Fast-Poly: A Fast Polyhedral Algorithm for 3D Multi-Object Tracking
- 10 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (11) , 10519-10526
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 letter, 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).Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62073101)
- Self-Planned Taskof SKLRS(HIT) of China (SKLRS202301A09, SKLRS202417B)
This publication has 31 references indexed in Scilit:
- FastTrack: A Highly Efficient and Generic GPU-Based Multi-object Tracking Method with Parallel Kalman FilterInternational Journal of Computer Vision, 2023
- SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking2023
- Tracking Objects as Points2020
- HOTA: A Higher Order Metric for Evaluating Multi-object TrackingInternational Journal of Computer Vision, 2020
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection2020
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset2020
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression2019
- Cascade R-CNN: Delving Into High Quality Object Detection2018
- An efficient algorith for determining the convex hull of a finite planar setInformation Processing Letters, 1972
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955