Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking

TL;DR

Fast-Poly is a novel, fast, and accurate filter-based 3D multi-object tracking framework that improves inference speed and precision by addressing rotational anisotropy and leveraging parallelization, achieving state-of-the-art results.

Contribution

Fast-Poly introduces a new filter-based approach for 3D MOT that enhances speed and accuracy by addressing rotational anisotropy and utilizing parallel computation.

Findings

Achieves 75.8% AMOTA on nuScenes, setting new state-of-the-art.

Runs at 34.2 FPS on CPU, demonstrating high efficiency.

Shows competitive accuracy and speed on Waymo dataset.

Abstract

3D Multi-Object Tracking (MOT) captures stable and comprehensive motion states of surrounding obstacles, essential for robotic perception. However, current 3D trackers face issues with accuracy and latency consistency. In this paper, we propose Fast-Poly, a fast and effective filter-based method for 3D MOT. Building upon our previous work Poly-MOT, Fast-Poly addresses object rotational anisotropy in 3D space, enhances local computation densification, and leverages parallelization technique, improving inference speed and precision. Fast-Poly is extensively tested on two large-scale tracking benchmarks with Python implementation. On the nuScenes dataset, Fast-Poly achieves new state-of-the-art performance with 75.8% AMOTA among all methods and can run at 34.2 FPS on a personal CPU. On the Waymo dataset, Fast-Poly exhibits competitive accuracy with 63.6% MOTA and impressive inference speed (35.5 FPS). The source code is publicly available at https://github.com/lixiaoyu2000/FastPoly.