An Efficient Labeled/Unlabeled Random Finite Set Algorithm for Multiobject Tracking

TL;DR

This paper introduces a computationally efficient multiobject tracking algorithm combining labeled multi-Bernoulli and Poisson RFSs, improving track continuity and reducing complexity compared to existing methods.

Contribution

The paper presents a novel hybrid RFS algorithm that dynamically switches between Poisson and labeled Bernoulli components for efficient multiobject tracking.

Findings

Significant reduction in computational complexity.

Maintains high tracking accuracy and continuity.

Outperforms existing RFS-based algorithms in simulations.

Abstract

We propose an efficient random finite set (RFS) based algorithm for multiobject tracking in which the object states are modeled by a combination of a labeled multi-Bernoulli (LMB) RFS and a Poisson RFS. The less computationally demanding Poisson part of the algorithm is used to track potential objects whose existence is unlikely. Only if a quantity characterizing the plausibility of object existence is above a threshold, a new labeled Bernoulli component is created and the object is tracked by the more accurate but more computationally demanding LMB part of the algorithm. Conversely, a labeled Bernoulli component is transferred back to the Poisson RFS if the corresponding existence probability falls below another threshold. Contrary to existing hybrid algorithms based on multi-Bernoulli and Poisson RFSs, the proposed method facilitates track continuity and implements complexity-reducing features. Simulation results demonstrate a large complexity reduction relative to other RFS-based algorithms with comparable performance.