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

Xiaoyu Li, Dedong Liu, Yitao Wu, Xian Wu, Lijun Zhao +1 more
3/20/2024
cs.CVcs.RO

Official code: lixiaoyu2000/FastPoly (123 stars, last commit 2025-04-16).

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.

View on arXivView PDF

Code Implementations(1)

lixiaoyu2000/FastPolyOfficial100%

Official Repo For IEEE RAL 2024 Accepted paper "Fast-Poly"

12311PythonMar 13, 20241 years ago

Similar Papers

IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter

83% match1 repo142025

Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking

83% match1 repo42024

ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer

82% match1 repo102024

MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking

81% match2026

MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking

81% match2024

Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking

81% match1 repo92024

Cite this paper

@article{li2024fastpoly,
  title  = {Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking},
  author = {Xiaoyu Li and Dedong Liu and Yitao Wu and Xian Wu and Lijun Zhao and Jinghan Gao},
  year   = {2024},
  eprint = {2403.13443},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.13443v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.13443.svg)](https://codeofpaper.com/paper/2403.13443)

Discussion