Sanjeev Arulampalam

Learn More
The conventional GMPHD/CPHD filters require the PHD for target births to be a Gaussian mixture, which is potentially inefficient because careful selection of the mixture parameters may be required to ensure good performance. Here we present approximations which allow part of the birth PHD to be uniformly distributed, obviating the need to use large Gaussian(More)
The standard Gaussian Mixture Probability Hypothesis Density (GMPHD) filter and Cardinalised Probability Hypothesis Density (GMCPHD) filter require the target birth model to take the form of a Gaussian mixture. Although any density (including a uniform density), can be approximated using a sum of Gaussians, this can be inefficient in practice, especially(More)
The generalized labeled multi-Bernoulli (GLMB) is a family of tractable models that alleviates the limitations of the Poisson family in dynamic Bayesian inference of point processes. In this paper, we derive closed form expressions for the void probability functional and the Cauchy–Schwarz divergence for GLMBs. The proposed analytic void probability(More)
In this paper, we propose a method for optimal stochastic sensor control, where the goal is to minimise the estimation error in multi-object tracking scenarios. Our approach is based on an information theoretic divergence measure between labelled random finite set densities. The multi-target posteriors are generalised labelled multi-Bernoulli (GLMB)(More)
This paper considers the angle-only filtering problem in 3D using bearing and elevation angle measurements from a single maneuvering sensor. We develop continuous-discrete extended Kalman filter (EKF) based algorithms using modified spherical coordinates (MSC) and log spherical coordinates (LSC), where the dynamic and measurement models are described in(More)
In this paper, Joint Integrated Probabilistic Data Association Filter (JIPDAF) and Sequential Sampling Particle Filter with Existence (SSPFE) trackers are applied to the problem of multitarget multistatic sonar tracking. The performance of these algorithms is compared using the recent benchmark Passive and Active Contact Simulator (PACsim) data sets. JIPDAF(More)
We compare the performance of the extended Kalman filter (EKF), unscented Kalman filter (UKF), and particle filter (PF) for the angle-only filtering problem in 3D using bearing and elevation measurements from a single maneuvering sensor. These nonlinear filtering algorithms use discrete-time dynamic and measurement models. Two types of coordinate systems(More)