A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithms

TL;DR

This paper introduces a mathematically rigorous metric for evaluating multi-target tracking algorithms by comparing estimated trajectories with ground truth, accounting for localization errors, missed and false targets, and track switches.

Contribution

It proposes a new metric on the space of finite sets of trajectories, including a polynomial-time computable lower bound, for more accurate multi-target tracking evaluation.

Findings

The metric effectively captures localization, missed, false targets, and track switches.

A polynomial-time computable lower bound is provided.

Extension to random finite sets of trajectories is demonstrated.

Abstract

In this paper, we propose a metric on the space of finite sets of trajectories for assessing multi-target tracking algorithms in a mathematically sound way. The main use of the metric is to compare estimates of trajectories from different algorithms with the ground truth of trajectories. The proposed metric includes intuitive costs associated to localization error for properly detected targets, missed and false targets and track switches at each time step. The metric computation is based on solving a multi-dimensional assignment problem. We also propose a lower bound for the metric, which is also a metric for sets of trajectories and is computable in polynomial time using linear programming. We also extend the proposed metrics on sets of trajectories to random finite sets of trajectories.