A two-stage data association approach for 3D Multi-object Tracking

TL;DR

This paper introduces a two-stage data association method for 3D multi-object tracking, improving accuracy over traditional bipartite matching approaches in autonomous driving scenarios.

Contribution

It adapts a successful image-based two-stage data association approach to 3D MOT, offering an effective alternative to bipartite matching algorithms.

Findings

Achieves 0.587 AMOTA on NuScenes validation set

Outperforms baseline one-stage bipartite matching method

Provides a more robust data association technique for 3D MOT

Abstract

Multi-object tracking (MOT) is an integral part of any autonomous driving pipelines because itproduces trajectories which has been taken by other moving objects in the scene and helps predicttheir future motion. Thanks to the recent advances in 3D object detection enabled by deep learning,track-by-detection has become the dominant paradigm in 3D MOT. In this paradigm, a MOT systemis essentially made of an object detector and a data association algorithm which establishes track-to-detection correspondence. While 3D object detection has been actively researched, associationalgorithms for 3D MOT seem to settle at a bipartie matching formulated as a linear assignmentproblem (LAP) and solved by the Hungarian algorithm. In this paper, we adapt a two-stage dataassociation method which was successful in image-based tracking to the 3D setting, thus providingan alternative for data association for 3D MOT. Our method outperforms the baseline using one-stagebipartie matching for data association by achieving 0.587 AMOTA in NuScenes validation set.