REVIEW 7 cited by
AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
3D multi-object tracking (MOT) is essential to applications such as autonomous driving. Recent work focuses on developing accurate systems giving less attention to computational cost and system complexity. In contrast, this work proposes a simple real-time 3D MOT system with strong performance. Our system first obtains 3D detections from a LiDAR point cloud. Then, a straightforward combination of a 3D Kalman filter and the Hungarian algorithm is used for state estimation and data association. Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods. We propose a new 3D MOT evaluation tool along with three new metrics to comprehensively evaluate 3D MOT methods. We show that, our proposed method achieves strong 3D MOT performance on KITTI and runs at a rate of $207.4$ FPS on the KITTI dataset, achieving the fastest speed among modern 3D MOT systems. Our code is publicly available at http://www.xinshuoweng.com/projects/AB3DMOT.
Forward citations
Cited by 7 Pith papers
-
PRISA: Proactive Infrastructure LiDAR Framework for Intersection Safety Assessment
A modular edge-based LiDAR framework that automatically curates site-specific training data, predicts trajectories, and flags intersection conflicts via TTC and predicted post-encroachment time.
-
NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving
A 0.5B LLM associates open-vocabulary 3D detections via trajectory sequence completion, raising novel-category AMOTA on nuScenes from 2.2% to 22.4%.
-
GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking
A depth-aware MOT tracker using mask-guided 3D point clouds, voxelized 3D IoU association, adaptive Kalman noise, and 3D motion consistency surpasses prior TBD methods on MOT17, MOT20, and DanceTrack.
-
Evaluation of an Uncertainty-Aware Late Fusion Algorithm for Multi-Source Bird's Eye View Detections Under Controlled Noise
UniKF, a Kalman-filter-based late fusion for BEV detections, achieves lower errors than IoU-based baselines on synthetic noise, but only marginal gains over the authors' own WLS method.
-
Framework and Multi-modal Dataset for Roadwork Zone Detection and Geo-localization
A new real/sim multi-modal dataset and AB3DMOT-based tracker pipeline geo-localize roadwork objects (barriers, beacons) to ~1 m global accuracy for HD-map updates.
-
CLIFE: Camera-LiDAR Fusion Framework for Edge-Deployable Roadside VRU Perception
An edge-deployed camera–LiDAR late-fusion system with targetless online calibration achieves real-time VRU tracking on a single Jetson, but its robustness claims are only partially supported by the experiments.
-
Contour Errors: Ego-Centric Matching for 3D Multi-Object Tracking Performance Evaluation
A modified Hausdorff distance on ego-nearest bounding box corners is proposed as a 3D tracking matching criterion, showing more robust matches than IoU or center-point distance.
Discussion (0). Continue with ORCID to comment.