Particle methods have been recently proposed to deal with the nonlinear filtering problem. These are Monte Carlo methods that can provide a nonparametric approximation to the signal conditional distribution even in nonlinear and non Gaussian cases, without depending on the state space dimension. In this article, we present a new version of regularized particle filter using a progressive correction (PC) principle which improves the appron'mation, in introducing a decreasing sequence of (fictitious) variance matrices for the observation noise. This method i s applied to the multisensor tracking problem (mdar and IR sensor) and compared to the classical regularized particle filter and the EKF.
Paper We2.1.2International audienceParticle filtering is a widely used Monte Carlo method to approximate the posterior density in non-linear filtering. Unlike the Kalman filter, the particle filter deals with non-linearity, multi-modality or non Gaussianity. However, recently, it has been observed that particle filtering can be inefficient when the dimension of the system is high. We discuss the effect of dimensionality on the Monte Carlo error and we analyze it in the case of a linear tracking model. In this case, we show that this error increases exponentially with the dimension
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.