High-accuracy target tracking for multistatic passive radar based on a deep feedforward neural network

In radar systems,target tracking errors are mainly from motion models and nonlinear measurements.When we evaluate a tracking algorithm,its tracking accuracy is the main criterion.To improve the tracking accuracy,in this paper we formulate the tracking problem into a regression model from measurements to target states.A tracking algorithm based on a modified deep feedforward neural network(MDFNN)is then proposed.In MDFNN,a filter layer is introduced to describe the temporal sequence relationship of the input measurement sequence,and the optimal measurement sequence size is analyzed.Simulations and field experimental data of the passive radar show that the accuracy of the proposed algorithm is better than those of extended Kalman filter(EKF),unscented Kalman filter(UKF),and recurrent neural network(RNN)based tracking methods under the considered scenarios.

Velocity-Varying Target Tracking of Mobile Sensor Network Based on Flocking Control

Existing coupled distributed estimation and motion control strategies of mobile sensor networks present limitations in velocity-varying target tracking. Therefore, a velocity-varying target tracking algorithm based on flocking control is proposed herein. The Kalman-consensus filter is utilized to estimate the position, velocity and acceleration of a target. The flocking control algorithm with a velocity-varying virtual leader enables the position of the center of the mobile sensor network to converge to that of the target. By applying an effective cascading Lyapunov method, stability analysis is performed. Simulation results are provided to validate the feasibility of the proposed algorithm.

Target Tracking and Obstacle Avoidance for Multi-agent Networks with Input Constraints

In this paper, the problems of target tracking and obstacle avoidance for multi-agent networks with input constraints are investigated. When there is a moving obstacle, the control objectives are to make the agents track a moving target and to avoid collisions among agents. First, without considering the input constraints, a novel distributed controller can be obtained based on the potential function. Second, at each sampling time, the control algorithm is optimized. Furthermore, to solve the problem that agents cannot effectively avoid the obstacles in dynamic environment where the obstacles are moving, a new velocity repulsive potential is designed. One advantage of the designed control algorithm is that each agent only requires local knowledge of its neighboring agents. Finally, simulation results are provided to verify the effectiveness of the proposed approach.

Track-to-Track Association Technique in Radar Network in the Presence of Systematic Errors

The presence of systematic measuring errors complicates track-to-track association, spatially separates the tracks that correspond to the same true target, and seriously decline the performances of traditional track-to-track association algorithms. Consequently, the influence of radar systematic errors on tracks from different radars, which is described as some rotation and translation, has been analyzed theoretically in this paper. In addition, a novel approach named alignment-correlation method is developed to estimate and reduce this effect, align and correlate tracks accurately without prior registration using phase correlation technique and statistic binary track correlation algorithm. Monte-Carlo simulation results illustrate that the proposed algorithm has good performance in solving the track-to-track association problem with systematic errors in radar network and could provide effective and reliable associated tracks for the next step of registration.

Adaptive time-space resource and waveform control for collocated MIMO radar with simultaneous multi-beam

Collocated multiple input multiple output(MIMO)radar,which has agile multi-beam working mode,can offer enhanced multiple targets tracking(MTT)ability.In detail,it can illuminate different targets simultaneously with multi-beam or one wide beam among multi-beam,providing greater degree of freedom in system resource control.An adaptive time-space resource and waveform control optimization model for the collocated MIMO radar with simultaneous multi-beam is proposed in this paper.The aim of the proposed scheme is to improve the overall tracking accuracy and meanwhile minimize the resource consumption under the guarantee of effective targets detection.A resource and waveform control algorithm which integrates the genetic algorithm(GA)is proposed to solve the optimization problem.The optimal transmitting waveform parameters,system sampling period,sub-array number,binary radar tracking parameterχ_i(t_k),transmitting energy and multi-beam direction vector combination are chosen adaptively,where the first one realizes the waveform control and the latter five realize the timespace resource allocation.Simulation results demonstrate the effectiveness of the proposed control method.

Online multi-target intelligent tracking using a deep long-short term memory network

Multi-target tracking is facing the difficulties of modeling uncertain motion and observation noise.Traditional tracking algorithms are limited by specific models and priors that may mismatch a real-world scenario.In this paper,considering the model-free purpose,we present an online Multi-Target Intelligent Tracking(MTIT)algorithm based on a Deep Long-Short Term Memory(DLSTM)network for complex tracking requirements,named the MTIT-DLSTM algorithm.Firstly,to distinguish trajectories and concatenate the tracking task in a time sequence,we define a target tuple set that is the labeled Random Finite Set(RFS).Then,prediction and update blocks based on the DLSTM network are constructed to predict and estimate the state of targets,respectively.Further,the prediction block can learn the movement trend from the historical state sequence,while the update block can capture the noise characteristic from the historical measurement sequence.Finally,a data association scheme based on Hungarian algorithm and the heuristic track management strategy are employed to assign measurements to targets and adapt births and deaths.Experimental results manifest that,compared with the existing tracking algorithms,our proposed MTIT-DLSTM algorithm can improve effectively the accuracy and robustness in estimating the state of targets appearing at random positions,and be applied to linear and nonlinear multi-target tracking scenarios.

基于网络流跟踪的信号灯检测方法

结合信号灯信息对机动车行进速度进行引导,减少机动车启停次数,可有效减少废气排放,缓解其造成的污染问题。针对信号灯转换时刻的获取问题,提出了一种基于网络流跟踪的信号灯检测方法。首先,该方法在数据集中引入辅助信号灯类别进行训练,将视频序列中该类目标检测结果关联为踪片,并通过踪片建模多目标跟踪任务。其次,该方法将多目标跟踪任务转换为最小费用流优化任务,以踪片作为节点建立最小费用流网络,提出了适合于信号灯的费用构建方式,通过最短路径算法求解,得到视频序列中辅助信号灯的多条轨迹。最后,基于求解的轨迹结果和图像分类技术,实现信号灯检测性能的提升。该方法的跟踪性能相较于对比算法有大幅提升,并将小目标信号灯检测响应的mAP提升至94.35%。实验结果表明,基于网络流的建模方式能极大地提升信号灯的跟踪准确率,结合跟踪轨迹还能大幅提高视频序列中小目标信号灯的检测准确率,并可有效确定信号灯状态的转换时刻。

一种多雷达机动目标探测高阶运动特征估计方法

针对单站雷达常因为跟踪模型与目标真实运动状态失配而造成对目标高阶运动特征估计精度较差的问题。从雷达组网结合径向速度增广量测的角度,来提升目标高阶运动特征估计精度。采用序贯无迹卡尔曼滤波算法对多雷达的异步量测信息进行集中式融合。分析了不同测距、测角精度与径向速度增广量测下目标高阶运动特征的估计效果,并利用双传感器的几何精度因子优化雷达站布局以分析雷达站布局对目标高阶运动特征估计效果的影响。通过仿真实验发现,在该雷达组网方式下,雷达测距精度比测角精度对目标高阶运动特征估计效果的影响要大。雷达站布局优化结合径向速度增广量测可以有效地获得目标高阶运动特征的高精度估计。

基于4D毫米波雷达点云的多目标跟踪算法

目前智能空调的研究主要基于视觉或红外传感器,基于单个4D毫米波雷达的相对较少。采用单个4D毫米波雷达传感器采集数据,根据不同目标反射点位置的不同提出了密度聚类(Density-Based Spatial Clustering of Application with Noise,DBSCAN)算法实现目标的聚类识别,并与K均值(K-means)聚类算法进行了效果对比。针对多目标跟踪问题,设计了一种基于联合概率数据关联算法(Joint Probabilistic Data Association,JPDA)和卡尔曼滤波(Kalman Filter,KF)的目标跟踪算法,从而实现多目标的匹配和跟踪。将所研究的算法应用到4D毫米波雷达系统,并在室内采集了行人目标数据,分析对比实际场景和算法跟踪效果,误差大约在8 cm内,准确率可达91.8%。结果表明:该算法可以较好地实现多目标跟踪,可用于智能空调中。

Coordination of multiple mobile robots with limited communication range in pursuit of single mobile target in cluttered environment

This paper addresses the problem of coordinating multiple mobile robots in searching for and capturing a mobile target,with the aim of reducing the capture time.Compared with the previous algorithms,we assume that the target can be detected by any robot and captured successfully by two or more robots.In this paper,we assume that each robot has a limited communication range.We maintain the robots within a mobile network to guarantee the successful capture.In addition,the motion of the target is modeled and incorporated into directing the motion of the robots to reduce the capture time.A coordination algorithm considering both aspects is proposed.This algorithm can greatly reduce the expected time of capturing the mobile target.Finally,we validate the algorithm by the simulations and experiments.

U-net分割网络雷达弱小目标检测方法

常规雷达检测方法难以满足当前弱小目标检测需求,而检测前跟踪(TBD)方法在雷达弱小目标检测中存在计算复杂度高、复杂场景性能严重退化的问题.为此,本文提出了一种U-net分割网络的雷达弱小目标检测方法.首先,利用过低门限的多圈检测点形成待分割的图片;然后,利用U-net网络对实体目标进行分割,实现对弱小目标的有效探测.雷达实测数据测试结果表明,本文提出的方法能够大幅提升雷达对远距离小目标的跟踪距离,有效抑制虚假短航迹,为解决雷达弱小目标检测提供了新的解决思路.

非理想检测下面向异步多目标跟踪的异构多雷达网络功率时间联合优化算法

该文针对异步多目标跟踪场景,研究了非理想检测下的异构多雷达网络功率时间联合优化问题。首先,将各融合采样间隔内得到的来自不同雷达节点的所有异步量测信息融合为复合量测信息,结合该复合量测信息推导了非理想检测下包含雷达节点选择、辐射功率和驻留时间等参数的异步目标跟踪误差贝叶斯克拉美罗下界(BCRLB)解析表达式,并将其作为异步多目标跟踪精度的衡量指标。在此基础上,建立了非理想检测下面向异步多目标跟踪的异构多雷达网络功率时间联合优化模型,即以最小化异步多目标跟踪误差为优化目标,以满足给定的系统辐射资源限制为约束条件,对不同雷达网络中雷达节点的选择方式、辐射功率和驻留时间等发射参数进行自适应联合优化设计,从而提升异构多雷达网络的异步多目标跟踪精度。最后,针对上述优化问题,结合序列二次规划(SQP)算法和循环最小法,采用四步分解算法进行求解。仿真结果表明,与现有算法相比,所提算法能够有效提升异构多雷达网络的异步多目标跟踪精度。

非理想检测下基于多目标跟踪的多雷达网络功率时间管控算法

为了在非理想检测下提升多雷达网络多目标跟踪的射频隐身性能,提出了一种多雷达网络功率时间管控算法。首先,推导并计算了非理想检测下目标跟踪误差的贝叶斯克拉美-罗下界,将其作为目标跟踪精度的衡量指标。其次,将多雷达网络系统中分配的雷达节点对目标的总辐射功率与总驻留时间作为优化函数,以预先设定的目标跟踪精度阈值以及系统射频辐射资源作为约束条件,建立了非理想检测下基于多目标跟踪的多雷达网络功率时间优化模型。最后,提出了一种结合障碍函数法与循环最小法的多步分解算法进行求解。仿真结果表明,随着检测概率逐渐降低,为了满足目标跟踪精度要求,系统需要分配更多的辐射功率和驻留时间,导致系统射频隐身性能变差,而相较于其他对比算法,所提算法辐射功率消耗最大降低约52.6%,驻留时间消耗最大降低约33.1%,有效提升了系统射频隐身性能。

基于无人机对雷达系统航迹欺骗干扰的仿真研究

以无人机对组网雷达的协同干扰为背景,利用Matlab软件对每一架无人机的运动规律进行分析,结合运动伪装学相关理论,对于轨迹控制参数进行研究,且以5架无人机协同干扰雷达为例进行模拟。通过仿真分析可知,在速度大小不变的条件下,多架干扰机可通过协同工作来对组网雷达实施航迹欺骗干扰,能够达到以假乱真的效果,虚假航迹可行。

基于LSTM子网络聚合的雷达TWS跟踪

为了提高雷达TWS跟踪的准确性和时效性,解决在高密度杂波环境下传统跟踪算法性能大幅下降和模型依赖问题,论文提出了一种免模型、纯数据驱动、端到端学习的雷达多目标跟踪框架和基于长短期记忆网络(LSTM)子网络聚合的雷达TWS跟踪方法。该方法将含噪声的量测通过数据关联子网络,在多目标、杂波和漏检情况下可正确输出与已跟踪目标的关联矩阵;并通过轨迹预测子网络预测和更新机动目标的运动轨迹;最后使用航迹管理子网络来管理航迹生命周期。通过仿真实验证明了该方法的可行性,与传统TWS跟踪算法相比,该方法具有更高的跟踪精度和关联正确率,而且不依赖复杂的先验运动模型和杂波分布知识。

不确定欠驱动系统的自适应跟踪控制设计

针对一类具有不确定参数的非线性欠驱动系统,研究了其基于辅助关联参考目标的跟踪控制问题,并提出了相应的自适应跟踪控制方案。首先建立欠驱动系统的动力学模型;然后基于辅助关联参考目标结合Lyapunov稳定性理论,合成了被控欠驱动系统的自适应跟踪控制方案;最终给出数值仿真验证了该控制方案的有效性。

频谱共存下机载组网雷达辐射资源与航迹规划联合优化算法

为了提升频谱共存环境下机载组网雷达多目标跟踪性能,提出了一种雷达辐射资源与航迹规划联合优化算法。首先,推导了包含雷达辐射资源以及载机飞行参数的贝叶斯克拉美-罗下界表达式,以此作为多目标跟踪精度的衡量指标;在此基础上,以最小化机载组网雷达多目标跟踪误差为优化目标,以雷达辐射资源总量、载机机动性能、通信基站可容忍干扰能量和跟踪各目标节点数为约束条件,建立频谱共存下机载组网雷达辐射资源与航迹规划联合优化模型;然后,将上述优化模型分解为多个子问题,并结合循环最小化算法、半正定规划算法和粒子群算法进行分步求解。最终仿真结果表明,所提算法能够在保证通信基站正常工作的条件下,充分利用各平台运动优势,与现有算法相比,能够有效提升机载组网雷达的多目标跟踪性能。

车载分布式MIMO雷达原理与实测数据分析

文中分析了分布式构型多输入多输出(MIMO)雷达及其处理框架,并针对车载应用场景,结合超分辨测角算法给出了一套基于分布式MIMO雷达的成像、测速、跟踪处理流程。在此处理流程的基础上,文中创新性地提出了基于高斯混合概率假设密度(GM-PHD)跟踪算法的距离-角度-速度关联方案,并对GM-PHD算法进行了改进,增加了标签配对功能,同时实现了多维信息的快速关联和目标的航迹跟踪。最后,利用实测数据验证了相关算法的有效性和实用性,与单一雷达成像及跟踪结果对比并进行了详细分析,验证了分布式MIMO雷达具有更优的目标检测性能及目标跟踪效果。

基于方位机扫雷达的机动目标双波门跟踪方法

点迹-航迹处理是雷达航迹跟踪过程中的重要一环,是把雷达探测到的点迹与已知航迹进行比较,然后正确关联配对的过程。复杂环境下的目标跟踪要求点迹-航迹关联处理、目标航迹跟踪的滤波和预测都要可靠,正确的点迹-航迹关联结果会产生较为准确的滤波和预测,而准确的滤波预测又会促进点迹-航迹的正确关联,二者之间是相辅相成的。常规跟踪法在目标机动尤其是悬停情况下的跟踪难度较大,多次掉点后不易重新正确关联,容易出现掉批、误关联等情况的发生。本文提出了一种基于前后双波门的机动目标跟踪法,可以使方位机扫雷达较好地连续跟踪机动目标。

基于CNN的雷达航迹分类方法

针对雷达目标识别问题,提出了一种航迹级的目标分类方法,基于目标航迹的运动学特征,应用卷积神经网络对目标航迹数据进行训练和分类。应用对数处理方法对数据进行预处理,搭建基于残差网络(ResNet)的深度学习模型,再应用连续识别策略,对目标类型进行综合判定。实验结果表明该方法可有效实现雷达目标航迹的分类识别。