Parallel Particle Filter Research Articles

Multi-source term estimation based on parallel particle filtering and dynamic state space in unknown radiation environments

When hazardous sources threaten the environment, source term estimation is a crucial concern. Robotics provides a secure solution to the issue but still encounters challenges in uncertain environments. Rapidly inferring source parameters is a prerequisite for unmanned source search. However, when the number of sources exceeds one, the sensor can only measure the intensity of the coupled field. We propose a novel online multi-radiation source term estimation framework for autonomous source-searching tasks. The method incrementally constructs the state space of Bayesian estimation to adapt to diverse scenarios. Inspired by multi-sensor fusion and particle filtering, this framework employs multi-layer particles and updates them simultaneously to enhance the efficiency of fitting observations. Subsequently, the approach corrects (eliminate and randomly generate) the particles based on Poisson kriging interpolation to prevent particles in redundant layers from interfering with estimation. Furthermore, we compare the performances of our proposed algorithm with those in simulated and real experiments. Various metrics demonstrate that the suggested framework is accurate and robust.

Massively parallel implicit equal-weights particle filter for ocean drift trajectory forecasting

Forecasting of ocean drift trajectories are important for many applications, including search and rescue operations, oil spill cleanup and iceberg risk mitigation. In an operational setting, forecasts of drift trajectories are produced based on computationally demanding forecasts of three-dimensional ocean currents. Herein, we investigate a complementary approach for shorter time scales by using the recently proposed two-stage implicit equal-weights particle filter applied to a simplified ocean model. To achieve this, we present a new algorithmic design for a data-assimilation system in which all components – including the model, model errors, and particle filter – take advantage of massively parallel compute architectures, such as graphical processing units. Faster computations can enable in-situ and ad-hoc model runs for emergency management, and larger ensembles for better uncertainty quantification. Using a challenging test case with near-realistic chaotic instabilities, we run data-assimilation experiments based on synthetic observations from drifting and moored buoys, and analyze the trajectory forecasts for the drifters. Our results show that even sparse drifter observations are sufficient to significantly improve short-term drift forecasts up to twelve hours. With equidistant moored buoys observing only 0.1% of the state space, the ensemble gives an accurate description of the true state after data assimilation followed by a high-quality probabilistic forecast.

Group Importance Sampling for particle filtering and MCMC

Bayesian methods and their implementations by means of sophisticated Monte Carlo techniques have become very popular in signal processing over the last years. Importance Sampling (IS) is a well-known Monte Carlo technique that approximates integrals involving a posterior distribution by means of weighted samples. In this work, we study the assignation of a single weighted sample which compresses the information contained in a population of weighted samples. Part of the theory that we present as Group Importance Sampling (GIS) has been employed implicitly in different works in the literature. The provided analysis yields several theoretical and practical consequences. For instance, we discuss the application of GIS into the Sequential Importance Resampling framework and show that Independent Multiple Try Metropolis schemes can be interpreted as a standard Metropolis–Hastings algorithm, following the GIS approach. We also introduce two novel Markov Chain Monte Carlo (MCMC) techniques based on GIS. The first one, named Group Metropolis Sampling method, produces a Markov chain of sets of weighted samples. All these sets are then employed for obtaining a unique global estimator. The second one is the Distributed Particle Metropolis–Hastings technique, where different parallel particle filters are jointly used to drive an MCMC algorithm. Different resampled trajectories are compared and then tested with a proper acceptance probability. The novel schemes are tested in different numerical experiments such as learning the hyperparameters of Gaussian Processes, two localization problems in a wireless sensor network (with synthetic and real data) and the tracking of vegetation parameters given satellite observations, where they are compared with several benchmark Monte Carlo techniques. Three illustrative Matlab demos are also provided.

A random finite set approach for dynamic occupancy grid maps with real-time application

Grid mapping is a well-established approach for environment perception in robotic and automotive applications. Early work suggests estimating the occupancy state of each grid cell in a robot’s environment using a Bayesian filter to recursively combine new measurements with the current posterior state estimate of each grid cell. This filter is often referred to as binary Bayes filter. A basic assumption of classical occupancy grid maps is a stationary environment. Recent publications describe bottom-up approaches using particles to represent the dynamic state of a grid cell and outline prediction-update recursions in a heuristic manner. This paper defines the state of multiple grid cells as a random finite set, which allows to model the environment as a stochastic, dynamic system with multiple obstacles, observed by a stochastic measurement system. It motivates an original filter called the probability hypothesis density / multi-instance Bernoulli (PHD/MIB) filter in a top-down manner. The paper presents a real-time application serving as a fusion layer for laser and radar sensor data and describes in detail a highly efficient parallel particle filter implementation. A quantitative evaluation shows that parameters of the stochastic process model affect the filter results as theoretically expected and that appropriate process and observation models provide consistent state estimation results.

Real-time data-driven gait phase detection using ground contact force measurements: Algorithms, platform design and performance

Abstract The world is experiencing an unprecedented, enduring, and pervasive aging process. With more people who need walking assistance, the demand for gait rehabilitation has increased rapidly over the years. Effective gait rehabilitation requires a comprehensive gait analysis, in which gait phase detection plays an important role. Although many specialized sensing systems have been developed for gait monitoring, most existing gait phase detection algorithms rely on significant input from medical professionals, which are subjective, manual and inaccurate. To address these problems, this paper presents a data-driven approach for real-time gait phase detection. The approach combines an infinite Gaussian mixture model (IGMM) to classify different gait phases based on the ground contact force (GCF) measurement, and a parallel particle filter to estimate and update the model parameters. Effective particle sharing mechanisms are further designed to distribute particles among different working nodes judiciously and thus strike a good balance between computational overhead and estimation accuracy. The proposed algorithm is implemented in our gait monitoring and analysis platform developed on a VMware cluster. Its estimation accuracy and computational efficiency are examined through extensive experiments using the data traces collected from both healthy human subjects and patients with neurological disorders.

Simultaneous Bayesian Estimation of Excitatory and Inhibitory Synaptic Conductances by Exploiting Multiple Recorded Trials.

Advanced statistical methods have enabled trial-by-trial inference of the underlying excitatory and inhibitory synaptic conductances (SCs) of membrane-potential recordings. Simultaneous inference of both excitatory and inhibitory SCs sheds light on the neural circuits underlying the neural activity and advances our understanding of neural information processing. Conventional Bayesian methods can infer excitatory and inhibitory SCs based on a single trial of observed membrane potential. However, if multiple recorded trials are available, this typically leads to suboptimal estimation because they neglect common statistics (of synaptic inputs (SIs)) across trials. Here, we establish a new expectation maximization (EM) algorithm that improves such single-trial Bayesian methods by exploiting multiple recorded trials to extract common SI statistics across the trials. In this paper, the proposed EM algorithm is embedded in parallel Kalman filters or particle filters for multiple recorded trials to integrate their outputs to iteratively update the common SI statistics. These statistics are then used to infer the excitatory and inhibitory SCs of individual trials. We demonstrate the superior performance of multiple-trial Kalman filtering (MtKF) and particle filtering (MtPF) relative to that of the corresponding single-trial methods. While relative estimation error of excitatory and inhibitory SCs is known to depend on the level of current injection into a cell, our numerical simulations using MtKF show that both excitatory and inhibitory SCs are reliably inferred using an optimal level of current injection. Finally, we validate the robustness and applicability of our technique through simulation studies, and we apply MtKF to in vivo data recorded from the rat barrel cortex.

High-speed parallel particle filter for PCMA signal blind separation

The paper proposes an improved high-speed parallel particle filter algorithm for the blind separation of PCMA-signals by utilizing particle filter’s characteristics of parallelism with the help of a cluster computer system built by using the Matlab distributed computing server and Matlab parallel computing toolbox. The simulation results show that the parallel algorithm can perform the PCMA-signal blind separation quickly and effectively. Further, it can greatly decrease the time of the separation, without reducing the performance of the algorithm, and improve the real-time application of system.

Cooperative parallel particle filters for online model selection and applications to urban mobility

We design a sequential Monte Carlo scheme for the dual purpose of Bayesian inference and model selection. We consider the application context of urban mobility, where several modalities of transport and different measurement devices can be employed. Therefore, we address the joint problem of online tracking and detection of the current modality. For this purpose, we use interacting parallel particle filters, each one addressing a different model. They cooperate for providing a global estimator of the variable of interest and, at the same time, an approximation of the posterior density of each model given the data. The interaction occurs by a parsimonious distribution of the computational effort, with online adaptation for the number of particles of each filter according to the posterior probability of the corresponding model. The resulting scheme is simple and flexible. We have tested the novel technique in different numerical experiments with artificial and real data, which confirm the robustness of the proposed scheme.

Parallel particle filter for tracking road centrelines from high-resolution SAR images using detected road junctions as initial seed points

ABSTRACTAcquiring road junction information is helpful for improving the quality of road network extraction. This article presents a new road network extraction method with three stages. First, road junction candidates are extracted by our previously proposed valley-finding algorithm. Second, numerous particle filters running in parallel track road centrelines starting from all of the detected junction candidates. Finally, the road centrelines are approximated by fitting the tracked centrepoints. The main contribution of this article lies in two aspects. First, road centrepoint tracking routes are launched simultaneously by considering the detected road junctions as starting points, which helps overcome the interference of various obstacles. Second, parallel tracking is implemented by a graphics processing unit (GPU) running accelerated particle filters, which significantly improves the execution time of the road network extraction task. The experimental results show that our proposed method not only handles various obstacles that occur on the roads capably, but also, on average, is 10.5 times as fast as previous methods. We compared the proposed method with two other existing methods in the literature using two different synthetic aperture radar (SAR) images to validate the superior performance of our proposed method.

A resampling method for parallel particle filter architectures

Particle filters are able to represent multi-modal beliefs but require a large number of particles in order to do so. The particle filter consists of three sequential steps: the sampling, the importance factor, and the resampling step. Each step processes every particle in oder to acquire the final state estimation. A high number of particles leads to a high processing time, thus reducing the particle filters usefulness for real-time embedded systems. Through parallelization, the processing time can be significantly reduced. However, the resampling step is not easily parallelizable since it requires the importance factor of each particle. In this work, a resampling scheme is proposed which uses virtual particles to solve the parallelization problem of the resampling component. Besides evaluating its performance against the multinomial resampling scheme, it is also implemented on a Xilinx Zynq-7000 FPGA.

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 measurement-track 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.

An Optimization-Based Parallel Particle Filter for Multitarget Tracking

Particle filters are used in state estimation applications because of their capability to solve nonlinear and non-Gaussian problems effectively. However, they have high computational requirements, especially in the case of multitarget tracking, where data association is the bottleneck. In order to perform data association and estimation together, an augmented state vector, whose dimensions depend on the number of targets, is typically used in particle filters. With data association, the computational load increases exponentially as the number of targets increases. In this case, parallelization is a possibility for achieving real-time feasibility in large-scale multitarget tracking applications. In the work presented here, an optimization-based scheduling algorithm, that is suitable for parallel implementation of particle filter, is presented. This proposed scheduling algorithm minimizes the total computation time for the bus-connected heterogeneous primary-secondary architecture. Further, this scheduler is capable of selecting the optimal number of processors from a large pool of secondary processors and mapping the particles among the selected ones. A new distributed resampling algorithm suitable for parallel computing is also proposed. Furthermore, a less communication-intensive parallel implementation of the particle filter without compromising tracking accuracy using an efficient load balancing technique, in which optimal particle migration among secondary processors is ensured, is presented. Simulation results demonstrate the tracking effectiveness of the new parallel particle filter and the speedup achieved using parallelization.

A new parallel particle filter face tracking method based on heterogeneous system

This paper proposed a multi-cue-based face-tracking algorithm with the supporting framework using parallel multi-core and one Graphic Processing Unit (GPU). Due to illumination and partial-occlusion problems, face tracking usually cannot stably work based on a single cue. Focusing on the above-mentioned problems, we first combined three different visual cues—color histogram, edge orientation histogram, and wavelet feature—under the framework of particle filters to considerably improve tracking performance. Furthermore, an online updating strategy made the algorithm adaptive to illumination changes and slight face rotations. Subsequently, attempting two parallel approaches resulted in real-time responses. However, the computational efficiency decreased considerably with the increase of particles and visual cues. In order to handle the large amount of computation costs resulting from the introduced multi-cue strategy, we explored two parallel computing techniques to speed up the tracking process, especially the most computation-intensive observational steps. One is a multi-core-based parallel algorithm with a MapReduce thread model, and the other is a GPU-based speedup approach. The GPU-based technique uses features-matching and particle weight computations, which have been put into the GPU kernel. The results demonstrate that the proposed face-tracking algorithm can work robustly with cluttered backgrounds and differing illuminations; the multi-core parallel scheme can increase the speed by 2–6 times compared with that of the corresponding sequential algorithms. Furthermore, a GPU parallel scheme and co-processing scheme can achieve a greater increase in speed (8×–12×) compared with the corresponding sequential algorithms.

Multitarget Simultaneous Localization and Mapping of a Sensor Network

This paper addresses the problem of simultaneously localizing multiple targets and estimating the positions of the sensors in a sensor network using particle filters. We develop a new technique called multitarget simultaneous localization and mapping (MSLAM) that has better performance than the well-known FastSLAM when there are several targets in the surveillance area. The proposed algorithm is based on the parallel partition particle filter, especially designed for multiple target tracking, and the truncated unscented Kalman filter for updating the sensors' positions.

Algorithm and Parallel Implementation of Particle Filtering and its Use in Waveform-Agile Sensing

Sequential Monte Carlo particle filters (PFs) are useful for estimating nonlinear non-Gaussian dynamic system parameters. As these algorithms are recursive, their real-time implementation can be computationally complex. In this paper, we analyze the bottlenecks in existing parallel PF algorithms, and propose a new approach that integrates parallel PFs with independent Metropolis---Hastings (PPF-IMH) resampling algorithms to improve root mean-squared estimation error (RMSE) performance. We implement the new PPF-IMH algorithm on a Xilinx Virtex-5 field programmable gate array (FPGA) platform. For a one-dimensional problem with 1,000 particles, the PPF-IMH architecture with four processing elements uses less than 5% of a Virtex-5 FPGA's resource and takes 5.85 μs for one iteration. We also incorporate waveform-agile tracking techniques into the PPF-IMH algorithm. We demonstrate a significant performance improvement when the waveform is adaptively designed at each time step with 6.84 μs FPGA processing time per iteration.

Parallel particle filters for online identification of mechanistic mathematical models of physiology from monitoring data: performance and real-time scalability in simulation scenarios

Combining mechanistic mathematical models of physiology with quantitative observations using probabilistic inference may offer advantages over established approaches to computerized decision support in acute care medicine. Particle filters (PF) can perform such inference successively as data becomes available. The potential of PF for real-time state estimation (SE) for a model of cardiovascular physiology is explored using parallel computers and the ability to achieve joint state and parameter estimation (JSPE) given minimal prior knowledge tested. A parallelized sequential importance sampling/resampling algorithm was implemented and its scalability for the pure SE problem for a non-linear five-dimensional ODE model of the cardiovascular system evaluated on a Cray XT3 using up to 1,024 cores. JSPE was implemented using a state augmentation approach with artificial stochastic evolution of the parameters. Its performance when simultaneously estimating the 5 states and 18 unknown parameters when given observations only of arterial pressure, central venous pressure, heart rate, and, optionally, cardiac output, was evaluated in a simulated bleeding/resuscitation scenario. SE was successful and scaled up to 1,024 cores with appropriate algorithm parametrization, with real-time equivalent performance for up to 10 million particles. JSPE in the described underdetermined scenario achieved excellent reproduction of observables and qualitative tracking of enddiastolic ventricular volumes and sympathetic nervous activity. However, only a subset of the posterior distributions of parameters concentrated around the true values for parts of the estimated trajectories. Parallelized PF's performance makes their application to complex mathematical models of physiology for the purpose of clinical data interpretation, prediction, and therapy optimization appear promising. JSPE in the described extremely underdetermined scenario nevertheless extracted information of potential clinical relevance from the data in this simulation setting. However, fully satisfactory resolution of this problem when minimal prior knowledge about parameter values is available will require further methodological improvements, which are discussed.

Particle Filtering: The Need for Speed

The particle filter (PF) has during the last decade been proposed for a wide range of localization and tracking applications. There is a general need in such embedded system to have a platform for efficient and scalable implementation of the PF. One such platform is the graphics processing unit (GPU), originally aimed to be used for fast rendering of graphics. To achieve this, GPUs are equipped with a parallel architecture which can be exploited for general-purpose computing on GPU (GPGPU) as a complement to the central processing unit (CPU). In this paper, GPGPU techniques are used to make a parallel recursive Bayesian estimation implementation using particle filters. The modifications made to obtain a parallel particle filter, especially for the resampling step, are discussed and the performance of the resulting GPU implementation is compared to the one achieved with a traditional CPU implementation. The comparison is made using a minimal sensor network with bearings-only sensors. The resulting GPU filter, which is the first complete GPU implementation of a PF published to this date, is faster than the CPU filter when many particles are used, maintaining the same accuracy. The parallelization utilizes ideas that can be applicable for other applications.

A parallel histogram-based particle filter for object tracking on SIMD-based smart cameras

We present a parallel implementation of a histogram-based particle filter for object tracking on smart cameras based on SIMD processors. We specifically focus on parallel computation of the particle weights and parallel construction of the feature histograms since these are the major bottlenecks in standard implementations of histogram-based particle filters. The proposed algorithm can be applied with any histogram-based feature sets—we show in detail how the parallel particle filter can employ simple color histograms as well as more complex histograms of oriented gradients (HOG). The algorithm was successfully implemented on an SIMD processor and performs robust object tracking at up to 30 frames per second—a performance difficult to achieve even on a modern desktop computer.

Design and Implementation of Flexible Resampling Mechanism for High-Speed Parallel Particle Filters

There are many applications in which particle filters outperform traditional signal processing algorithms. Some of these applications include tracking, joint detection and estimation in wireless communication, and computer vision. However, particle filters are not used in practice for these applications mainly because they cannot satisfy real-time requirements. This paper presents an efficient resampling architecture for parallel particle filtering. The proposed architecture is flexible such that it supports various modes of parallel resampling operations with up to four processing elements. The resampling algorithm is developed in order to compensate for possible error caused by finite precision quantization in the resampling step. Communication between the processing elements after resampling is identified as an implementation bottleneck, and therefore, concurrent buffering is incorporated in order to speed up communication of particles among processing elements. The flexible resampling mechanism is implemented in 0.35 μ m CMOS process and its complexity and performance are analyzed.