Native Matlab MHT based on MeMBer-Poisson factorization

A simple implementation of Multiple Hypothesis Tracking

The zip-file contains m-files for an implementation of Multiple Hypothesis Tracking in accordance with the random finite set formulation of the multitarget Bayes filter. The main reference underlying the method is
Brekke, E. & Chitre, M.: "The multiple hypothesis tracker derived from finite set statistics", Proc. Fusion 2017.

which again is based on

Williams, J.: "Marginal multi-Bernoulli filters: RFS derivation of MHT, JIPDA, and association-based MeMBer", IEEE Transactions on Aerospace and Electronic Systems, 2015, vol. 51, pp. 1664-1687.

The program (executed by running script_mbmp_mht01.m) is developed with the purpose of testing some of the bounds developed in

Devijver, P. A.: "On a New Class of Bounds on Bayes Risk in Multihypothesis Pattern Recognition", IEEE Transactions on Computers, 1974, Vol. 23, pp. 70-80.

This is a very simple MHT implementation that is fully hypothesis-oriented and which only uses pruning operations (and no clustering/merging) to mitigate complexity. It has been tested for scenarios involving up to 4 targets and 10 time steps. The main benefit of the implementation is that it is 100% Matlab and therefore does not require any compilation. At the core of the program is an implementation of Murty's method which originally was written by Umut Orguner.