Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning

TL;DR

This paper compares a novel Transformer-based deep learning approach to traditional Bayesian filters for multitarget tracking, demonstrating superior performance in complex scenarios while matching Bayesian methods in simpler cases.

Contribution

Introduces a Transformer-based deep learning method for multitarget tracking and compares it with Bayesian filters under known model conditions, highlighting its effectiveness.

Findings

Deep learning outperforms Bayesian filters in complex scenarios.

Deep learning matches Bayesian filters in simple scenarios.

The proposed method benefits from unlimited training data.

Abstract

Multitarget Tracking (MTT) is the problem of tracking the states of an unknown number of objects using noisy measurements, with important applications to autonomous driving, surveillance, robotics, and others. In the model-based Bayesian setting, there are conjugate priors that enable us to express the multi-object posterior in closed form, which could theoretically provide Bayes-optimal estimates. However, the posterior involves a super-exponential growth of the number of hypotheses over time, forcing state-of-the-art methods to resort to approximations for remaining tractable, which can impact their performance in complex scenarios. Model-free methods based on deep-learning provide an attractive alternative, as they can, in principle, learn the optimal filter from data, but to the best of our knowledge were never compared to current state-of-the-art Bayesian filters, specially not in contexts where accurate models are available. In this paper, we propose a high-performing deep-learning method for MTT based on the Transformer architecture and compare it to two state-of-the-art Bayesian filters, in a setting where we assume the correct model is provided. Although this gives an edge to the model-based filters, it also allows us to generate unlimited training data. We show that the proposed model outperforms state-of-the-art Bayesian filters in complex scenarios, while matching their performance in simpler cases, which validates the applicability of deep-learning also in the model-based regime. The code for all our implementations is made available at https://github.com/JulianoLagana/MT3 .