A Solution for Large-scale Multi-object Tracking

TL;DR

This paper introduces a large-scale multi-object tracking algorithm based on the GLMB filter, capable of handling over a million objects with high accuracy despite false alarms and measurement uncertainties.

Contribution

It presents a novel large-scale multi-object tracking method using the GLMB filter, including a new evaluation strategy for large scenarios.

Findings

Successfully tracked over one million objects in simulation.

Developed an efficient large-scale OSPA metric evaluation method.

Demonstrated robustness against false alarms and measurement errors.

Abstract

A large-scale multi-object tracker based on the generalised labeled multi-Bernoulli (GLMB) filter is proposed. The algorithm is capable of tracking a very large, unknown and time-varying number of objects simultaneously, in the presence of a high number of false alarms, as well as misdetections and measurement origin uncertainty due to closely spaced objects. The algorithm is demonstrated on a simulated large-scale tracking scenario, where the peak number objects appearing simultaneously exceeds one million. To evaluate the performance of the proposed tracker, we also introduce a new method of applying the optimal sub-pattern assignment (OSPA) metric, and an efficient strategy for its evaluation in large-scale scenarios.