Spatiotemporal Constraints for Sets of Trajectories with Applications to PMBM Densities

@article{Granstrom2020SpatiotemporalCF,
  title={Spatiotemporal Constraints for Sets of Trajectories with Applications to PMBM Densities},
  author={Karl Granstrom and Lennart Svensson and Yuxuan Xia and {\'A}ngel F. Garc{\'i}a-Fern{\'a}ndez and Jason L. Williams},
  journal={2020 IEEE 23rd International Conference on Information Fusion (FUSION)},
  year={2020},
  pages={1-8},
  url={https://api.semanticscholar.org/CorpusID:211572604}
}
This paper introduces spatiotemporal constraints for trajectories, and shows that if the unconstrained set of trajectories density is PMBM, then the constrained density is also PMBM.
[PDF] Semantic Reader

Figures from this paper

6 Citations

Poisson Multi-Bernoulli Mixtures for Sets of Trajectories

This article shows that the PMBM density is also conjugate for sets of trajectories with the standard point target measurement model, and establishes that the density of the set of trajectories in any time window, given the measurements in a possibly different time window, is also a PMBM.

Continuous-Discrete Multiple Target Tracking With Out-of-Sequence Measurements

The optimal Bayesian processing of an out-of-sequence (OOS) set of measurements in continuoustime for multiple target tracking is derived via the continuous-discrete trajectory Poisson multi-Bernoulli mixture (TPMBM) filter.

The PHD/CPHD filter for Multiple Extended Target Tracking with Trajectory Set Theory and Explicit Shape Estimation

Two proposed algorithms for tracking multiple extended targets or unresolved group targets with elliptical extent shape have advantages over existing algorithms in target shape estimation, as well as in the completeness and accuracy of target trajectory generation.

Innovative Filter for Nonlinear Multitarget Tracking: Improved SCKF-GM-DLPMBM Filter and Its Implementation

The dual-label PMBM (DLPMBM) filter is enhanced by incorporating labels for both measurements and targets, and an implementation of the Gaussian mixture DLPMBM filter using the square-root cubature Kalman filter (SCKF).

Joint One-Hop Flooding Communication and Event-Triggered Distributed Trajectory Fusion in Spatiotemporal Constraint Sensor Networks

This work proposes a novel distributed trajectory fusion (DTF) method, which incorporates Gaussian mixture approximated trajectory Poisson multi-Bernoulli filter with spatiotemporal constraints to accurately capture the expected target movements as they enter the area of interest.

Robust Model-Dependent Poisson Multi Bernoulli Mixture Trackers for Multistatic Sonar Networks

The adaptive measurement-driven birth process improves the robustness of the track initiation, the multistatic acoustic model-dependent probability of detection advances the track continuity through the transition regions, and these contributions make the PMBM tracker robust in terms of tracker performance in challenging underwater environments and acoustic transition regions.

25 References

Poisson Multi-Bernoulli Mixtures for Sets of Trajectories

This article shows that the PMBM density is also conjugate for sets of trajectories with the standard point target measurement model, and establishes that the density of the set of trajectories in any time window, given the measurements in a possibly different time window, is also a PMBM.

Poisson Multi-Bernoulli Mixture Trackers: Continuity Through Random Finite Sets of Trajectories

A recently developed formulation of the multi-target tracking problem as a random finite set (RFS) of trajectories, and derives two trajectory RFS filters, called PMBM trackers, which efficiently estimate the set of trajectory, and share hypothesis structure with the PMBM filter.

Extended target Poisson multi-Bernoulli mixture trackers based on sets of trajectories

Two trajectory RFS filters for extended target tracking, called extended target PMBM trackers, are derived based on sets on targets and explicit track continuity between time steps is provided.

An Implementation of the Poisson Multi-Bernoulli Mixture Trajectory Filter via Dual Decomposition

The proposed implementation of the Poisson multi-Bernoulli mixture trajectory filter performs track-oriented N-scan pruning to limit complexity, and uses dual decomposition to solve the involved multi-frame assignment problem.

Poisson Multi-Bernoulli Mapping Using Gibbs Sampling

This paper uses a Poisson process prior on the map and proves that the posterior distribution is a hybrid Poisson, multi-Bernoulli mixture distribution, and devise a Gibbs sampling algorithm to sample from the batch multiobject posterior.

Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter

A new multi-target tracker is proposed based on the GM-PHD filter, which gives the association amongst state estimates of targets over time and provides track labels and a technique for resolving identities of targets in close proximity, which the PHD filter is unable to do on its own.

Multi-Scan Implementation of the Trajectory Poisson Multi-Bernoulli Mixture Filter

An efficient implementation that performs track-oriented $N$-scan pruning to limit computational complexity, and uses dual decomposition to solve the involved multi-frame assignment problem is proposed.

Labeled Random Finite Sets and Multi-Object Conjugate Priors

A new class of RFS distributions is proposed that is conjugate with respect to the multiobject observation likelihood and closed under the Chapman-Kolmogorov equation and is tested on a Bayesian multi-target tracking algorithm.

Multiple Target Tracking Based on Sets of Trajectories

A solution of the multiple target tracking (MTT) problem based on sets of trajectories and the random finite set framework is proposed by considering multiobject density functions in which objects are trajectories.

The δ-generalized multi-Bernoulli poisson filter in a multi-sensor application

A multi-target tracking strategy using a δ-Generalized Multi-Bernoulli Poisson (δ-GMBP) filter applied in a multi-sensor scenario, which is closed under the Chapman-Kolmogorov equation and Bayes rule, and also closed for a wide family of multi- target likelihood functions.