The CPHD filter with target spawning

Daniel S. Bryant (1) , Emmanuel Delande (2) , Steven Gehly (1) , Jeremie Houssineau (2) , Daniel E Clark (2) , Brandon Jones (1)

1 Department of Aerospace Engineering Sciences
2 HWU - Heriot-Watt University [Edinburgh]

In its classical form, the cardinalized probability hypothesis density (CPHD) filter does not model the appearance of new targets through spawning, yet there are applications for which spawning models more appropriately account for newborn objects when compared to spontaneous birth models. In this paper, we propose a principled derivation of the CPHD filter prediction step including spontaneous birth and spawning. A Gaussian Mixture implementation of the CPHD filter with spawning is then presented, illustrated with three applicable spawning models on a simulated scenario involving two parent targets spawning a total of five objects

Mots clés: Target spawning; Multi-object filtering; Cardinalized probability hypothesis density (CPHD) filter; Point processes; Random finite sets; Bayesian estimation; Target tracking

Domaines: Traitement du signal et de l'image [eess.SP]

Daniel S. Bryant, Emmanuel Delande, Steven Gehly, Jeremie Houssineau, Daniel E Clark, et al.. The CPHD filter with target spawning. IEEE Transactions on Signal Processing, 2017, 65 (5), pp.1324-1338. ⟨10.1109/TSP.2016.2597126⟩. ⟨hal-01730369⟩