Modified joint probabilistic data association with classification-aided for multitarget tracking

Joint probabilistic data association is an effective method for tracking multiple targets in clutter, but only the target kinematic information is used in measure-to-track association. If the kinematic likelihoods are similar for different closely spaced targets, there is ambiguity in using the kinematic information alone; the correct association probability will decrease in conventional joint probabilistic data association algorithm and track coalescence will occur easily. A modified algorithm of joint probabilistic data association with classification-aided is presented, which avoids track coalescence when tracking multiple neighboring targets. Firstly, an identification matrix is defined, which is used to simplify validation matrix to decrease computational complexity. Then, target class information is integrated into the data association process. Performance comparisons with and without the use of class information in JPDA are presented on multiple closely spaced maneuvering targets tracking problem. Simulation results quantify the benefits of classification-aided JPDA for improved multiple targets tracking, especially in the presence of association uncertainty in the kinematic measurement and target maneuvering. Simulation results indicate that the algorithm is valid.

VIDEO MULTI-TARGET TRACKING BASED ON PROBABILISTIC GRAPHICAL MODEL

In the technique of video multi-target tracking,the common particle filter can not deal well with uncertain relations among multiple targets.To solve this problem,many researchers use data association method to reduce the multi-target uncertainty.However,the traditional data association method is difficult to track accurately when the target is occluded.To remove the occlusion in the video,combined with the theory of data association,this paper adopts the probabilistic graphical model for multi-target modeling and analysis of the targets relationship in the particle filter framework.Ex-perimental results show that the proposed algorithm can solve the occlusion problem better compared with the traditional algorithm.

Maneuvering Multi-target Tracking Algorithm Based on Modified Generalized Probabilistic Data Association

Aiming at the problem of strong nonlinear and effective echo confirm of multi-target tracking system in clutters environment, a novel maneuvering multitarget tracking algorithm based on modified generalized probabilistic data association is proposed in this paper. In view of the advantage of particle filter which can deal with the nonlinear and non-Gaussian system, it is introduced into the framework of generalized probabilistic data association to calculate the residual and residual covariance matrices, and the interconnection probability is further optimized. On that basis, the dynamic combination of particle filter and generalized probabilistic data association method is realized in the new algorithm. The theoretical analysis and experimental results show the filtering precision is obviously improved with respect to the tradition method using suboptimal filter.

Missing Value Imputation for Radar-Derived Time-Series Tracks of Aerial Targets Based on Improved Self-Attention-Based Network

The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.

Vessel fusion tracking with a dual-frequency high-frequency surface wave radar and calibrated by an automatic identification system

High-frequency surface wave radar（HFSWR） and automatic identification system（AIS） are the two most important sensors used for vessel tracking.The HFSWR can be applied to tracking all vessels in a detection area,while the AIS is usually used to verify the information of cooperative vessels.Because of interference from sea clutter,employing single-frequency HFSWR for vessel tracking may obscure vessels located in the blind zones of Bragg peaks.Analyzing changes in the detection frequencies constitutes an effective method for addressing this deficiency.A solution consisting of vessel fusion tracking is proposed using dual-frequency HFSWR data calibrated by the AIS.Since different systematic biases exist between HFSWR frequency measurements and AIS measurements,AIS information is used to estimate and correct the HFSWR systematic biases at each frequency.First,AIS point measurements for cooperative vessels are associated with the HFSWR measurements using a JVC assignment algorithm.From the association results of the cooperative vessels,the systematic biases in the dualfrequency HFSWR data are estimated and corrected.Then,based on the corrected dual-frequency HFSWR data,the vessels are tracked using a dual-frequency fusion joint probabilistic data association（JPDA）-unscented Kalman filter（UKF） algorithm.Experimental results using real-life detection data show that the proposed method is efficient at tracking vessels in real time and can improve the tracking capability and accuracy compared with tracking processes involving single-frequency data.

Study on multiple maneuvering targets tracking based on JPDA algorithm

A tracking algorithm for multiple-maneuvering targets based on joint probabilistic data association（JPDA）is proposed to improve the accuracy for tracking algorithm of traditional multiple maneuvering targets.The interconnection probability of the two targets is calculated,the weighted value is processed and the target tracks are obtained.The simulation results show that JPDA algorithm achieves higher tracking accuracy and provides a basis for more targets tracking.

Method of target tracking with Doppler blind zone constraint

Doppler blind zone （DBZ） has a bad influence on the airborne early warning radar, although it has good detection performance for low altitude targets with pulse Doppler （PD） technology. In target tracking, the blind zone can cause target tracking breakage easily. In order to solve this problem, a parallel particle filter （PF） algorithm based on multi-hypothesis motion models （MHMMs） is proposed. The algorithm produces multiple possible target motion models according to the DBZ constraint. Particles are updated with the constraint in each motion model. Once the first measurement from the target which reappears from DBZ falls into the particle cloud formed by any model, the measurementtrack association succeeds and track breakage is avoided. The simulation results show that on the condition of different DBZ ranges, a high association ratio can be got for targets with different maneuverability levels, which accordingly improves the tracking quality.

Target tracking based on frequency spectrum amplitude

The amplitude of frequency spectrum can he integrated with prohabilisfic data association （PDA） to distinguish the target with clutter echoes, especially in low SNR underwater environment. A new target-tracking algorithm is presented which adopts the amplitude of frequency spectrum to improve target tracking in clutter. The prohabilisfic density distribution of frequency spectrum amplitude is analyzed. By simulation, the results show that the algorithm is superior to PDA. This approach enhances stability for the association probability and increases the performance of target tracking.

A novel maneuvering multi-target tracking algorithm based on multiple model particle filter in clutters

To solve the problem of strong nonlinear and motion model switching of maneuvering target tracking system in clutter environment, a novel maneuvering multi-target tracking algorithm based on multiple model particle filter is presented in this paper. The algorithm realizes dynamic combination of multiple model particle filter and joint probabilistic data association algorithm. The rapid expan- sion of computational complexity, caused by the simple combination of the interacting multiple model algorithm and particle filter is solved by introducing model information into the sampling process of particle state, and the effective validation and utilization of echo is accomplished by the joint proba- bilistic data association algorithm. The concrete steps of the algorithm are given, and the theory analysis and simulation results show the validity of the method.

Dominant Correlogram Based Particle Filter Tracking

A novel dominant correlogram based particle filter was proposed for an object tracking in visual surveillance. Particle filter outperforms the Kalman filter in non-linear and non-Gaussian estimation problem. This paper proposed incorporating spatial information into visual feature, and yields a reliable likelihood description of the observation and prediction. A similarity-ratio is defined to evaluate the effectivity of different similarity measurements in weighing samples. The experimental results demonstrate the effective and robust performance compared with the histogram based tracking in traffic scenes.

车辆-轨道系统动力极值预测及可靠度计算

为从车辆-轨道系统的动力极值预测及其可靠度计算角度分析车辆系统行车安全、衡量系统可靠程度,基于车辆-轨道耦合动力学及概率理论,提出一种车轨系统动力极值预测及可靠度评估方法。首先,基于轨道不平顺概率模型,采用轨道不平顺累计概率谱确定具有不同激振能量的随机不平顺序列;依据离散Parseval定理,建立轨道不平顺时域序列和功率谱间的对应关系;将轨道不平顺概率模型与车辆-轨道耦合动力学模型相结合,从随机动力计算中提取车辆-轨道的动力极值及可靠度信息;随后利用车辆-轨道耦合动力模型及二维插值算子,根据谱线能量关系实现动力极值预测;此外,基于此系统激励输入与响应输出间的概率等效性,导出了动力极值的可靠度计算式。以实测的轨道不平顺和车体加速度数据及4种类型不平顺在不同累计概率下的谱组合计算得出的轮轨横向力和钢轨垂向位移的计算结果为样本,与预测结果进行对比。研究结果表明:计算时程的分布趋势基本与实测时程一致,动力极值预测结果与实际的动力计算结果较为接近。由于轨道不平顺随机性的存在使得车辆-轨道系统的动力响应存在随机离散及方差特征,但通过轨道不平顺的幅频及能量特性预测车辆-轨道系统的动力极值的方法是较为可行的。

基于消息传递的机载雷达组网航迹融合

机载雷达组网航迹融合需要解决目标跟踪、数据关联与航迹管理3个子问题,然而这3个子问题相互耦合,采用开环序贯估计算法会导致性能下降.本文提出了一种基于消息传递的机载雷达组网航迹融合方法,该方法在联合优化框架下解决目标跟踪、数据关联与航迹管理3个子问题.首先,建立机载雷达组网航迹融合的联合概率密度函数,并将其转换为因子图.其次,将因子图分解为置信传播区域与平均场近似区域.目标运动状态的统计模型服从共轭指数模型,因此采用平均场近似以获得简单的消息传递更新公式.数据关联包含一对一约束,因此采用置信传播.目标存在状态同样采用置信传播,以获得更好的近似结果.最后,可以通过闭环迭代框架近似估计后验分布,从而有效处理目标跟踪、数据关联与航迹管理之间的耦合问题.仿真结果表明,所提算法的性能优于多假设跟踪算法和联合概率密度关联算法.

基于PACA的复杂空中目标战术意图识别方法

针对战场中空中目标航迹动态性、时序变化性及意图多样的特性,提出一种基于端到端类属属性学习的识别方法,作为智能多意图识别模型的基本框架。融合目标航迹中的时序特征及属性特点,通过压缩及修正预处理统一输入编码信息,封装专家的知识经验为标签,学习指挥员战时情况判断的思维方式,消除其隐蔽性、欺骗性和对抗性所带来的干扰因素,得出特定目标的复杂战术意图。通过仿真实验,采用常用多分类评价体系分析端到端训练方式对结果的影响,以及与相关方法的对比分析表明,所提算法针对多意图识别更具有效性和参考价值,可用于支撑作战筹划系统建立非合作目标与保卫要地的关联关系。

Object Tracking and Tracing:Hidden Semi-Markov Model Based Probabilistic Location Determination

The enhancement of radio frequency identification(RFID) technology to track and trace objects has attracted a lot of attention from the healthcare and the supply chain industry.However,RFID systems do not always function reliably under complex and variable deployment environment.In many cases,RFID systems provide only probabilistic observations of object states.Thus,an approach to predict,record and track real world object states based upon probabilistic RFID observations is required.Hidden Markov model(HMM) has been used in the field of probabilistic location determination.But the inherent duration probability density of a state in HMM is exponential,which may be inappropriate for modeling of object location transitions.Hence,in this paper,we put forward a hidden semi-Markov model(HSMM) based approach for probabilistic location determination. We evaluated its performance comparing with that of the HMM-based approach.The results show that the HSMM-based approach provides a more accurate determination of real world object states based on observation data.

不同累积概率不平顺状态下轨道板离缝损伤研究

为明晰线弹性模型与非线性损伤塑性模型在无砟轨道不同状态下的适用范围,研究层间离缝纵向扩展过程中轨道板在列车动荷载作用下的损伤萌生扩展规律,基于ABAQUS有限元软件建立CRTSⅠ型板式无砟轨道空间实体模型,以不同累积概率不平顺状态下的扣件支点压力作为荷载激励,分别采用线弹性模型与非线性损伤塑性模型描述轨道板混凝土应力-应变关系,对比分析整体轨道板在2种本构模型下的受力状态,分析其在轨道板-CA砂浆层层间离缝状态下的动力损伤规律。研究结果表明:在轨道结构正常状态下,各累积概率不平顺状态下的轨道板纵、横向拉应力水平较低,可采用线弹性模型简化计算;层间离缝状态下,轨道板上表面将承受较大拉应力而使轨道板受力进入塑性软化阶段,此时可采用非线性损伤塑性模型描述轨道板损伤的萌生、扩展过程。10%~90%累积概率不平顺状态下,轨道板损伤萌生所需离缝纵向长度处于820~890 mm之间,99%累积概率下仅需580 mm。轨道板损伤首先产生于第2组承轨台周围的轨下对应区域,随离缝纵向发展同时向板中与板边扩展直至贯通;轨道不平顺状态越差,轨道板损伤萌生与达到最大拉伸损伤所需离缝纵向长度越小。损伤所产生的塑性应变将引起轨道板几何状态的改变,进一步恶化轨道不平顺状态,造成轨道板损伤-轨道不平顺加剧的恶性循环。

基于概率校准平衡随机森林算法的轨道电路故障诊断方法

传统的轨道电路故障分析方法大多假设不同类别的数据样本数量是相似或相等的,然而在实际采集到的监测数据中,正常工作的样本数据占绝大部分,故障数据只占少部分,这种数据不平衡特性会影响学习模型的分类性能,从而不能给出准确的故障诊断结果。因此文中提出基于概率校准平衡随机森林算法的轨道电路故障分析方法,以减少数据不平衡对轨道电路故障诊断准确度的影响。实验结果表明:经过概率校准后的平衡随机森林算法对实际监测数据具有更好的分析诊断能力;与XGBoost、LightGBM等算法相比,PC-BRF在ZPW-2000二分类数据集以及在25 Hz轨道电路多分类数据集上的分类综合性能更优,能对轨道电路故障不平衡数据进行有效分析,提高现场监测数据的利用率。

Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking

The performance of existing maneuvering target tracking methods for highly maneuvering targets in cluttered environments is unsatisfactory.This paper proposes a hybrid-driven approach for tracking multiple highly maneuvering targets,leveraging the advantages of both data-driven and model-based algorithms.The time-varying constant velocity model is integrated into the Gaussian process(GP)of online learning to improve the performance of GP prediction.This integration is further combined with a generalized probabilistic data association algorithm to realize multi-target tracking.Through the simulations,it has been demonstrated that the hybrid-driven approach exhibits significant performance improvements in comparison with widely used algorithms such as the interactive multi-model method and the data-driven GP motion tracker.

PTMOT: A Probabilistic Multiple Object Tracker Enhanced by Tracklet Confidence for Autonomous Driving

Real driving scenarios,due to occlusions and disturbances,provide disordered and noisy measurements,which makes the task of multi-object tracking quite challenging.Conventional approach is to find deterministic data association;however,it has unstable performance in high clutter density.This paper proposes a novel probabilistic tracklet-enhanced multiple object tracker(PTMOT),which integrates Poisson multi-Bernoulli mixture(PMBM)filter with confidence of tracklets.The proposed method is able to realize efficient and robust probabilistic association for 3D multi-object tracking(MOT)and improve the PMBM filter’s continuity by smoothing single target hypothesis with global hypothesis.It consists of two key parts.First,the PMBM tracker based on sets of tracklets is implemented to realize probabilistic fusion of disordered measure-ments.Second,the confidence of tracklets is smoothed through a smoothing-while-filtering approach.Extensive MOT tests on nuScenes tracking dataset demonstrate that the proposed method achieves superior performance in different modalities.

基于联合概率数据融合的多目标车辆安全跟随

为了实现密集杂波环境下多目标车辆安全跟随,提出多源传感器数据融合的多目标车辆跟踪算法与纵向避撞预警策略.针对多源传感器观测序列因采样周期、采样起始时刻、通信时延差异等引起的时间异步,以及空间上存在不同维度、不同坐标系的问题,给出时间配准与空间融合的软同步方法.采用基于改进的联合概率数据关联(JPDA)的单一传感器多目标状态估计算法对目标轨迹进行滤波估计,能够在保证有效关联的同时,在一定程度上降低计算复杂度.基于多源传感器联合概率数据融合(MSJPDA)序贯滤波算法对目标的运动状态进行序贯更新,将最后一级的输出作为融合中心的最终状态估计,再根据威胁估计模型对追尾危险的发展态势进行评估与分级.实车试验与仿真结果验证了该算法的可行性与有效性.

视频监控系统中的概率模型单目标跟踪框架

针对视频监控的特点与跟踪目标的强机动性,提出了一种新的基于概率模型的目标跟踪框架,从目标表观模型、系统动态模型以及系统观测模型3个方面对当前标准的粒子滤波目标跟踪方法进行了改进。首先,考虑人眼细胞的分布特点,基于人眼分布结构建立目标表观模型来提高跟踪系统抵抗局部遮挡的能力;然后,建立基于自适应目标运动的系统动态模型,提高跟踪算法对快速机动目标的鲁棒性;最后,采用实时更新的系统观测模型,有效避免目标在遇到遮挡、光照变化、剧烈变形等情况下发生的跟踪漂移现象。实验结果表明,本文算法的正确跟踪率可达98%;平均跟踪误差小于6个像元。实验证明本文算法在保证系统跟踪精度要求的同时,具有计算量小、抗干扰能力强等特点。