A Metric on the Space of Finite Sets of Trajectories for Evaluation of Multi-Target Tracking Algorithms
Artikel i vetenskaplig tidskrift, 2020

In this article, 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.

sets of trajectories

Metrics

random finite sets

multiple target tracking

Författare

Angel Garcia

University of Liverpool

Universidad Nebrija

Abu Sajana Rahmathullah

Zenuity AB

Lennart Svensson

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

IEEE Transactions on Signal Processing

1053-587X (ISSN) 1941-0476 (eISSN)

Vol. 68 3917-3928 9127194

Ämneskategorier

Beräkningsmatematik

Signalbehandling

Matematisk analys

DOI

10.1109/TSP.2020.3005309

Mer information

Senast uppdaterat

2020-09-17