Improved pruning algorithm for Gaussian mixture probability hypothesis density filter

With the increment of the number of Gaussian components, the computation cost increases in the Gaussian mixture probability hypothesis density(GM-PHD) filter. Based on the theory of Chen et al, we propose an improved pruning algorithm for the GM-PHD filter, which utilizes not only the Gaussian components’ means and covariance, but their weights as a new criterion to improve the estimate accuracy of the conventional pruning algorithm for tracking very closely proximity targets. Moreover, it solves the end-less while-loop problem without the need of a second merging step. Simulation results show that this improved algorithm is easier to implement and more robust than the formal ones.

Particle filter with importance density function generated by updated system equation

The current measurement was exploited in a more efficient way. Firstly, the system equation was updated by introducing a correction term, which depends on the current measurement and can be obtained by running a suboptimal filter. Then, a new importance density function(IDF) was defined by the updated system equation. Particles drawn from the new IDF are more likely to be in the significant region of state space and the estimation accuracy can be improved. By using different suboptimal filter, different particle filters(PFs) can be developed in this framework. Extensions of this idea were also proposed by iteratively updating the system equation using particle filter itself, resulting in the iterated particle filter. Simulation results demonstrate the effectiveness of the proposed IDF.

A novel fast classification filtering algorithm for LiDAR point clouds based on small grid density clustering

Clustering filtering is usually a practical method for light detection and ranging(LiDAR)point clouds filtering according to their characteristic attributes.However,the amount of point cloud data is extremely large in practice,making it impossible to cluster point clouds data directly,and the filtering error is also too large.Moreover,many existing filtering algorithms have poor classification results in discontinuous terrain.This article proposes a new fast classification filtering algorithm based on density clustering,which can solve the problem of point clouds classification in discontinuous terrain.Based on the spatial density of LiDAR point clouds,also the features of the ground object point clouds and the terrain point clouds,the point clouds are clustered firstly by their elevations,and then the plane point clouds are selected.Thus the number of samples and feature dimensions of data are reduced.Using the DBSCAN clustering filtering method,the original point clouds are finally divided into noise point clouds,ground object point clouds,and terrain point clouds.The experiment uses 15 sets of data samples provided by the International Society for Photogrammetry and Remote Sensing(ISPRS),and the results of the proposed algorithm are compared with the other eight classical filtering algorithms.Quantitative and qualitative analysis shows that the proposed algorithm has good applicability in urban areas and rural areas,and is significantly better than other classic filtering algorithms in discontinuous terrain,with a total error of about 10%.The results show that the proposed method is feasible and can be used in different terrains.

Kernel density estimation and marginalized-particle based probability hypothesis density filter for multi-target tracking

In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis density filter algorithm based on marginalized particle and kernel density estimation is proposed, which utilizes the idea of marginalized particle filter to enhance the estimating performance of the PHD. The state variables are decomposed into linear and non-linear parts. The particle filter is adopted to predict and estimate the nonlinear states of multi-target after dimensionality reduction, while the Kalman filter is applied to estimate the linear parts under linear Gaussian condition. Embedding the information of the linear states into the estimated nonlinear states helps to reduce the estimating variance and improve the accuracy of target number estimation. The meanshift kernel density estimation, being of the inherent nature of searching peak value via an adaptive gradient ascent iteration, is introduced to cluster particles and extract target states, which is independent of the target number and can converge to the local peak position of the PHD distribution while avoiding the errors due to the inaccuracy in modeling and parameters estimation. Experiments show that the proposed algorithm can obtain higher tracking accuracy when using fewer sampling particles and is of lower computational complexity compared with the PF-PHD.

MULTITARGET STATE AND TRACK ESTIMATION FOR THE PROBABILITY HYPOTHESES DENSITY FILTER

The particle Probability Hypotheses Density (particle-PHD) filter is a tractable approach for Random Finite Set (RFS) Bayes estimation, but the particle-PHD filter can not directly derive the target track. Most existing approaches combine the data association step to solve this problem. This paper proposes an algorithm which does not need the association step. Our basic ideal is based on the clustering algorithm of Finite Mixture Models (FMM). The intensity distribution is first derived by the particle-PHD filter, and then the clustering algorithm is applied to estimate the multitarget states and tracks jointly. The clustering process includes two steps: the prediction and update. The key to the proposed algorithm is to use the prediction as the initial points and the convergent points as the es- timates. Besides, Expectation-Maximization (EM) and Markov Chain Monte Carlo (MCMC) ap- proaches are used for the FMM parameter estimation.

Cubature Kalman probability hypothesis density filter based on multi-sensor consistency fusion

The GM-PHD framework as recursion realization of PHD filter is extensively applied to multitarget tracking system. A new idea of improving the estimation precision of time-varying multi-target in non-linear system is proposed due to the advantage of computation efficiency in this paper. First,a novel cubature Kalman probability hypothesis density filter is designed for single sensor measurement system under the Gaussian mixture framework. Second,the consistency fusion strategy for multi-sensor measurement is proposed through constructing consistency matrix. Furthermore,to take the advantage of consistency fusion strategy,fused measurement is introduced in the update step of cubature Kalman probability hypothesis density filter to replace the single-sensor measurement. Then a cubature Kalman probability hypothesis density filter based on multi-sensor consistency fusion is proposed. Capabilily of the proposed algorithm is illustrated through simulation scenario of multi-sensor multi-target tracking.

Particle filter based on iterated importance density function and parallel resampling

The design, analysis and parallel implementation of particle filter(PF) were investigated. Firstly, to tackle the particle degeneracy problem in the PF, an iterated importance density function(IIDF) was proposed, where a new term associating with the current measurement information(CMI) was introduced into the expression of the sampled particles. Through the repeated use of the least squares estimate, the CMI can be integrated into the sampling stage in an iterative manner, conducing to the greatly improved sampling quality. By running the IIDF, an iterated PF(IPF) can be obtained. Subsequently, a parallel resampling(PR) was proposed for the purpose of parallel implementation of IPF, whose main idea was the same as systematic resampling(SR) but performed differently. The PR directly used the integral part of the product of the particle weight and particle number as the number of times that a particle was replicated, and it simultaneously eliminated the particles with the smallest weights, which are the two key differences from the SR. The detailed implementation procedures on the graphics processing unit of IPF based on the PR were presented at last. The performance of the IPF, PR and their parallel implementations are illustrated via one-dimensional numerical simulation and practical application of passive radar target tracking.

Free clustering optimal particle probability hypothesis density(PHD) filter

As to the fact that it is difficult to obtain analytical form of optimal sampling density and tracking performance of standard particle probability hypothesis density(P-PHD) filter would decline when clustering algorithm is used to extract target states,a free clustering optimal P-PHD(FCO-P-PHD) filter is proposed.This method can lead to obtainment of analytical form of optimal sampling density of P-PHD filter and realization of optimal P-PHD filter without use of clustering algorithms in extraction target states.Besides,as sate extraction method in FCO-P-PHD filter is coupled with the process of obtaining analytical form for optimal sampling density,through decoupling process,a new single-sensor free clustering state extraction method is proposed.By combining this method with standard P-PHD filter,FC-P-PHD filter can be obtained,which significantly improves the tracking performance of P-PHD filter.In the end,the effectiveness of proposed algorithms and their advantages over other algorithms are validated through several simulation experiments.

THE PROBABILITY HYPOTHESIS DENSITY FILTER WITH EVIDENCE FUSION

The original Probability Hypothesis Density (PHD) filter is a tractable algorithm for Multi-Target Tracking (MTT) in Random Finite Set (RFS) frameworks. In this paper,we introduce a novel Evidence PHD (E-PHD) filter which combines the Dempster-Shafer (DS) evidence theory. The proposed filter can deal with the uncertain information,thus it forms target track. We mainly discusses the E-PHD filter under the condition of linear Gaussian. Research shows that the E-PHD filter has an analytic form of Evidence Gaussian Mixture PHD (E-GMPHD). The final experiment shows that the proposed E-GMPHD filter can derive the target identity,state,and number effectively.

Plasma diagnosis of tetrahedral amorphous carbon films by filtered cathodic vacuum arc deposition

Filtered cathodic vacuum arc(FCVA)deposition is regarded as an important technique for the synthesis of tetrahedral amorphous carbon(ta-C)films due to its high ionization rate,high deposition rate and effective filtration of macroparticles.Probing the plasma characteristics of arc discharge contributes to understanding the deposition mechanism of ta-C films on a microscopic level.This work focuses on the plasma diagnosis of an FCVA discharge using a Langmuir dualprobe system with a discrete Fourier transform smoothing method.During the ta-C film deposition,the arc current of graphite cathodes and deposition pressure vary from 30 to 90 A and from 0.3 to 0.9 Pa,respectively.The plasma density increases with arc current but decreases with pressure.The carbon plasma density generated by the arc discharge is around the order of10^(10)cm^(-3).The electron temperature varies in the range of 2-3.5 eV.As the number of cathodic arc sources and the current of the focused magnetic coil increase,the plasma density increases.The ratio of the intensity of the D-Raman peak and G-Raman peak(I_(D)/I_(G))of the ta-C films increases with increasing plasma density,resulting in a decrease in film hardness.It is indicated that the mechanical properties of ta-C films depend not only on the ion energy but also on the carbon plasma density.

Probability density analysis of SINR in massive MIMO systems with matched filter beamformer

This paper derives an approximate formula for probability density function(PDF) of received signal-to-interference-and-noise ratio(SINR) at user terminal when matched filter(MF) is adopted at a base station(BS).This distribution of SINR can be used to make an analysis of average sum-rate,outage probability,and symbol error rate of massive MIMO downlink with MF at BS.From simulation,it is found that the derived approximate analytical expression for PDF of SINR is consistent with the simulated exact PDF from the definition of SINR in medium-scale and large-scale MIMO systems.

多孔介质微观结构对柴油机颗粒捕集器性能影响的模拟探究

为了优化柴油机颗粒捕集器的捕集、压降性能,本文基于孔径概率密度函数和孔隙率分布函数建立了二维柴油机颗粒捕集器孔道微观结构模型,考虑了拦截机理和扩散机理用以计算颗粒在过滤器中的沉积分布情况和捕集效率。计算结果表明:多孔介质微观结构和入口速度对颗粒捕集效率的影响与粒径有关,100 nm粒径颗粒随流速增大初始捕集效率降低最为明显,1000 nm粒径颗粒在不同均匀性的过滤壁下的捕集效率差超过了30%;孔径分布函数方差越大,颗粒就会更多地分布在过滤壁前端,捕集效率也越高,但较大的孔径方差会导致捕集器的初始压降增大和捕集过程结束时的性能出现恶化。

基于PSD特征的FBCCA脑电信号识别方法

当前基于稳态视觉诱发电位(steady-state visual evoked potential,SSVEP)的脑机接口(brain-computer interfaces,BCIs)使用的都是单一识别算法,针对不同时间长度的识别准确率较低。提出了一种基于滤波器组的典型相关分析(filter bank canonical correlation analysis,FBCCA)与功率谱密度(power spectral density,PSD)分析相结合的SSVEP识别算法,可以提高SSVEP识别的普适性与准确率。该方法使用FBCCA寻找高相似度的参考频率信号,再通过多组PSD分析来锁定最终的响应频率,完成频率识别。该方法无需经过训练就能得到较高的识别准确率。实验结果表明:在刺激时长为1 s时,该方法能达到86.61%的准确率,比PSD分析方法提升了5.44%,比典型相关性分析方法(canonical correlation analysis,CCA)提升了10.38%的准确率,比FBCCA提升了8.86%的准确率。

一种新的多机动目标跟踪的GMPHD滤波算法

针对多机动目标跟踪的传统数据关联算法约束条件苛刻、估计精度低、计算量大等问题,提出了一种基于随机集理论的非数据关联的多机动目标跟踪算法.该算法将高斯混合概率假设密度(GMPHD)滤波与"当前"统计模型的优点相结合,绕过了棘手的数据关联问题,能高效处理目标数较大的机动跟踪问题.在漏检、虚警、多机动目标交叉杂波复杂环境下进行了仿真实验,结果表明,该算法具有较高的跟踪精度和稳健的跟踪性能.

基于异常检测的标签噪声过滤框架

噪声是影响机器学习模型可靠性的重要因素,而标签噪声相比特征噪声对模型训练更具决定性的影响。噪声过滤是处理标签噪声的一种有效方法,它不需要估计噪声率,也不需要依赖任何损失函数,然而目前大多数标签噪声过滤算法都会面临过度清洗问题。针对此问题,文中提出了基于异常检测的标签噪声过滤框架,并在此框架下给出了一种自适应近邻聚类的标签噪声过滤算法AdNN(Label Noise Filtering via Adaptive Nearest Neighbor Clustering)。该算法分别考虑分类问题中的每一个类别,把标签噪声检测问题转化成离群点检测问题,识别出每一个类别的离群点,然后根据相对密度去除离群点中的非噪声样本,得到噪声备选集,最后通过噪声因子对噪声备选集中的离群点进行噪声识别和过滤。实验结果表明,在合成数据集和公开数据集上,所提噪声过滤方法可以减轻过度清洗现象,同时能够得到很好的噪声过滤效果和分类预测性能。

基于LGJMS-GMPHDF的多机动目标联合检测、跟踪与分类算法

线性高斯跳变马尔可夫系统模型下的高斯混合概率假设密度滤波器(LGJMS-GMPHDF)为杂波背景下多机动目标跟踪提供了一种有效方法。该文将类别辅助信息引入LGJMS-GMPHDF,提出了一种密集杂波背景下多机动目标联合检测、跟踪与分类算法。该算法在LGJMS-GMPHDF中用属性向量扩展单目标状态向量,用位置和属性的组合测量似然函数代替单目标位置及杂波位置测量似然函数,提高了不同类目标与杂波测量间的鉴别能力,进而改善了目标数目及状态的估计精度;在更新目标状态的同时,对目标属性信息进行更新。该算法实现了时变数目的目标状态和类别估计。杂波背景下交叉和临近并行机动目标的跟踪实验验证了该文算法的联合检测、跟踪与分类性能。

多元假设检验GMPHD轨迹跟踪

由于在军事和民事领域逐步广泛的应用,数目不定的多目标跟踪技术正受到越来越多的关注。概率假设密度(PHD)滤波方法,特别是具有闭式递归的高斯混合概率假设密度(GMPHD)技术,在噪声和漏警等影响下仍能形成优越的群目标跟踪性能。然而PHD滤波器并不能实现多目标航迹跟踪,而其与传统数据互联的结合,复杂度高且跟踪效果不尽如人意。在该文中,各目标的航迹信息以假设形式表述,数据互联则是通过使用经典的多元假设检测方法判决假设矩阵实现。其与GMPHD的结合不仅实现了数据互联和轨迹管理,还因为积累时间信息大大降低了杂波干扰的影响。实验结果证明,该算法可以对多个目标所形成的轨迹实施正确跟踪,同时,计算量的大幅度降低带来了跟踪系统可实现性的提高。

PAC耦合的脑电信号中疲劳特征过滤提纯仿真

脑电信号具有高维度和复杂性,如果筛选出的特征不合理,会导致分析结果存在较大的误差。针对这一问题,研究一种脑电信号中疲劳相关特征过滤提纯方法。针对采集到的脑电信号,利用ICA方法去除其中的伪影,降低非脑电活动所引起的信号的干扰,并通过计算信息增益实现脑电信号中疲劳相关特征过滤。针对过滤出来的功率谱密度以及PAC耦合值特征,通过计算熵值进一步筛选出不同波段的功率谱特征,完成特征提纯。测试结果表明:所研究方法应用提纯得到的功率谱特征+PAC特征输入下,准确率相对较高,且反应时间相对较低,由此说明所研究方法过滤提纯得到的功率谱特征和PAC特征较为合理。

基于粒子群敏度更新的拓扑优化方法

为了进一步减少拓扑优化过程中出现的灰度单元,提出一种基于粒子群优化和分区加权敏度过滤的敏度更新方法。引入粒子群状态更新表达式,以寻找周围单元的敏度极值,将其在一定权重下与经过过滤的敏度值相加,组成新的敏度更新策略。结合变密度法和基于粒子群的敏度更新策略,以柔度最小化为目标,利用5个经典算例验证本文方法的可行性和有效性。优化结果表明,基于粒子群敏度更新的拓扑优化方法能有效减少灰度单元并能快速收敛。