A New Architecture for Neural Enhanced Multiobject Tracking

TL;DR

This paper introduces a novel neural architecture within a hybrid model-based and data-driven framework for multiobject tracking, significantly improving data association and object initialization, and achieving leading performance in a major LiDAR tracking challenge.

Contribution

It presents a new neural architecture for NEBP that enhances data association and object initialization in multiobject tracking, integrating traditional and neural methods effectively.

Findings

Outperforms existing MOT methods in challenging scenarios.

Leads the nuScenes LiDAR-only tracking challenge.

Demonstrates improved accuracy and robustness in multiobject tracking.

Abstract

Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More recent methods are fully data-driven and rely on the training of neural networks. The two approaches have demonstrated advantages in certain scenarios. In particular, in problems where plenty of labeled data for the training of neural networks is available, data-driven MOT tends to have advantages compared to traditional methods. A natural thought is whether a general and efficient framework can integrate the two approaches. This paper advances a recently introduced hybrid model-based and data-driven method called neural-enhanced belief propagation (NEBP). Compared to existing work on NEBP for MOT, it introduces a novel neural architecture that can improve data association and new object initialization, two critical aspects of MOT. The proposed tracking method is leading the nuScenes LiDAR-only tracking challenge at the time of submission of this paper.