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

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.

[1]  Chongwei Liu,et al.  FastTrack: A Highly Efficient and Generic GPU-Based Multi-object Tracking Method with Parallel Kalman Filter , 2023, International Journal of Computer Vision.

[2]  Juergen Gall,et al.  3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking , 2023, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Jin Gao,et al.  Poly-MOT: A Polyhedral Framework For 3D Multi-Object Tracking , 2023, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Pei Sun,et al.  ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box , 2023, ArXiv.

[5]  Sergey Zagoruyko,et al.  Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jie Li,et al.  ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking , 2022, IEEE Robotics and Automation Letters.

[7]  X. Zhang,et al.  CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking With Camera-LiDAR Fusion , 2022, IEEE Transactions on Intelligent Transportation Systems.

[8]  S. Savarese,et al.  Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking , 2022, ArXiv.

[9]  Huizi Mao,et al.  BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation , 2022, 2023 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Yilun Wang,et al.  MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Jiaya Jia,et al.  Focal Sparse Convolutional Networks for 3D Object Detection , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Haoqian Wang,et al.  Faster-LIO: Lightweight Tightly Coupled Lidar-Inertial Odometry Using Parallel Sparse Incremental Voxels , 2022, IEEE Robotics and Automation Letters.

[13]  Chiew-Lan Tai,et al.  TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Xiyang Wang,et al.  DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion With Deep Association , 2022, IEEE Robotics and Automation Letters.

[15]  Dalong Du,et al.  BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View , 2021, ArXiv.

[16]  Ziqi Pang,et al.  SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking , 2021, ECCV Workshops.

[17]  Ping Luo,et al.  ByteTrack: Multi-Object Tracking by Associating Every Detection Box , 2021, ECCV.

[18]  Kemiao Huang,et al.  Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving , 2021, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[19]  Andreas Zell,et al.  Score refinement for confidence-based 3D multi-object tracking , 2021, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Laura Leal-Taixé,et al.  EagerMOT: 3D Multi-Object Tracking via Sensor Fusion , 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Luc Van Gool,et al.  Learnable Online Graph Representations for 3D Multi-Object Tracking , 2021, IEEE Robotics and Automation Letters.

[22]  Hujun Bao,et al.  LoFTR: Detector-Free Local Feature Matching with Transformers , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Cheng Wang,et al.  3D Multi-Object Tracking in Point Clouds Based on Prediction Confidence-Guided Data Association , 2021, IEEE Transactions on Intelligent Transportation Systems.

[24]  Jeannette Bohg,et al.  Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving , 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[25]  Philip H. S. Torr,et al.  HOTA: A Higher Order Metric for Evaluating Multi-object Tracking , 2020, International Journal of Computer Vision.

[26]  Philipp Krähenbühl,et al.  Center-based 3D Object Detection and Tracking , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Vladlen Koltun,et al.  Tracking Objects as Points , 2020, ECCV.

[28]  Xiaogang Wang,et al.  PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Dragomir Anguelov,et al.  Scalability in Perception for Autonomous Driving: Waymo Open Dataset , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Hui Zhou,et al.  Robust Multi-Modality Multi-Object Tracking , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[31]  David Held,et al.  3D Multi-Object Tracking: A Baseline and New Evaluation Metrics , 2019, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[32]  Qiang Xu,et al.  nuScenes: A Multimodal Dataset for Autonomous Driving , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Silvio Savarese,et al.  Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[36]  Ivan E. Sutherland,et al.  Reentrant polygon clipping , 1974, Commun. ACM.

[37]  R. Graham.  An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set , 1972, Inf. Process. Lett..

[38]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[39]  Jonathan Li,et al.  CasA: A Cascade Attention Network for 3-D Object Detection From LiDAR Point Clouds , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Jiaya Jia,et al.  Scaling up Kernels in 3D CNNs , 2022, ArXiv.

[41]  Rainer Stiefelhagen,et al.  Multiple Object Tracking Performance Metrics and Evaluation in a Smart Room Environment , 2006 .