An Alternative Derivation of the Cardinalized Probability Hypothesis Density Filter
In this report, an alternative approach to derive the Gaussian mixture cardinalized probability hypothesis density (GM-CPHD) filter is presented. The derivations differ in that the presented ones are based on "ordinary" statistics, while the original GM-CPHD derivation started from the finite set statistics (FISST) description of the CPHD filter. The results of the derivations are compared with filter update equations presented in another paper. The sets of equations are not completely equivalent. However, initial performance evaluations of the approaches indicate similar performance. Future work is needed to understand the differences between different GM-CPHD filter equations.