Title :
Particle flow and Monge-Kantorovich transport
Author :
Daum, Fred ; Huang, Jim
Author_Institution :
Raytheon, Woburn, MA, USA
Abstract :
We compare our new particle flow nonlinear filter algorithms with Monge-Kantorovich optimal transport (MKT) algorithms. These two classes of algorithms are the same in several ways, but they differ in computational complexity and the overall intended purpose, as well as differing in several crucial details of the computation and the problem. Moreover, the deep mathematical theory of incompressible particle flow that was developed recently by Shnirelman can be used to provide insight into why our particle flow algorithms work so well.
Keywords :
computational complexity; nonlinear filters; particle filtering (numerical methods); MKT algorithms; Monge-Kantorovich transport algorithm; computational complexity; deep mathematical theory; incompressible particle flow; particle flow nonlinear filter algorithms; Approximation algorithms; Approximation methods; Computational complexity; Equations; Nonlinear filters; Particle filters; Standards; Monge-Kantorovich optimal transport; extended Kalman filter; nonlinear filter; particle filter; particle flow; transport problem;
Conference_Titel :
Information Fusion (FUSION), 2012 15th International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4673-0417-7
Electronic_ISBN :
978-0-9824438-4-2
