Multi-sensor Joint Adaptive Birth Sampler for Labeled Random Finite Set Tracking

Abstract

This paper provides a scalable, multi-sensor measurement adaptive track initiation technique for labeled random finite set filters. A naive construction of the multi-sensor measurement adaptive birth set distribution leads to an exponential number of newborn components in the number of sensors. A truncation criterion is established for a labeled multi-Bernoulli random finite set birth density. The proposed truncation criterion is shown to have a bounded L1 error in the generalized labeled multi-Bernoulli posterior density. This criterion is used to construct a Gibbs sampler that produces a truncated measurement-generated labeled multi-Bernoulli birth distribution with quadratic complexity in the number of sensors. A closed-form solution of the conditional sampling distribution assuming linear Gaussian likelihoods is provided, alongside an approximate solution using Monte Carlo importance sampling. Multiple simulation results are provided to verify the efficacy of the truncation criterion, as well as the reduction in complexity.

References in corpus (6)

• Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter
• Poisson multi-Bernoulli mixture filter: direct derivation and implementation
• Robust Distributed Fusion with Labeled Random Finite Sets
• Annealed Importance Sampling
• Passive Multi-Target Tracking Using the Adaptive Birth Intensity PHD Filter
• Multi-object Tracking with an Adaptive Generalized Labeled Multi-Bernoulli Filter

Cited by in corpus (4)

• Linear Complexity Gibbs Sampling for Generalized Labeled Multi-Bernoulli Filtering
• An Overview of Multi-Object Estimation via Labeled Random Finite Set
• Arithmetic Average Density Fusion -- Part III: Heterogeneous Unlabeled and Labeled RFS Filter Fusion
• Multi-Target Tracking with Transferable Convolutional Neural Networks