Trajectory Poisson multi-Bernoulli filters

Abstract

This paper presents two trajectory Poisson multi-Bernoulli (TPMB) filters for multi-target tracking: one to estimate the set of alive trajectories at each time step and another to estimate the set of all trajectories, which includes alive and dead trajectories, at each time step. The filters are based on propagating a Poisson multi-Bernoulli (PMB) density on the corresponding set of trajectories through the filtering recursion. After the update step, the posterior is a PMB mixture (PMBM) so, in order to obtain a PMB density, a Kullback-Leibler divergence minimisation on an augmented space is performed. The developed filters are computationally lighter alternatives to the trajectory PMBM filters, which provide the closed-form recursion for sets of trajectories with Poisson birth model, and are shown to outperform previous multi-target tracking algorithms.

arXiv commentMatlab code is provided at https://github.com/Agarciafernandez/MTT

References in corpus (12)

• Marginal multi-Bernoulli filters: RFS derivation of MHT, JIPDA and association-based MeMBer
• Poisson multi-Bernoulli mixture filter: direct derivation and implementation
• Poisson multi-Bernoulli conjugate prior for multiple extended object filtering
• Approximate evaluation of marginal association probabilities with belief propagation
• Generalized Multiple Importance Sampling
• Multiple target tracking based on sets of trajectories
• An efficient, variational approximation of the best fitting multi-Bernoulli filter
• A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithms
• Trajectory PHD and CPHD filters
• Hybrid Poisson and multi-Bernoulli filters
• A track-before-detect labelled multi-Bernoulli particle filter with label switching
• Multi-Scan Implementation of the Trajectory Poisson Multi-Bernoulli Mixture Filter

Cited by in corpus (11)

• Fusion of labeled RFS densities with minimum information loss
• A Poisson multi-Bernoulli mixture filter for coexisting point and extended targets
• Poisson multi-Bernoulli mixture filter with general target-generated measurements and arbitrary clutter
• Continuous-discrete multiple target tracking with out-of-sequence measurements
• Tracking multiple spawning targets using Poisson multi-Bernoulli mixtures on sets of tree trajectories
• Data-driven clustering and Bernoulli merging for the Poisson multi-Bernoulli mixture filter
• Poisson Multi-Bernoulli Mixtures for Sets of Trajectories
• Multiple Object Trajectory Estimation Using Backward Simulation
• Gaussian multi-target filtering with target dynamics driven by a stochastic differential equation
• Distributed Poisson multi-Bernoulli filtering via generalised covariance intersection
• Poisson multi-Bernoulli mixture filter for trajectory measurements