Target tracking may be modeled as a state estimation problem which consists of two models, the state transition model which shows how the different states of the target such as position, velocity etc. are evolving with respect to time and the measurement model which relates the current state with the current observations. When the model is linear and the noise associated with the model is Gaussian then Kalman Filter (KF) may be applied. The marginalized particle filter (MPF) is considered to be an efficient state estimation technique, which is applicable when there is a linear Gaussian substructure present in the model. The MPF consists of both Kalman filter (KF) and particle filter (PF).

Papers:

Rong Li X, Vesselin P J. Survey of Maneuvering Target Tracking. Part II : Motion Models of Ballistic and Space Targets. IEEE Trans on Aerospace and Electronic Systems 2010; 46(1): 96-119.

Kalane Prasad. Target Tracking Using Kalman Filter. International Journal of Science & Technology 2012; 2 (2): 16-24.

Hayes H Monson. Statistical Digital Signal Processing and Modelling. John Wiley & Sons: 1996; 371–378.