Comparisons of PHD Filter and CPHD Filter for Space Object Tracking
The Probability Hypothesis Density (PHD) filter and the Cardinalized PHD (CPHD) filter are two computationally tractable approximate Bayesian multiobject filters within the Finite Set Statistics framework. The PHD filter estimates the intensity function; the CPHD filter estimates the intensity function and the conditional distribution of the number of objects. The two filters are compared in an example of tracking three space objects, where the CPHD filter is shown to estimate the number of objects as well as the intensity function more accurately.
Y. Cheng et al., "Comparisons of PHD Filter and CPHD Filter for Space Object Tracking," Proceedings of the 2013 AAS/AIAA Astrodynamics Specialist Conference (2013, Hilton Head, SC), vol. 150, pp. 1043-1054, Univelt Inc., Jan 2014.
2013 AAS/AIAA Astrodynamics Specialist Conference (2013: Aug. 11-15, Hilton Head, SC)
Mechanical and Aerospace Engineering
Keywords and Phrases
Estimation; Target tracking; Approximate Bayesian; Cardinalized PHD filter (CPHD); Conditional distribution; CPHD filters; Finite set statistics; Intensity functions; Probability hypothesis density filter; Space objects; Astrophysics
International Standard Book Number (ISBN)
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2014 Univelt Inc., All rights reserved.
This document is currently not available here.