Hybrid PHD-PMB Trajectory Smoothing Using Backward Simulation

TL;DR

This paper introduces a hybrid PHD-PMB trajectory smoother that combines forward PHD filtering with backward PMB smoothing, enabling comprehensive trajectory estimation without labeling and outperforming existing methods in accuracy.

Contribution

The paper presents a novel hybrid PHD-PMB smoothing method that estimates all trajectories without labeling, improving upon existing PHD and trajectory PHD smoothers.

Findings

Outperforms PHD filter in state and cardinality estimates.

Enables estimation of all trajectories, not just alive ones.

Reduces false detections compared to trajectory PHD filter.

Abstract

The probability hypothesis density (PHD) and Poisson multi-Bernoulli (PMB) filters are two popular set-type multi-object filters. Motivated by the fact that the multi-object filtering density after each update step in the PHD filter is a PMB without approximation, in this paper we present a multi-object smoother involving PHD forward filtering and PMB backward smoothing. This is achieved by first running the PHD filtering recursion in the forward pass and extracting the PMB filtering densities after each update step before the Poisson Point Process approximation, which is inherent in the PHD filter update. Then in the backward pass we apply backward simulation for sets of trajectories to the extracted PMB filtering densities. We call the resulting multi-object smoother hybrid PHD-PMB trajectory smoother. Notably, the hybrid PHD-PMB trajectory smoother can provide smoothed trajectory estimates for the PHD filter without labeling or tagging, which is not possible for existing PHD smoothers. Also, compared to the trajectory PHD filter, which can only estimate alive trajectories, the hybrid PHD-PMB trajectory smoother enables the estimation of the set of all trajectories. Simulation results demonstrate that the hybrid PHD-PMB trajectory smoother outperforms the PHD filter in terms of both state and cardinality estimates, and the trajectory PHD filter in terms of false detections.