Machine Learning Methods for Data Association in Multi-Object Tracking

TL;DR

This survey reviews recent machine learning approaches for data association in multi-object tracking, emphasizing their connections to classical optimization problems and highlighting future research directions.

Contribution

It unifies various learning-based data association methods in multi-object tracking, connecting them to linear assignment and the MDAP, and compares their performance.

Findings

Learning algorithms improve data association accuracy.

Probabilistic and end-to-end methods show promising results.

Future research should focus on scalability and robustness.

Abstract

Data association is a key step within the multi-object tracking pipeline that is notoriously challenging due to its combinatorial nature. A popular and general way to formulate data association is as the NP-hard multidimensional assignment problem (MDAP). Over the last few years, data-driven approaches to assignment have become increasingly prevalent as these techniques have started to mature. We focus this survey solely on learning algorithms for the assignment step of multi-object tracking, and we attempt to unify various methods by highlighting their connections to linear assignment as well as to the MDAP. First, we review probabilistic and end-to-end optimization approaches to data association, followed by methods that learn association affinities from data. We then compare the performance of the methods presented in this survey, and conclude by discussing future research directions.