Learnable Online Graph Representations for 3D Multi-Object Tracking

TL;DR

This paper introduces a learnable, graph-based neural network approach for online 3D multi-object tracking that improves stability and reduces ID switches, achieving state-of-the-art results on nuScenes.

Contribution

It proposes a fully trainable neural message passing network for data association in 3D MOT, replacing handcrafted features and heuristics.

Findings

Achieved 65.6% AMOTA on nuScenes

Reduced ID-switches by 58%

Outperformed previous methods in 3D MOT accuracy

Abstract

Tracking of objects in 3D is a fundamental task in computer vision that finds use in a wide range of applications such as autonomous driving, robotics or augmented reality. Most recent approaches for 3D multi object tracking (MOT) from LIDAR use object dynamics together with a set of handcrafted features to match detections of objects. However, manually designing such features and heuristics is cumbersome and often leads to suboptimal performance. In this work, we instead strive towards a unified and learning based approach to the 3D MOT problem. We design a graph structure to jointly process detection and track states in an online manner. To this end, we employ a Neural Message Passing network for data association that is fully trainable. Our approach provides a natural way for track initialization and handling of false positive detections, while significantly improving track stability. We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.