An Uncertainty-Aware Performance Measure for Multi-Object Tracking

TL;DR

This paper introduces a new uncertainty-aware performance measure for multi-object tracking based on negative log-likelihood, which considers all available uncertainty information without hyperparameters, improving evaluation accuracy.

Contribution

It proposes the use of NLL as a comprehensive, hyperparameter-free performance measure for MOT, along with algorithms for its efficient computation and comparison to existing metrics.

Findings

NLL effectively captures uncertainty in MOT evaluation.

The proposed measure can decompose and approximate GOSPA.

Illustrative examples demonstrate advantages over traditional metrics.

Abstract

Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context. This can lead practitioners to select models which produce uncertainty estimates of lower quality, negatively impacting any downstream systems that rely on them. Additionally, most MOT performance measures have hyperparameters, which makes comparisons of different trackers less straightforward. We propose the use of the negative log-likelihood (NLL) of the multi-object posterior given the set of ground-truth objects as a performance measure. This measure takes into account all available uncertainty information in a sound mathematical manner without hyperparameters. We provide efficient algorithms for approximating the computation of the NLL for several common MOT algorithms, show that in some cases it decomposes and approximates the widely-used GOSPA metric, and provide several illustrative examples highlighting the advantages of the NLL in comparison to other MOT performance measures.