Second-order multi-object filtering with target interaction using determinantal point processes

DOI10.1007/S00498-020-00271-XMaRDI QIDQ2227003zbMATHOpenAlexFDO

Authors Nicolas Privault, Timothy Teoh

Publication date 9 February 2021

Published in MCSS. Mathematics of Control, Signals, and Systems (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.06522

zbMATH Keywords

correlationdeterminantal point processeshigher-order statisticsmulti-target trackingprobability hypothesis density filtersecond-order momentmulti-object filtering

Mathematics Subject Classification ID

Inference from spatial processes (62M30) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Signal detection and filtering (aspects of stochastic processes) (60G35) Sequential estimation (62L12)

Abstract: The Probability Hypothesis Density (PHD) filter, which is used for multi-target tracking based on sensor measurements, relies on the propagation of the first-order moment, or intensity function, of a point process. This algorithm assumes that targets behave independently, an hypothesis which may not hold in practice due to potential target interactions. In this paper, we construct a second-order PHD filter based on Determinantal Point Processes (DPPs) which are able to model repulsion between targets. Such processes are characterized by their first and second-order moments, which allows the algorithm to propagate variance and covariance information in addition to first-order target count estimates. Our approach relies on posterior moment formulas for the estimation of a general hidden point process after a thinning operation and a superposition with a Poisson Point Process (PPP), and on suitable approximation formulas in the determinantal point process setting. The repulsive properties of determinantal point processes apply to the modeling of negative correlation between distinct measurement domains. Monte Carlo simulations with correlation estimates are provided.

Recommendations

• Multi-target probability hypothesis density filtering with unknown probability of detection
• Particle probability hypothesis density filter based on pairwise Markov chains
• Convergence of the SMC implementation of the PHD filter
• scientific article; zbMATH DE number 6500516
• A linear multisensor PHD filters via the measurement product space

Cites work

• scientific article; zbMATH DE number 1103097 (Why is no real title available?)
• scientific article; zbMATH DE number 3806227 (Why is no real title available?)
• scientific article; zbMATH DE number 761753 (Why is no real title available?)
• A CPHD Approximation Based on a Discrete-Gamma Cardinality Model
• A Consistent Metric for Performance Evaluation of Multi-Object Filters
• A Second-Order PHD Filter With Mean and Variance in Target Number
• An Introduction to the Theory of Point Processes
• Analytic Implementations of the Cardinalized Probability Hypothesis Density Filter
• Conditional intensity and Gibbsianness of determinantal point processes
• Determinantal Point Processes
• Determinantal random point fields
• Filters for spatial point processes
• Interacting Brownian motions in infinite dimensions with logarithmic interaction potentials
• Models for point processes observed with noise
• Multiplicative population processes
• On optimal filtering of multitarget tracking systems based on point processes observations
• Random point fields associated with certain Fredholm determinants. I: Fermion, Poisson and Boson point processes.
• Regional Variance for Multi-Object Filtering
• The Cardinality Balanced Multi-Target Multi-Bernoulli Filter and Its Implementations
• The Gaussian Mixture Probability Hypothesis Density Filter
• The coincidence approach to stochastic point processes
• The general theory of stochastic population processes
• Zeros of Gaussian analytic functions and determinantal point processes

This page was built for publication: Second-order multi-object filtering with target interaction using determinantal point processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2227003)