April 2015
Intermediate to advanced
1062 pages
40h 35m
English
In this chapter, sequential sampling techniques are considered. Kalman filtering is viewed in terms of probabilistic arguments as a special case of a linear dynamic system, where the involved variables follow Gaussian distributions. Particle filtering techniques are then considered as a vehicle to treat more general nonlinear models and/or non-Gaussian random variables. They are introduced as a special instance of the more general family of sequential sampling methods. Different schemes are discussed such as the generic particle and the auxiliary particle filtering algorithms.
Keywords
Sequential importance sampling
Kalman filtering
Particle filtering
Resampling
Degeneracy
Generic particle filters