quantum Magnetics, Inc.     

A Boolean algebra approach to multiple sensor voting fusion

A technique for integrating multiple-sensor data using a voting fusion process that combines the individual sensor outputs is described. An important attribute of the method is the automatic confirmation of the target by the fusion processor without the need to explicitly determine which sensors and what level of sensor participation are involved. A three-sensor system, with multiple confidence levels in each sensor, is discussed to illustrate the approach. Boolean algebra is used to derive closed-form expressions for the multiple sensor-system detection probability and false-alarm probability. Procedures for relating confidence levels to detection and false alarm probabilities are described through an example. The hardware implementation for the sensor system fusion algorithm is discussed     

Performance of an adaptive feature-based processor for a wideband ground penetrating radar system

A two-stage algorithm for landmine detection with a ground penetrating radar (GPR) system is described. First, 3-D data sets are processed using a computationally inexpensive pre-screening algorithm which flags potential locations of interest. These flagged locations are then passed to a feature-based processor which further discriminates target-like anomalies from naturally occurring clutter. Current field trial (over 6500 square meters) and blind test results (over 39000 square meters) are presented and these show at least an order of magnitude improvement over other radar system-based detection algorithms on the same test lanes.     

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％.     

机载探测设备目标识别算法的研究

针对机载探测设备多传感器系统具有多目标,大量观测数据的特点,提出了一种基于Demp-ster-Shafer（D-S）证据理论和主观Bayesian方法组合的数据融合算法。在数据融合过程中,为保证融合的实时性,融合系统采用时域融合和空域融合相结合的方法,首先对相同传感器的各次抽样值进行时域融合,然后传感器之间的融合采用D-S方法进行融合;最后,其融合结果经概率转化后,与来自于ELINT（Electronic Intelligence）的信息通过主观Bayesian方法进行识别级融合。最后给出一个实例,经过仿真计算证明了该算法的可行性和实用性。     

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).     

多传感器协同探测证据理论分类融合方法

随着智能化、网络化集群作战等理念和技术的兴起，精确制导武器越来越向智能化、协同化方向发展。多传感器协同探测能够针对不同的探测任务背景和作战需求，提升目标探测性能，还可以跨域整合多种探测平台。但是由于信息的不确定性等特点，使得多传感器数据直接融合可能造成决策困难。因此，在证据理论体系下对信息融合的有效性进行合理分析与度量是很有必要的。提出了一种基于Deng熵的证据理论分类融合算法，以熵减为主要思想，将证据进行分类融合。在决策过程中，将含有证据数最多的类别融合结果作为总体融合结果，避免高冲突证据的影响，提升融合结果的信息有效性。采用算例说明了所提方法不仅能够得到合理正确的结果，并且融合可靠性较高，便于决策与后续的信息处理。     

Fault Detection in Dynamic Systems via Decision Fusion

Due to the growing demands for system reliability and availability of large amounts of data, efficient fault detection techniques for dynamic systems are desired. In this paper, we consider fault detection in dynamic systems monitored by multiple sensors. Normal and faulty behaviors can be modeled as two hypotheses. Due to communication constraints, it is assumed that sensors can only send binary data to the fusion center. Under the assumption of independent and identically distributed (1ID) observations, we propose a distributed fault detection algorithm, including local detector design and decision fusion rule design, based on state estimation via particle filtering. Illustrative examples are presented to demonstrate the effectiveness of our approach.     

基于加权融合的多信源弹道数据实时野值检测方法

研究多信源弹道数据实时处理中斑点野值的检测问题.通过计算各信源数据的实时精度,给出了具有自适应加权系数的加权融合方法,实现了对目标状态参数较高精度的估计,从而实时、准确、高效地检测各信源数据野值.仿真结果表明,本方法可以快速、有效地检测多信源数据的斑点野值,解决因数据切换带来的台阶跳跃问题.     

Decentralized CFAR signal detection

The authors develop the theory of CA-CFAR (cell-averaging constant false-alarm rate) detection using multiple sensors and data fusion, where detection decisions are transmitted from each CA-CFAR detector to the data fusion center. The overall decision is obtained at the data fusion center based on some k out of n fusion rule. For a Swerling target model I embedded in white Gaussian noise of unknown level, the authors obtain the optimum threshold multipliers of the individual detectors. At the data fusion center, they derive an expression for the overall probability of detection while the overall probability of false alarm is maintained at the desired value for the given fusion rules. An example is presented showing numerical results     

临近空间无人飞行器多余度容错导航系统设计

临近空间无人飞行器导航系统的故障直接影响到飞行器的任务执行和飞行安全,因此必须能够长时间地保持稳定性和精确性,为达到此目的必须设计由惯性导航、卫星导航等多种导航传感器组成的多源多余度容错导航系统,提高系统的可靠性。针对临近空间飞行器制导控制对导航信息的需求,提出了一种标准的三余度导航系统架构,并设计了采用新型加权平均表决子算法,具备故障检测和隔离以及故障重构功能的容错重构算法,构建了适用于临近空间无人飞行器的多余度容错导航系统,通过实测试验数据仿真验证了容错导航系统的性能,展示了系统一次故障工作的故障容错能力。所研究内容也可被其他类型的无人飞行器借鉴和参考。     

基于神经网络补偿的室内无人机组合导航系统

针对无人飞行器在环境特征突变情况下数据融合的可靠性大幅下降问题，提出了神经网络预测补偿的组合导航算法。首先利用扩展卡尔曼滤波和粒子滤波对激光、光流等传感器得到的数据进行融合，然后采用径向基函数（RBF）神经网络对粒子滤波前后的误差进行预测。当激光数据可靠时，RBF神经网络进行训练学习模式，当激光数据中断或者不可靠时，利用训练后的模型对系统进行误差补偿。利用无人飞行器在室内环境下进行定点和轨迹实验，结果表明补偿后的位置导航信息能够明显降低激光数据不可靠时带来的定位误差。     

Optimal m-ary data fusion with distributed sensors

An optimal data fusion rule is derived for an m-ary detection problem. Each detector determines a local decision using a local decision rule and transmits the local decision to the fusion center. Considering the reliability of local detectors, local decisions are combined to produce the final decision. In this study, based upon the maximum posterior probability concept, optimal decision rules for m-ary detection problems are proposed for the local detector and the data fusion center     

液体火箭发动机泄漏故障诊断的信息融合技术

从故障诊断角度出发,分析了故障诊断和信息融合技术关系。综合现在进行液体火箭发动机检漏的相关技术,为了弥补泄漏故障诊断信息不足等问题,提出了采用点式和红外传感器相结合的方法来探测泄漏故障引起的各种现象,概述了该领域的相关技术和实现方法,建立了基于信息融合的泄漏故障检测与诊断系统,有利于提高泄漏故障的有效性和可信度。      

时空关联多跟踪剔除的多源数据融合方法

随着网络信息共享技术的深入发展,多源异构数据将是未来数据融合的主要信息源,这种数据融合表现出跨平台、跨军种、跨领域等特征,对多源异构数据关联与融合提出了新要求。针对特定场景敏感区域内有限多目标的探测问题,结合一体化作战数据融合的数据滤波、空时配准、航迹关联与建立、多目标跟踪等方面,提出了时空关联多跟踪剔除的数据融合方法,并从数据滤波、航迹关联与融合、时空关联多跟踪剔除以及融合数据“簇”等方面重点研究了所提出的数据融合方法。距离波门拖引干扰和牵引干扰的对抗仿真试验表明,所提方法具有一定应用价值。     

Propagation velocity uncertainty on GPR SAR processing

To detect buried landmines, Planning Systems Incorporated (PSI) has developed a ground-penetrating synthetic aperture radar (GPSAR) system. Since the electromagnetic wave propagation velocity in the soil depends on many factors, velocity uncertainty is inevitable. However, we have observed that, unlike conventional airborne/spaceborne synthetic aperture radar (SAR) systems, the PSI GPSAR system is very robust against the velocity uncertainty under mild conditions. Theoretical analysis is provided to explain this observation. Although our discussion is based on the PSI GPSAR system, it applies to other GPR-based (ground-penetrating radar) landmine detection systems as well.     

Adaptive learning approach to landmine detection

We consider landmine detection using forward-looking ground penetrating radar (FLGPR). The two main challenging tasks include extracting intricate structures of target signals and adapting a classifier to the surrounding environment through learning. Through the time-frequency (TF) analysis, we find that the most discriminant information is TF localized. This observation motivates us to use the over-complete wavelet packet transform (WPT) to sparsely represent signals with the discriminant information encoded into several bases. Then the sequential floating forward selection method is used to extract these components and thereby a neural network (NNW) classifier is designed. To further improve the classification performance and deal with the problem of detecting mines in an unconstraint environment, the AdaBoost algorithm is used. We integrate the feature selection process into the original AdaBoost algorithm. In each iteration, AdaBoost identifies the hard-to-learn examples and a new set of features which provide the specific discriminant information for these hard samples is extracted adaptively and a new classifier is trained. Experimental results based on measured data are presented, showing that a significant improvement on the classification performance can be achieved.     

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.     

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。