Página 1 dos resultados de 862 itens digitais encontrados em 0.011 segundos

Second Order Filter Distribution Approximations for Financial Time Series with Extreme Outliers

Smith, J. Q.; Santos, António A. F.
Fonte: FEUC. Grupo de Estudos Monetários e Financeiros Publicador: FEUC. Grupo de Estudos Monetários e Financeiros
Tipo: Trabalho em Andamento
Português
Relevância na Pesquisa
56.31%
Particle Filters are now regularly used to obtain the filter distributions associated with state space financial time series. Most commonly used nowadays is the auxiliary particle filter method in conjunction with a first order Taylor expansion of the log-likelihood. We argue in this paper that for series such as stock returns, which exhibit fairly frequent and extreme outliers, filters based on this first order approximation can easily break down. However, an auxiliary particle filter based on the much more rarely used second order approximation appears to perform well in these circumstances. To detach the issue of algorithm design from problems related to model misspecification and parameter estimation, we demonstrate the lack of robustness of the first order approximation and the feasibility of a specific second order approximation using simulated data.

Mice and larvae tracking using a particle filter with an auto-adjustable observation model

PISTORI, Hemerson; ODAKURA, Valguima Victoria Viana Aguiar; MONTEIRO, Joao Bosco Oliveira; GONCALVES, Wesley Nunes; ROEL, Antonia Railda; SILVA, Jonathan de Andrade; MACHADO, Bruno Brandoli
Fonte: ELSEVIER SCIENCE BV Publicador: ELSEVIER SCIENCE BV
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
56.22%
This paper proposes a novel way to combine different observation models in a particle filter framework. This, so called, auto-adjustable observation model, enhance the particle filter accuracy when the tracked objects overlap without infringing a great runtime penalty to the whole tracking system. The approach has been tested under two important real world situations related to animal behavior: mice and larvae tracking. The proposal was compared to some state-of-art approaches and the results show, under the datasets tested, that a good trade-off between accuracy and runtime can be achieved using an auto-adjustable observation model. (C) 2009 Elsevier B.V. All rights reserved.; Dom Bosco Catholic University; Dom Bosco Catholic University; UCDB; UCDB; Foundation of Teaching, Science and Technology Development of Mato Grosso do Sul State; Foundation of Teaching, Science and Technology Development of Mato Grosso do Sul State; FUNDECT; FUNDECT; Brazilian Studies and Projects Funding Body (FINEP); Financiadora de Estudos e Projetos (FINEP); Brazilian National Counsel of Technological and Scientific Development, CNPQ; Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Filtro de partículas adaptativo para o tratamento de oclusões no rastreamento de objetos em vídeos; Adaptive MCMC-particle filter to handle of occlusions in object tracking on videos

Oliveira, Alessandro Bof de
Fonte: Universidade Federal do Rio Grande do Sul Publicador: Universidade Federal do Rio Grande do Sul
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
66.27%
O rastreamento de objetos em vídeos representa um importante problema na área de processamento de imagens, quer seja pelo grande número de aplicações envolvidas, ou pelo grau de complexidade que pode ser apresentado. Como exemplo de aplicações, podemos citar sua utilização em áreas como robótica móvel, interface homem-máquina, medicina, automação de processo industriais até aplicações mais tracionais como vigilância e monitoramento de trafego. O aumento na complexidade do rastreamento se deve principalmente a interação do objeto rastreado com outros elementos da cena do vídeo, especialmente nos casos de oclusões parciais ou totais. Quando uma oclusão ocorre a informação sobre a localização do objeto durante o rastreamento é perdida parcial ou totalmente. Métodos de filtragem estocástica, utilizados para o rastreamento de objetos, como os Filtros de Partículas não apresentam resultados satisfatórios na presença de oclusões totais, onde temos uma descontinuidade na trajetória do objeto. Portanto torna-se necessário o desenvolvimento de métodos específicos para tratar o problema de oclusão total. Nesse trabalho, nós desenvolvemos uma abordagem para tratar o problema de oclusão total no rastreamento de objetos utilizando Filtro de Partículas baseados em Monte Carlo via Cadeia de Markov (MCCM) com função geradora de partículas adaptativa. Durante o rastreamento do objeto...

Rastreando a mão com o filtro de particulas com hierarquia de subespaços; Hand tracking with the subspace hierarchical particle filter

Bruno Cedraz Brandão
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 21/02/2006 Português
Relevância na Pesquisa
46.37%
Nesta dissertação, tratamos o problema de rastrear modelos hierárquicos através de visão computacional no contexto de interfaces gestuais. Gestos formam uma modalidade importante de comunicação humana, e ainda assim, existem poucas, e limitadas, aplicações computacionais com base em gestos. Nosso trabalho é mais uma iniciativa para reverter este quadro. Começamos justificando e discutindo aplicações para a interface visual de gestos da m?ao. Descrevemos os componentes de um sistema de reconhecimento capaz de tornar esta interface possível. Revisamos a teoria Bayesiana da probabilidade, discutimos suas vantagens, os motivos que adiaram sua adoção em larga escala e derivamos, a partir dela, o filtro de partículas. O filtro de partículas pode ser visto como uma solução aproximada para o problema de estimativa de parâmetros. ´E usado, por exemplo, para determinar os ângulos das juntas de um modelo tridimensional da m?ao que melhor caracterizem a pose e posição de uma mão real, gravada em uma seqüência de vídeo. Entretanto, a performance do filtro degrada à medida que aumentamos o número de dimensões do espaço de parâmetros. Nestes casos, um número exponencialmente maior de partículas é necessário para que o filtro convirja...

Rao-Blackwellized particle filter with vector observations for satellite three-axis attitude estimation and control in a simulated testbed

Chagas,Ronan Arraes Jardim; Waldmann,Jacques
Fonte: Sociedade Brasileira de Automática Publicador: Sociedade Brasileira de Automática
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/06/2012 Português
Relevância na Pesquisa
66.42%
A Rao-Blackwellized particle filter has been designed and its performance investigated in a simulated three-axis satellite testbed used for evaluating on-board attitude estimation and control algorithms. Vector measurements have been used to estimate attitude and angular rate and, additionally, a pseudo-measurement based on a low-pass filtered time-derivative of the vector measurements has been proposed to improve the filter performance. Conventional extended and unscented Kalman filters, and standard particle filtering have been compared with the proposed approach to gauge its performance regarding attitude and angular rate estimation accuracy, computational workload, convergence rate under uncertain initial conditions, and sensitivity to disturbances. Though a myriad of filters have been proposed in the past to tackle the problem of spacecraft attitude and angular rate estimation with vector observations, to the best knowledge of the authors the present Rao-Blackwellized particle filter is a novel approach that significantly reduces the computational load, provides an attractive convergence rate, and successfully preserves the performance of the standard particle filter when subjected to disturbances.

Distributed SLAM Using Improved Particle Filter for Mobile Robot Localization

Pei, Fujun; Wu, Mei; Zhang, Simin
Fonte: Hindawi Publishing Corporation Publicador: Hindawi Publishing Corporation
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
46.46%
The distributed SLAM system has a similar estimation performance and requires only one-fifth of the computation time compared with centralized particle filter. However, particle impoverishment is inevitably because of the random particles prediction and resampling applied in generic particle filter, especially in SLAM problem that involves a large number of dimensions. In this paper, particle filter use in distributed SLAM was improved in two aspects. First, we improved the important function of the local filters in particle filter. The adaptive values were used to replace a set of constants in the computational process of importance function, which improved the robustness of the particle filter. Second, an information fusion method was proposed by mixing the innovation method and the number of effective particles method, which combined the advantages of these two methods. And this paper extends the previously known convergence results for particle filter to prove that improved particle filter converges to the optimal filter in mean square as the number of particles goes to infinity. The experiment results show that the proposed algorithm improved the virtue of the DPF-SLAM system in isolate faults and enabled the system to have a better tolerance and robustness.

Particle Filter Design Using Importance Sampling for Acoustic Source Localisation and Tracking in Reverberant Environments

Lehmann, Eric A; Williamson, Robert C
Fonte: SpringerOpen Publicador: SpringerOpen
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
66.34%
Sequential Monte Carlo methods have been recently proposed to deal with the problem of acoustic source localisation and tracking using an array of microphones. Previous implementations make use of the basic bootstrap particle filter, whereas a more general approach involves the concept of importance sampling. In this paper, we develop a new particle filter for acoustic source localisation using importance sampling, and compare its tracking ability with that of a bootstrap algorithm proposed previously in the literature. Experimental results obtained with simulated reverberant samples and real audio recordings demonstrate that the new algorithm is more suitable for practical applications due to its reinitialisation capabilities, despite showing a slightly lower average tracking accuracy. A real-time implementation of the algorithm also shows that the proposed particle filter can reliably track a person talking in real reverberant rooms.; This paper was performed while Eric A. Lehmann was working with National ICT Australia. National ICT Australia is funded by the Australian Government’s Department of Communications, Information Technology, and the Arts, the Australian Research Council, through Backing Australia’s Ability, and the ICT Centre of Excellence programs.

Collaborative information processing techniques for target tracking in wireless sensor networks.

Ma, Hui
Fonte: Universidade de Adelaide Publicador: Universidade de Adelaide
Tipo: Tese de Doutorado
Publicado em //2008 Português
Relevância na Pesquisa
46.43%
Target tracking is one of the typical applications of wireless sensor networks: a large number of spatially deployed sensor nodes collaboratively sense, process and estimate the target state (e.g., position, velocity and heading). This thesis aimed to develop the collaborative information processing techniques that jointly address information processing and networking for the distributive estimation of target state in the highly dynamic and resources constrained wireless sensor networks. Taking into account the interplay between information processing and networking, this thesis proposed a collaborative information processing framework. The framework integrates the information processing which is responsible for the representation, fusion and processing of data and information with networking which caters for the formation of network, the delivery of information and the management of wireless channels. Within the proposed collaborative information processing framework, this thesis developed a suite of target tracking algorithms on the basis of the recursive Bayesian estimation method. For tracking a single target in wireless sensor networks, this thesis developed the sequential extended Kalman filter (S-EKF), the sequential unscented Kalman filter (S-UKF) and the Particle filter (PF). A novel extended Kalman filter and Particle filter hybrid algorithm...

Range-only tracking in multipath environments - an algorithm based on particle filtering

Sathyan, Thuraiappah; Hedley, Mark
Fonte: Institute of Electrical and Electronics Engineers Publicador: Institute of Electrical and Electronics Engineers
Tipo: Conference paper
Publicado em //2009 Português
Relevância na Pesquisa
56.1%
In complex propagation environments with multipath reflections determining the time-of-arrival (TOA) of the line-of-sight (LoS) signal, which is required for localization, is challenging. As a result the localization accuracy of TOA-based systems degrade in such environments. We are pursuing a novel approach where the TOA algorithm returns not one but multiple candidate TOA values as this list is more likely to contain the LoS TOA value and the localization algorithm uses all of these to form a more reliable estimate of the node location. In this paper we present a new algorithm for localization and tracking based on multiple candidate TOA values from each anchor. We show that this is similar to the well-known data association problem in target tracking and exploit this similarity to propose a particle filter based algorithm that has linear computational complexity in the number of anchors. The performance of the algorithm is validated using simulated data.; T. Sathyan, M. Hedley; Extent: 6p.

Neighborhood-based Regularization of Proposal Distribution for Improving Resampling Quality in Particle Filters

Martí, Enrique David; García, Jesús; Molina, José M.
Fonte: IEEE - The Institute Of Electrical And Electronics Engineers, Inc Publicador: IEEE - The Institute Of Electrical And Electronics Engineers, Inc
Tipo: info:eu-repo/semantics/acceptedVersion; info:eu-repo/semantics/conferenceObject; info:eu-repo/semantics/bookPart
Publicado em //2011 Português
Relevância na Pesquisa
56.14%
Particle Filter is a sequential Montecarlo algorithm extensively used for solving estimation problems with non-linear and non-Gaussian features. In spite of its relative simplicity, it is known to suffer some undesired effects that can spoil its performance. Among these problems we can account the one known as sample depletion. This paper reviews the different causes of sample depletion and the many solutions proposed in the existing literature. It also introduces a new strategy for particle resampling which relies in a local linearization of the proposal distribution. The particles drawn using the proposed method are not affected by sample impoverishment and can indirectly lead to better results thanks to a reduction in the plant noise employed, as well to increased performance because of requiring a lower number of particles to achieve same results.; Proceedings of: 14th International Conference on Information Fusion (FUSION 2011). Chicago, Illinois, USA 5-8 July 2011

Maritime UAVs' swarm intelligent robot modelling and simulation using accurate SLAM method and Rao-Blackwellized particle filters

Karimian, H.; Anvar, A.
Fonte: The Modelling and Simulation Society of Aust & NZ; Australia Publicador: The Modelling and Simulation Society of Aust & NZ; Australia
Tipo: Conference paper
Publicado em //2013 Português
Relevância na Pesquisa
56.43%
The objective of this research-study is to explore the performance of Rao-Blackwellized Particle Filters for accurate, simultaneous localization and mapping (SLAM), with Swarm Intelligent network of UAV Robots in oceanic environment. SLAM is a method for Mobile-robots such as Maritime-UAVs Robots which could be valuable and effective to build-up a map on an unknown oceanic–air environment. In this aim, a variety of methods can be implemented and suggested by scientists. The Kalman Filter, Extended Kalman Filter, and Particle Filter are well known and popular algorithm techniques. Each of the named methods, are able to investigate on SLAM problem but may have some drawbacks, with working under some assumptions, that are not always true. As an example Extended Kalman filter estimates covariance matrix, that tends to underestimate the true covariance matrix, therefore it risks becoming inconsistent in the statistical sense. Therefore, to get a good and accurate result, it is necessary to combine several methods together. That is included with Rao-Blackwellized method, with ability to construct Particle Filter and Extended Kalman Filter for SLAM scenarios. The Particle Filter technique is responsible for estimating Robot’s pose as the Extended-Kalman-Filter estimates the landmarks. Generally in marine applications UAVs are used for search and rescue mission(s)...

Particle filter design using importance sampling for environments

Lehmann, Eric A.; Williamson, Robert
Fonte: Hindawi Publishing Corporation Publicador: Hindawi Publishing Corporation
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
56.1%
Sequential Monte Carlo methods have been recently proposed to deal with the problem of acoustic source localisation and tracking using an array of microphones. Previous implementations make use of the basic bootstrap particle filter, whereas a more genera

A Stable Particle Filter in High-Dimensions

Beskos, Alex; Crisan, Dan; Jasra, Ajay; Kamatani, Kengo; Zhou, Yan
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 10/12/2014 Português
Relevância na Pesquisa
46.45%
We consider the numerical approximation of the filtering problem in high dimensions, that is, when the hidden state lies in $\mathbb{R}^d$ with $d$ large. For low dimensional problems, one of the most popular numerical procedures for consistent inference is the class of approximations termed particle filters or sequential Monte Carlo methods. However, in high dimensions, standard particle filters (e.g. the bootstrap particle filter) can have a cost that is exponential in $d$ for the algorithm to be stable in an appropriate sense. We develop a new particle filter, called the \emph{space-time particle filter}, for a specific family of state-space models in discrete time. This new class of particle filters provide consistent Monte Carlo estimates for any fixed $d$, as do standard particle filters. Moreover, we expect that the state-space particle filter will scale much better with $d$ than the standard filter. We illustrate this analytically for a model of a simple i.i.d. structure and one of a Markovian structure in the $d$-dimensional space-direction, when we show that the algorithm exhibits certain stability properties as $d$ increases at a cost $\mathcal{O}(nNd^2)$, where $n$ is the time parameter and $N$ is the number of Monte Carlo samples...

Comparison of SCIPUFF Plume Prediction with Particle Filter Assimilated Prediction for Dipole Pride 26 Data

Terejanu, Gabriel; Cheng, Yang; Singh, Tarunraj; Scott, Peter D.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/07/2011 Português
Relevância na Pesquisa
46.39%
This paper presents the application of a particle filter for data assimilation in the context of puff-based dispersion models. Particle filters provide estimates of the higher moments, and are well suited for strongly nonlinear and/or non-Gaussian models. The Gaussian puff model SCIPUFF, is used in predicting the chemical concentration field after a chemical incident. This model is highly nonlinear and evolves with variable state dimension and, after sufficient time, high dimensionality. While the particle filter formalism naturally supports variable state dimensionality high dimensionality represents a challenge in selecting an adequate number of particles, especially for the Bootstrap version. We present an implementation of the Bootstrap particle filter and compare its performance with the SCIPUFF predictions. Both the model and the Particle Filter are evaluated on the Dipole Pride 26 experimental data. Since there is no available ground truth, the data has been divided in two sets: training and testing. We show that even with a modest number of particles, the Bootstrap particle filter provides better estimates of the concentration field compared with the process model, without excessive increase in computational complexity.; Comment: The Chemical and Biological Defense Physical Science and Technology Conference...

The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems

Wüthrich, Manuel; Bohg, Jeannette; Kappler, Daniel; Pfreundt, Claudia; Schaal, Stefan
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/05/2015 Português
Relevância na Pesquisa
46.4%
Parametric filters, such as the Extended Kalman Filter and the Unscented Kalman Filter, typically scale well with the dimensionality of the problem, but they are known to fail if the posterior state distribution cannot be closely approximated by a density of the assumed parametric form. For nonparametric filters, such as the Particle Filter, the converse holds. Such methods are able to approximate any posterior, but the computational requirements scale exponentially with the number of dimensions of the state space. In this paper, we present the Coordinate Particle Filter which alleviates this problem. We propose to compute the particle weights recursively, dimension by dimension. This allows us to explore one dimension at a time, and resample after each dimension if necessary. Experimental results on simulated as well as real data confirm that the proposed method has a substantial performance advantage over the Particle Filter in high-dimensional systems where not all dimensions are highly correlated. We demonstrate the benefits of the proposed method for the problem of multi-object and robotic manipulator tracking.

Feedback Particle Filter

Yang, Tao; Mehta, Prashant G.; Meyn, Sean P.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 26/02/2013 Português
Relevância na Pesquisa
46.37%
A new formulation of the particle filter for nonlinear filtering is presented, based on concepts from optimal control, and from the mean-field game theory. The optimal control is chosen so that the posterior distribution of a particle matches as closely as possible the posterior distribution of the true state given the observations. This is achieved by introducing a cost function, defined by the Kullback-Leibler (K-L) divergence between the actual posterior, and the posterior of any particle. The optimal control input is characterized by a certain Euler-Lagrange (E-L) equation, and is shown to admit an innovation error-based feedback structure. For diffusions with continuous observations, the value of the optimal control solution is ideal. The two posteriors match exactly, provided they are initialized with identical priors. The feedback particle filter is defined by a family of stochastic systems, each evolving under this optimal control law. A numerical algorithm is introduced and implemented in two general examples, and a neuroscience application involving coupled oscillators. Some preliminary numerical comparisons between the feed- back particle filter and the bootstrap particle filter are described.

Variance estimation and allocation in the particle filter

Lee, Anthony; Whiteley, Nick
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/09/2015 Português
Relevância na Pesquisa
46.38%
We introduce estimators of the variance and weakly consistent estimators of the asymptotic variance of particle filter approximations. These estimators are defined using only a single realization of a particle filter, and can therefore be used to report estimates of Monte Carlo error together with such approximations. We also provide weakly consistent estimators of individual terms appearing in the asymptotic variance, again using a single realization of a particle filter. When the number of particles in the particle filter is allowed to vary over time, the latter permits approximation of their asymptotically optimal allocation. Some of the estimators are unbiased, and hence generalize the i.i.d. sample variance to the non-i.i.d. particle filter setting.

The iterated auxiliary particle filter

Guarniero, Pieralberto; Johansen, Adam M.; Lee, Anthony
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/11/2015 Português
Relevância na Pesquisa
46.41%
We present an offline, iterated particle filter to facilitate statistical inference in general state space hidden Markov models. Given a model and a sequence of observations, the associated marginal likelihood L is central to likelihood-based inference for unknown statistical parameters. We define a class of "twisted" models: each member is specified by a sequence of positive functions psi and has an associated psi-auxiliary particle filter that provides unbiased estimates of L. We identify a sequence psi* that is optimal in the sense that the psi*-auxiliary particle filter's estimate of L has zero variance. In practical applications, psi* is unknown so the psi*-auxiliary particle filter cannot straightforwardly be implemented. We use an iterative scheme to approximate psi*, and demonstrate empirically that the resulting iterated auxiliary particle filter significantly outperforms the bootstrap particle filter in challenging settings. Applications include parameter estimation using a particle Markov chain Monte Carlo algorithm.

Joint Probabilistic Data Association-Feedback Particle Filter for Multiple Target Tracking Applications

Yang, Tao; Huang, Geng; Mehta, Prashant G.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 05/03/2013 Português
Relevância na Pesquisa
46.38%
This paper introduces a novel feedback-control based particle filter for the solution of the filtering problem with data association uncertainty. The particle filter is referred to as the joint probabilistic data association-feedback particle filter (JPDA-FPF). The JPDA-FPF is based on the feedback particle filter introduced in our earlier papers. The remarkable conclusion of our paper is that the JPDA-FPF algorithm retains the innovation error-based feedback structure of the feedback particle filter, even with data association uncertainty in the general nonlinear case. The theoretical results are illustrated with the aid of two numerical example problems drawn from multiple target tracking applications.; Comment: In Proc. of the 2012 American Control Conference

Combining Particle Filter and Population-based Metaheuristics for Visual Articulated Motion Tracking

Pantrigo, Juan José; Sánchez, Ángel; Gianikellis, Kostas; Montemayor, Antonio S.
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2005 Português
Relevância na Pesquisa
66.41%
Visual tracking of articulated motion is a complex task with high computational costs. Because of the fact that articulated objects are usually represented as a set of linked limbs, tracking is performed with the support of a model. Model-based tracking allows determining object pose in an effortless way and handling occlusions. However, the use of articulated models generates a multidimensional state-space and, therefore, the tracking becomes computationally very expensive or even infeasible. Due to the dynamic nature of the problem, some sequential estimation algorithms like particle filters are usually applied to visual tracking. Unfortunately, particle filter fails in high dimensional estimation problems such as articulated objects or multiple object tracking. These problems are called \emph{dynamic optimization problems}. Metaheuristics, which are high level general strategies for designing heuristics procedures, have emerged for solving many real world combinatorial problems as a way to efficiently and effectively exploring the problem search space. Path relinking (PR) and scatter search (SS) are evolutionary metaheuristics successfully applied to several hard optimization problems. PRPF and SSPF algorithms respectively hybridize both...