Bayesian Smoothing for the Extended Object Random Matrix Model
Artikel i vetenskaplig tidskrift, 2019

The random matrix model is popular in extended object tracking, due to its relative simplicity and versatility. In this model, the extended object state consists of a kinematic vector for the position and motion parameters (velocity, etc.), and an extent matrix. Two versions of the model can be found in the literature, one where the state density is modeled by a conditional density, and one where the state density is modeled by a factorized density. In this paper, we present closed-form Bayesian smoothing expressions for both the conditional and the factorized model. In a simulation study, we compare the performance of different versions of the smoother. Code is published on GitHub.

smoothing

inverse Wishart

random matrix

Wishart

Extended object tracking

Gaussian

Författare

Karl Granström

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Signalbehandling

Jakob Bramstång

Knightec AB

Student vid Chalmers

IEEE Transactions on Signal Processing

1053-587X (ISSN)

Vol. 67 14 3732-3742 8728053

Ämneskategorier

Beräkningsmatematik

Sannolikhetsteori och statistik

Reglerteknik

DOI

10.1109/TSP.2019.2920471

Mer information

Senast uppdaterat

2019-10-16