Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking (2403.13443v2)

Published 20 Mar 2024 in cs.CV and cs.RO

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. X. Li, T. Xie, D. Liu, J. Gao, K. Dai, Z. Jiang, L. Zhao, and K. Wang, “Poly-mot: A polyhedral framework for 3d multi-object tracking,” in IROS.   IEEE, 2023, pp. 9391–9398.
  2. L. Wang, X. Zhang, W. Qin, X. Li, J. Gao, L. Yang, Z. Li, J. Li, L. Zhu, H. Wang et al., “Camo-mot: Combined appearance-motion optimization for 3d multi-object tracking with camera-lidar fusion,” IEEE T-ITS, 2023.
  3. A. Kim, A. Ošep, and L. Leal-Taixé, “Eagermot: 3d multi-object tracking via sensor fusion,” in ICRA.   IEEE, 2021, pp. 11 315–11 321.
  4. Z. Pang, Z. Li, and N. Wang, “Simpletrack: Understanding and rethinking 3d multi-object tracking,” in ECCV Workshops.   Springer, 2022, pp. 680–696.
  5. J. Gwak, S. Savarese, and J. Bohg, “Minkowski tracker: A sparse spatio-temporal r-cnn for joint object detection and tracking,” arXiv preprint arXiv:2208.10056, 2022.
  6. T. Sadjadpour, J. Li, R. Ambrus, and J. Bohg, “Shasta: Modeling shape and spatio-temporal affinities for 3d multi-object tracking,” IEEE RA-L, 2023.
  7. J.-N. Zaech, A. Liniger, D. Dai, M. Danelljan, and L. Van Gool, “Learnable online graph representations for 3d multi-object tracking,” IEEE RA-L, vol. 7, no. 2, pp. 5103–5110, 2022.
  8. H. Caesar, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom, “nuscenes: A multimodal dataset for autonomous driving,” in CVPR, 2020, pp. 11 621–11 631.
  9. P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine et al., “Scalability in perception for autonomous driving: Waymo open dataset,” in CVPR, 2020, pp. 2446–2454.
  10. X. Weng, J. Wang, D. Held, and K. Kitani, “3d multi-object tracking: A baseline and new evaluation metrics,” in IROS.   IEEE, 2020, pp. 10 359–10 366.
  11. X. Wang, C. Fu, Z. Li, Y. Lai, and J. He, “Deepfusionmot: A 3d multi-object tracking framework based on camera-lidar fusion with deep association,” IEEE RA-L, vol. 7, no. 3, pp. 8260–8267, 2022.
  12. H.-k. Chiu, J. Li, R. Ambrus, and J. Bohg, “Probabilistic 3d multi-modal, multi-object tracking for autonomous driving,” ICRA, 2021.
  13. H. Wu, W. Han, C. Wen, X. Li, and C. Wang, “3d multi-object tracking in point clouds based on prediction confidence-guided data association,” IEEE T-ITS, vol. 23, no. 6, pp. 5668–5677, 2021.
  14. C. Liu, H. Li, and Z. Wang, “Fasttrack: A highly efficient and generic gpu-based multi-object tracking method with parallel kalman filter,” IJCV, pp. 1–21, 2023.
  15. N. Benbarka, J. Schröder, and A. Zell, “Score refinement for confidence-based 3d multi-object tracking,” in IROS.   IEEE, 2021, pp. 8083–8090.
  16. S. Ding, E. Rehder, L. Schneider, M. Cordts, and J. Gall, “3dmotformer: Graph transformer for online 3d multi-object tracking,” in ICCV, 2023, pp. 9784–9794.
  17. Y. Zhang, X. Wang, X. Ye, W. Zhang, J. Lu, X. Tan, E. Ding, P. Sun, and J. Wang, “Bytetrackv2: 2d and 3d multi-object tracking by associating every detection box,” 2023.
  18. T. Zhang, X. Chen, Y. Wang, Y. Wang, and H. Zhao, “Mutr3d: A multi-camera tracking framework via 3d-to-2d queries,” in CVPR, 2022, pp. 4537–4546.
  19. Z. Pang, J. Li, P. Tokmakov, D. Chen, S. Zagoruyko, and Y.-X. Wang, “Standing between past and future: Spatio-temporal modeling for multi-camera 3d multi-object tracking,” in CVPR, 2023, pp. 17 928–17 938.
  20. T. Yin, X. Zhou, and P. Krahenbuhl, “Center-based 3d object detection and tracking,” in CVPR, 2021, pp. 11 784–11 793.
  21. Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, Z. Yuan, P. Luo, W. Liu, and X. Wang, “Bytetrack: Multi-object tracking by associating every detection box,” in ECCV.   Springer, 2022, pp. 1–21.
  22. X. Zhou, V. Koltun, and P. Krähenbühl, “Tracking objects as points,” in European conference on computer vision.   Springer, 2020, pp. 474–490.
  23. K. Bernardin, A. Elbs, and R. Stiefelhagen, “Multiple object tracking performance metrics and evaluation in a smart room environment,” in Sixth IEEE International Workshop on Visual Surveillance, in conjunction with ECCV, vol. 90, no. 91.   Citeseer, 2006.
  24. J. Luiten, A. Osep, P. Dendorfer, P. Torr, A. Geiger, L. Leal-Taixé, and B. Leibe, “Hota: A higher order metric for evaluating multi-object tracking,” IJCV, vol. 129, pp. 548–578, 2021.
  25. J. Huang, G. Huang, Z. Zhu, Y. Ye, and D. Du, “Bevdet: High-performance multi-camera 3d object detection in bird-eye-view,” arXiv preprint arXiv:2112.11790, 2021.
  26. Z. Liu, H. Tang, A. Amini, X. Yang, H. Mao, D. L. Rus, and S. Han, “Bevfusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation,” in ICRA.   IEEE, 2023, pp. 2774–2781.
  27. Y. Chen, Y. Li, X. Zhang, J. Sun, and J. Jia, “Focal sparse convolutional networks for 3d object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5428–5437.
  28. Y. Chen, J. Liu, X. Qi, X. Zhang, J. Sun, and J. Jia, “Scaling up kernels in 3d cnns,” arXiv preprint arXiv:2206.10555, 2022.
  29. H. Wu, J. Deng, C. Wen, X. Li, C. Wang, and J. Li, “Casa: A cascade attention network for 3-d object detection from lidar point clouds,” IEEE T-GRS, vol. 60, pp. 1–11, 2022.
  30. S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, and H. Li, “Pv-rcnn: Point-voxel feature set abstraction for 3d object detection,” in CVPR, 2020, pp. 10 529–10 538.
  31. K. Huang and Q. Hao, “Joint multi-object detection and tracking with camera-lidar fusion for autonomous driving,” in IROS.   IEEE, 2021, pp. 6983–6989.
  32. W. Zhang, H. Zhou, S. Sun, Z. Wang, J. Shi, and C. C. Loy, “Robust multi-modality multi-object tracking,” in ICCV, October 2019.
  33. H. W. Kuhn, “The hungarian method for the assignment problem,” Naval research logistics quarterly, vol. 2, no. 1-2, pp. 83–97, 1955.
  34. I. E. Sutherland and G. W. Hodgman, “Reentrant polygon clipping,” Communications of the ACM, vol. 17, no. 1, pp. 32–42, 1974.
  35. R. L. Graham, “An efficient algorithm for determining the convex hull of a finite planar set,” Info. Proc. Lett., vol. 1, pp. 132–133, 1972.
  36. H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” in CVPR, 2019, pp. 658–666.
  37. J. Sun, Z. Shen, Y. Wang, H. Bao, and X. Zhou, “Loftr: Detector-free local feature matching with transformers,” in CVPR, 2021, pp. 8922–8931.
  38. C. Bai, T. Xiao, Y. Chen, H. Wang, F. Zhang, and X. Gao, “Faster-lio: Lightweight tightly coupled lidar-inertial odometry using parallel sparse incremental voxels,” IEEE RA-L, vol. 7, no. 2, pp. 4861–4868, 2022.
  39. S. Van Der Walt, S. C. Colbert, and G. Varoquaux, “The numpy array: a structure for efficient numerical computation,” Computing in science & engineering, vol. 13, no. 2, pp. 22–30, 2011.
  40. Z. Cai and N. Vasconcelos, “Cascade r-cnn: Delving into high quality object detection,” in CVPR, 2018, pp. 6154–6162.
  41. X. Bai, Z. Hu, X. Zhu, Q. Huang, Y. Chen, H. Fu, and C.-L. Tai, “Transfusion: Robust lidar-camera fusion for 3d object detection with transformers,” in CVPR, 2022, pp. 1090–1099.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Xiaoyu Li (348 papers)
  2. Dedong Liu (4 papers)
  3. Lijun Zhao (26 papers)
  4. Yitao Wu (5 papers)
  5. Xian Wu (139 papers)
  6. Jinghan Gao (8 papers)
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets