Particle Filter Methods for Space Object Tracking


An approach for space object tracking utilizing particle filters is presented. New meth-ods are developed and used to construct a robust constrained admissible region given a set of angles-only measurements, which is then approximated by a finite mixture distri-bution. This probabilistic initial orbit solution is refined using subsequent measurements through a particle filter approach. A proposal density is constructed based on an approxi-mate Bayesian update and samples, or particles, are drawn from this proposed probability density to assign and correct weflights, which form the basis for a more accurate Bayesian update. A finite mixture distribution is then fit to these weflighted samples to reinitialize the cycle. This approach is compared to methods that approximate all probability densities as finite mixtures and process them as such. Both approaches utilize recursive estimation based on Bayesian statistics, but the benefits of densely sampling the support probabil-ity based on incoming measurements is weighed against remaining solely within the finite mixture approximation and performing measurement corrections there.

Meeting Name

AIAA/AAS Astrodynamics Specialist Conference (2014: Aug, 4- 7, San Diego, CA)


Mechanical and Aerospace Engineering

Keywords and Phrases

Astrophysics; Distributed computer systems; Mixtures; Probability density function; Signal filtering and prediction; Target tracking; Admissible regions; Bayesian statistics; Finite mixture distribution; Finite mixtures; Measurement corrections; Particle filter; Probability densities; Recursive estimation; Monte Carlo methods

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version


File Type





© 2014 American Institute of Aeronautics and Astronautics (AIAA), All rights reserved.

Publication Date

01 Aug 2014

This document is currently not available here.