Traditional Particle Filter Research Articles

パーティクルフィルタとセルオートマトンの組み合わせによる自己位置推定

The purpose of this research is to improve the accuracy of the calculation of localization of a stationary object by combining cellular automata with particle filter. We conducted position estimation experiment of a stationary red object in order to verify of the proposed method. As a result, the error of estimated position decreased compared to the traditional particle filter approach. Since the significant improvement was not obtained, we continue to discuss the combination method of particle filter and cellular automata.

A lead-acid battery's remaining useful life prediction by using electrochemical model in the Particle Filtering framework

Accurate prediction of battery's remaining useful life (RUL) is significant for the reliability and the cost of systems. This paper presents a new Particle Filter (PF) framework for lead-acid battery's RUL prediction by incorporating the battery's electrochemical model. An electrochemical model that simulates the charging and discharging of lead-acid battery is introduced. The effectiveness of both the model and parameter identification is validated through both synthetic and experimental data. In the new PF framework, model parameters that reflect the degradation of battery are seen as state variables, the procedure of capacity simulation and the fitting equations of known state variables are measurement model and process model respectively. Aging experiment is depicted and applied to validate the effectiveness of the method. RUL predictions are made with two different beginning points, the results of which show that the new electrochemical-model-based PF has better state variable stability and prediction accuracy than the traditional data-driven PF.

Fault prognostic of electronics based on optimal multi-order particle filter

The accurate fault prediction is of great importance in electronics high reliability applications for condition based maintenance. Traditional Particle filter (TPF) used for fault prognostic mainly uses the first-order state equation which represents the relationship between the current state and one-step-before state without considering the relation with multi-step-before states. This paper presents an optimal multi-order particle filter method to improve the prediction accuracy. The multiple τth-order state equation is established by training Least Squares Support Vector Regression (LSSVR) via electronics historical failure data, the τ value and LSSVR parameters are optimized through Genetic Algorithm (GA). The optimal τth-order state equation which can really reflect electronics degradation process is used in particle filter to predict the electronics status, remaining useful life (RUL) or other performances. An online update scheme is developed to adapt the optimal τth-order state transformation model to dynamic electronics. The performance of the proposed method is evaluated by using the testing data from CG36A transistor degradation and lithium-ion battery data. Results show that it surpasses classical prediction methods, such as LSSVR, TPF.

Assimilation of satellite chlorophyll measurements into a coupled biophysical model of the Indian Ocean with a guided particle filter

ABSTRACTSatellite observations of surface chlorophyll have been assimilated into a coupled biophysical model of the Indian Ocean with particle filter (PF). Following the approach advocated in an earlier study, we have operated in a low-dimensional error subspace. Two different versions of PF have been implemented. In the traditional PF, the ensemble is augmented with two biological parameters, which are resampled along with state vector, followed by perturbation of the parameters with zero-mean Gaussian noise. In the other version, called guided PF, there is additional guidance of the ensemble towards future observations. While the traditional PF has not been able to outperform the standard run, the guided PF has been able to do so quite emphatically. This superior performance has been reflected in the time series of averaged chlorophyll in two sub-regions as well as in the spatial distribution of averaged chlorophyll in the same two sub-regions.

Object tracking based on Kalman particle filter with LSSVR

In visual tracking field, traditional Kalman particle filter often suffers from the accuracy loss when estimating the target. To alleviate this problem, we propose a novel object tracking method with the fusion of the extended Kalman particle filter (EKPF) and the least squares support vector regression (LSSVR). First, the observation value of Kalman filter is acquired with the cues of color and motion features. The importance probability density function is generated by extended Kalman filter (EKF), which makes the distribution of particles approximately to the posterior probability. And then, a weighted plan is used to determine the weighted coefficient of LSSVR model, the robustness and sparseness of LSSVR modeling will thereby be enhanced. The updated EKF features of tested samples served as training samples to establish the dynamic LSSVR model real-time in the next frame. Finally, the LSSVR is used to calibrate the tracking results of Kalman particle filter, such that the tracking object will always follow the correct motion trajectory. The experimental results show that our method performs favorably against traditional Kalman particle filter with real-time performance and strong robustness.

Online Monitoring and Fault Diagnosis of Hybrid Systems Using Switched Dynamic Bayesian Networks


 
 
 Modern real-world engineering systems typically have hybrid dynamic behaviors that can be modeled by continuous behaviors with discrete mode transitions. These complex systems present many significant challenges for online monitoring and diagnosis, including tracking system behavior, dealing with noisy measurements and disturbances, and diagnosing different types of faults. In this paper, we propose an integrated model-based diagnosis approach that extends the traditional Dynamic Bayesian Network-based particle filter approach for tracking continuous system dynamics. A novel mode diagnoser is presented that discriminates between residuals generated by inaccurate system tracking, discrete faults, and parametric faults. An extended quantitative fault isolation and identification scheme is combined with a qualitative fault isolation scheme to identify the abrupt parametric faults. We demonstrate the effectiveness of our approach by applying it to Reverse Osmosis (RO) subsystem of the Water Recovery System (WRS) developed at the NASA Johnson Space Center for long duration human missions.
 
 

Measuring the Uncertainty of RFID Location Streams Based on Optimal Estimation Particle Filter

Radio Frequency Identification (RFID) technology is widely used in object tracking and tracing, especially in real-time locating system (RTLS). Due to the external and internal influence of RFID systems, a lot of redundant and uncertain location streams could be generated in RFID-based RTLS applications, which could seriously affect the accuracy of estimation for RFID mobile object position and cause great difficulties in RFID-based RTLS applications. In this paper, we systematically analyzed the characteristics of RFID location streams. We then derived the optimal weight for the attributes of RFID location streams by applying information entropy based methods and used probability matrix to optimize weight attributes in location streams. We also proposed an optimal estimation particle filter algorithm (OEPF) based on traditional particle filter, which greatly reduced the data redundancy and realized online measurement for the uncertainty of RFID location streams. Finally, the experimental results showed that, compared to the existing algorithms, our algorithm effectively improved the accuracy of location estimation in ensuring the premise of real-time.

Delayed-State Nonparametric Filtering in Cooperative Tracking

This paper presents a novel nonparametric approach toward delayed-state filtering for cooperative tracking. Standard parametric cooperative localization/tracking approaches are generally aimed at problems that can be easily parameterized and/or are limited to incorporate only real-time measurements. This paper provides a nonparametric yet computationally tractable alternative that is suitable for tracking cases where real-time observations are not always possible, e.g., in a sparse mesh network. The proposed delayed-state cooperative particle filter features forward filtering and backward smoothing to incorporate measurements that are received with time delays. A record of historical marginal states is kept for each mobile node within a sliding time window, instead of the high-dimensional joint state. Essentially, it replaces the importance sampling in traditional particle filters by a Gibbs sampler, which is a Markov chain Monte Carlo method, to fuse all available egocentric and internode relative observations into the global position estimate, thus alleviating the high-dimensionality problems in cooperative tracking. The performance of the proposed approach is evaluated in a multiagent simulation, and experimental results from a large-scale multivehicle industrial operation clearly demonstrate that the proposed approach effectively facilitates the tracking of mobile nodes without position awareness, through the use of relative range, negative detection, and time-delayed measurements.

Integration of GPS precise point positioning and MEMS-based INS using unscented particle filter.

Integration of Global Positioning System (GPS) and Inertial Navigation System (INS) integrated system involves nonlinear motion state and measurement models. However, the extended Kalman filter (EKF) is commonly used as the estimation filter, which might lead to solution divergence. This is usually encountered during GPS outages, when low-cost micro-electro-mechanical sensors (MEMS) inertial sensors are used. To enhance the navigation system performance, alternatives to the standard EKF should be considered. Particle filtering (PF) is commonly considered as a nonlinear estimation technique to accommodate severe MEMS inertial sensor biases and noise behavior. However, the computation burden of PF limits its use. In this study, an improved version of PF, the unscented particle filter (UPF), is utilized, which combines the unscented Kalman filter (UKF) and PF for the integration of GPS precise point positioning and MEMS-based inertial systems. The proposed filter is examined and compared with traditional estimation filters, namely EKF, UKF and PF. Tightly coupled mechanization is adopted, which is developed in the raw GPS and INS measurement domain. Un-differenced ionosphere-free linear combinations of pseudorange and carrier-phase measurements are used for PPP. The performance of the UPF is analyzed using a real test scenario in downtown Kingston, Ontario. It is shown that the use of UPF reduces the number of samples needed to produce an accurate solution, in comparison with the traditional PF, which in turn reduces the processing time. In addition, UPF enhances the positioning accuracy by up to 15% during GPS outages, in comparison with EKF. However, all filters produce comparable results when the GPS measurement updates are available.

Tracking by local structural manifold learning in a new SSIR particle filter

We propose a new object tracking algorithm by local structural manifold learning in a selective sampling importance resampling (SSIR) particle filter framework. A new local structural manifold learning strategy is designed for the invariant appearance modeling in challenging conditions. The appearance of the object which has complex structure in the low-dimensional space is approximated with a set of local structural manifolds. The local structures of the appearance manifold are incrementally learned with changes in the appearance of the object. Unlike traditional particle filters which rely on random re-sampling for new particles generation, we propose a new SSIR particle filter, which integrates an auto-regressive filter to improve the process of samples generation. The distribution of the generated particle samples by our method is better than that of the traditional techniques. Experimental results on several challenging videos demonstrate the robustness and accuracy of our algorithm compared with other recent excellent tracking approaches.

Blended particle methods with adaptive subspaces for filtering turbulent dynamical systems

It is a major challenge throughout science and engineering to improve uncertain model predictions by utilizing noisy data sets from nature. Hybrid methods combining the advantages of traditional particle filters and the Kalman filter offer a promising direction for filtering or data assimilation in high dimensional turbulent dynamical systems. In this paper, blended particle filtering methods that exploit the physical structure of turbulent dynamical systems are developed. Non-Gaussian features of the dynamical system are captured adaptively in an evolving-in-time low dimensional subspace through particle methods, while at the same time statistics in the remaining portion of the phase space are amended by conditional Gaussian mixtures interacting with the particles. The importance of both using the adaptively evolving subspace and introducing conditional Gaussian statistics in the orthogonal part is illustrated here by simple examples. For practical implementation of the algorithms, finding the most probable distributions that characterize the statistics in the phase space as well as effective resampling strategies is discussed to handle realizability and stability issues. To test the performance of the blended algorithms, the forty dimensional Lorenz 96 system is utilized with a five dimensional subspace to run particles. The filters are tested extensively in various turbulent regimes with distinct statistics and with changing observation time frequency and both dense and sparse spatial observations. In real applications perfect dynamical models are always inaccessible considering the complexities in both modeling and computation of high dimensional turbulent system. The effects of model errors from imperfect modeling of the systems are also checked for these methods. The blended methods show uniformly high skill in both capturing non-Gaussian statistics and achieving accurate filtering results in various dynamical regimes with and without model errors.

Gaussian Sum Reapproximation for Use in a Nonlinear Filter

A new method has been developed to approximate one Gaussian sum by another. This algorithm is being developed as part of an effort to generalize the concept of a particle filter. In a traditional particle filter, the underlying probability density function is described by particles: Dirac delta functions with infinitesimal covariances. This paper develops an important component of a more general filter, which uses a Gaussian sum with “fattened” finite-covariance “blobs” (i.e., Gaussian components), which replace infinitesimal particles. The goal of such a filter is to save computational effort by using many fewer Gaussian components than particles. Most of the techniques necessary for this type of filter exist. The one missing technique is a resampling algorithm that bounds the covariance of each Gaussian component while accurately reproducing the original probability distribution. The covariance bounds keep the blobs from becoming too “fat” to ensure low truncation error in extended Kalman filter or unscented Kalman filter calculations. A new resampling algorithm is described, and its performance is studied using two test cases. The new algorithm enables Gaussian sum filter performance that is better than standard nonlinear filters when applied in simulation to a difficult seven-state estimation problem: the new filter’s root mean square error is only 60% higher than the Cramer–Rao lower bound, whereas the next best filter’s root mean square error is 370% higher.

A particle filtering and kernel smoothing-based approach for new design component prognostics

This work addresses the problem of predicting the Remaining Useful Life (RUL) of components for which a mathematical model describing the component degradation is available, but the values of the model parameters are not known and the observations of degradation trajectories in similar components are unavailable. The proposed approach solves this problem by using a Particle Filtering (PF) technique combined with a kernel smoothing (KS) method. This PF–KS method can simultaneously estimate the degradation state and the unknown parameters in the degradation model, while significantly overcoming the problem of particle impoverishment. Based on the updated degradation model (where the unknown parameters are replaced by the estimated ones), the RUL prediction is then performed by simulating future particles evolutions. A numerical application regarding prognostics for Lithium-ion batteries is considered. Various performance indicators measuring precision, accuracy, steadiness and risk of the obtained RUL predictions are computed. The obtained results show that the proposed PF–KS method can provide more satisfactory results than the traditional PF methods.

Pedestrian Motion Tracking and Crowd Abnormal Behavior Detection Based on Intelligent Video Surveillance

Pedestrian tracking and detection of crowd abnormal activity under dynamic and complex background us ing I ntelligent V ideo S urveillance (IVS) system are beneficial for security in public places. T his paper present s a pedestrian tracking method combing Histogram of Oriented Gradients (HOG) detection and particle filter . This method regards the particle filter as the tracking framework, identifies the target area according to the result of HOG detection and modifies particle sampling constantly. Our method can track pedestrians in dynamic backgrounds more accurately compared with the traditional particle filter algorithms. Meanwhile, a method to detect crowd abnormal activity is also proposed based on a model of crowd features using Mixture of Gaussian (MOG). This method calculates features of crowd-interest points, then establishes the crowd features model using MOG, conducts self-adaptive updating and detect s a bnormal activity by matching the input feature with model distribution. Experiments show o ur algorithm can efficiently detect abnormal velocity and escape panic in crowds with a high detection rate and a relatively low false alarm rate

Storage battery remaining useful life prognosis using improved unscented particle filter

Storage battery is one of the most important power sources in portable devices, marine systems, automotive vehicles, aerospace systems, and so on. For this kind of battery, it is essential to prognose its remaining useful life before its end of life, which would reduce some unnecessary sudden disasters caused by battery failure. In this article, we propose an improved unscented particle filter method for prognosing the remaining useful life of storage battery, in which the sigma samples of unscented transformation in traditional unscented particle filter are generated by singular value decomposition, and then, those sigma points are propagated by the standard unscented Kalman filter to generate a sophisticated proposal distribution. When both improved unscented particle filter and unscented particle filter methods were used for prognosing the remaining useful life of storage battery, it shows that the performance of improved unscented particle filter is better than unscented particle filter; the proposed method is more robust in remaining useful life prognosis procedure.

Face Tracking Based on Particle Filtering and α-β-γ Filtering

In view of the traditional particle filter algorithm cannot guarantee effective tracking in the case of target rotation or obscured. The study proposes a tracking method based on α-β-γ filter and particle filter. The algorithm uses α-β-γ filtering prediction position as the next frame image target candidate model of computing center of particle filter algorithm. The algorithm uses α-β-γ filtering prediction position as the next frame image target candidate model of computing center of particle filter. To reduce the number of iterations of particle filter algorithm, strengthen the real-time tracking of moving face. When detect the face is obscured, with α-β-γ filter prediction point as facial movement position, so as to realize the continuity of the movement. The experimental results show that the proposed algorithm improves the traditional particle filter for real-time face tracking, enhancing the ability of anti-occlusion.

Visual Object Tracking Using Fast Three-Dimensional Discrete Cosine Transform

A novel visual object tracking method for color video stream based on traditional particle filter is proposed in this paper. Feature vectors are extracted from coefficient matrices of fast three-dimensional Discrete Cosine Transform (fast 3-D DCT). The feature, as experiment showed, is very robust to occlusion and rotation and it is not sensitive to scale changes. The proposed method is efficient enough to be used in a real-time application. The experiment was carried out on some common used datasets in literature. The results are satisfied and showed the estimated trace follows the target object very closely.

Data Processing with an Innovation Self-Adaptive Denoising Amalgamation Algorithm

The process noise and observation noise of a system are easily disturbed. It’s hard to know its statistic character. This paper proposes an innovation self-adaptive fading UPF algorithm to solve this problem. In the new algorithm, self-adaptive gradually vanishing UKF is used as weightiness density function of particle filter. New observation data is used to modify the error caused by state function of system and noise statistic parameter in time. What’s more, the new algorithm avoids traditional particle filter’s defect that it always gets part optimal solutions. Experiment results indicate that this new algorithm has a higher accuracy and robustness for the changeable noise statistics and non-linear system.

Dynamic multi-cue tracking using particle filter

We present a novel particle filter approach in this paper for robust object tracking using multi-cue association. In contrast to conventional particle trackers that are based on the single space, which does not provide enough information of good foreground/background discrimination, mapping the object into multiple spaces can help to seize the most informative properties of distinguishing the target from background. Moreover, the proposed algorithm commands all the spaces and their corresponding judgments in a global boosting view, which is implemented in an incremental manner to strengthen the ability of separating the target and background classes. The implicit appearance model is then used in updating step of the particle filter to measure the target region. Experimental results on several challenging video sequences have verified that the proposed method is compared very robust and effective with the traditional particle filter in many complicated scenes.

Particle Filter Object Tracking Algorithm Based on Color and Gradient

With the robustness of a single color which is not high in standard particle filter tracking, a fusion of color and gradient particle filter algorithm is proposed. By the advantages of color described the target ’global and gradients described the shape of structure, they are weighted fusion to form a new integrated histogram and applied to the particle filter framework. The experimental results show that compared with the traditional particle filter algorithm, the text of the algorithm can achieve relatively reliable target tracking under complicated background and illumination changes, with better robustness and reliability.