Derivation of the PHD and CPHD Filters Based on Direct Kullback–Leibler Divergence Minimization
- 14 August 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 63 (21) , 5812-5820
Abstract
In this paper, we provide novel derivations of the probability hypothesis density (PHD) and cardinalised PHD (CPHD) filters without using probability generating functionals or functional derivatives. We show that both the PHD and CPHD filters fit in the context of assumed density filtering and implicitly perform Kullback-Leibler divergence (KLD) minimizations after the prediction and update steps. We perform the KLD minimizations directly on the multitarget prediction and posterior densities.Keywords
Funding Information
- Australian Research Council (DP130104404)
This publication has 30 references indexed in Scilit:
- Integrated Tracking, Classification, and Sensor Management2014
- Analysis of Kalman Filter Approximations for Nonlinear MeasurementsIEEE Transactions on Signal Processing, 2013
- A CPHD Filter for Tracking With Spawning ModelsIEEE Journal of Selected Topics in Signal Processing, 2013
- Particle Filters for Random Set Models2013
- Adaptive Target Birth Intensity for PHD and CPHD FiltersIEEE Transactions on Aerospace and Electronic Systems, 2012
- Fundamentals of Object Tracking2011
- CPHD Filtering With Unknown Clutter Rate and Detection ProfileIEEE Transactions on Signal Processing, 2011
- "Spooky Action at a Distance" in the Cardinalized Probability Hypothesis Density FilterIEEE Transactions on Aerospace and Electronic Systems, 2009
- Analytic Implementations of the Cardinalized Probability Hypothesis Density FilterIEEE Transactions on Signal Processing, 2007
- Gaussian particle filteringIEEE Transactions on Signal Processing, 2003