3D Multi-Object Tracking: A Baseline and New Evaluation Metrics

By Xinshuo Weng, Jianren Wang, David Held, Kris M. Kitani. IEEE/RJS International Conference on Intelligent RObots and Systems, 2019

563 citations recorded by the source corpus.

3D multi-object tracking (MOT) is an essential component for many applications such as autonomous driving and assistive robotics. Recent work on 3D MOT focuses on developing accurate systems giving less attention to practical considerations such as computational cost and system complexity. In contrast, this work proposes a simple real-time 3D MOT system. 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 the 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods. Therefore, we propose a new 3D MOT evaluation tool along with three new metrics to comprehensively evaluate 3D MOT methods. We show that, although our system employs a combination of classical MOT modules, we achieve state-of-the-art 3D MOT performance on two 3D MOT benchmarks (KITTI and nuScenes). Surprisingly, although our system does not use any 2D data as inputs, we achieve competitive performance on the KITTI 2D MOT leaderboard. Our proposed system runs at a rate of 207.4 FPS on the KITTI dataset, achieving the fastest speed among all modern MOT systems. To encourage standardized 3D MOT evaluation, our code is publicly available at http://www.xinshuoweng.com/projects/AB3DMOT.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/43b9bf090d1d7c8308f87bc4775680f5c8813ce6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking (2020, methodology): “A number of extensions to the MOTA metric, such as PR-MOTA [78] and AMOTA [79], have previously been proposed to adapt the MOTA metric to handle conﬁdence ranked tracking results as is done in Track-mAP.”
V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception (2023, methodology): “The recent development of deep learning brings significant breakthroughs in various perception tasks such as 3D object detection [22, 35, 42], object tracking [43, 56], and semantic segmentation [47, 57].”
StrongSORT: Make DeepSORT Great Again (2022, unknown): “HOTA(↑) MOTA(↑) AssA(↑) IDs(↓) HOTA(↑) MOTA(↑) AssA(↑) IDs(↓) AB3D [53] IROS2020 69.”
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks (2021, methodology): “Online methods [10], [14], [44], [45] only require information up to the current frame for data association and can be useful to online applications.”
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (2023, methodology): “Most previous methods [2, 9, 51] directly use the Kalman ﬁlter upon detection results, such as AB3DMOT [51].”
Track to Detect and Segment: An Online Multi-Object Tracker (2021, unknown): “66 2,252 37ms Mapillary[34]+AB3D[47] 12.”