Tracking Multiple Spawning Targets Using Poisson Multi-Bernoulli Mixtures on Sets of Tree Trajectories

This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter on the space of sets tree trajectories for multiple target tracking with spawning targets. A trajectory contains all information and its descendants, which appear due to process. Each set branches, where each branch has or one descendants genealogy. For standard dynamic measurement models spawning, posterior is PMBM density, Bernoulli having potential trajectory. To enable computationally efficient implementation, we derive an approximate in obtained by minimising Kullback-Leibler divergence. The resulting improves performance state-of-the-art algorithms simulated scenario.