目前大多數追蹤方法只針對光學雷達或相機單一感測器進行追蹤的研究，卻忽略了單個感測器在一定程度上會造成資訊的缺失，又或者是為了追求更高的追蹤準確度，而在追蹤方法中藉由複雜的計算來達到不同感測器的結合。在本研究中，為了提升三維的追蹤準確度，以及達到實時追蹤的目的，考慮了光達及相機檢測器效果的不一致，我們透過了有效的資料前處理，並搭配了結合二維及三維的追蹤關聯機制，在過程中利用三維幫助二維軌跡，最後再根據現有的二維資訊來更新三維追蹤框的狀態，藉此增進三維軌跡的穩定及延續性，從而達到更優的追蹤效果，最後在實驗階段，我們藉由目前兩大的追蹤評估指標HOTA以及sAMOTA指標，來探討追蹤器在不同面向的性能表現，經過實驗證實，利用檢測器互補的資訊來更新三維追蹤框的狀態，能有效增進追蹤器整體的性能。

Currently, most tracking methods focus solely on a single sensor, such as optical radar or camera, for tracking research. However, they overlook the fact that relying on a single sensor can result in information gaps to some extent. Alternatively, in pursuit of higher tracking accuracy, some tracking methods use complex computations to integrate different sensors.In this study, aiming to enhance 3D tracking accuracy and achieve real-time tracking, we address the inconsistency between LiDAR and camera detector effects. We employ effective data preprocessing and combine 2D and 3D tracking association mechanisms. Throughout the process, we utilize 3D data to assist 2D trajectories. Finally, we update the state of 3D tracking boxes based on existing 2D information, thereby improving the stability and continuity of 3D trajectories and achieving superior tracking performance.In the experimental phase, we employ the two major tracking evaluation metrics, HOTA and sAMOTA, to investigate the tracker's performance from various perspectives. The experiments confirm that utilizing complementary information from detectors to update the state of 3D tracking boxes effectively enhances the overall performance of the tracker.

[1] A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple online and realtime tracking," in 2016 IEEE international conference on image processing (ICIP), 2016: IEEE, pp. 3464-3468.
[2] N. Wojke, A. Bewley, and D. Paulus, "Simple online and realtime tracking with a deep association metric," in 2017 IEEE international conference on image processing (ICIP), 2017: IEEE, pp. 3645-3649.
[3] J. Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani, "Observation-centric sort: Rethinking sort for robust multi-object tracking," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9686-9696.
[4] X. Weng, J. Wang, D. Held, and K. Kitani, "3d multi-object tracking: A baseline and new evaluation metrics," in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020: IEEE, pp. 10359-10366.
[5] T. Yin, X. Zhou, and P. Krahenbuhl, "Center-based 3d object detection and tracking," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11784-11793.
[6] M. Liang et al., "Pnpnet: End-to-end perception and prediction with tracking in the loop," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11553-11562.
[7] A. Kim, A. Ošep, and L. Leal-Taixé, "Eagermot: 3d multi-object tracking via sensor fusion," in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021: IEEE, pp. 11315-11321.
[8] 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 Robotics and Automation Letters, vol. 7, no. 3, pp. 8260-8267, 2022.
[9] W. Zhang, H. Zhou, S. Sun, Z. Wang, J. Shi, and C. C. Loy, "Robust multi-modality multi-object tracking," in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 2365-2374.
[10] Z. Wang, L. Zheng, Y. Liu, Y. Li, and S. Wang, "Towards real-time multi-object tracking," in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XI 16, 2020: Springer, pp. 107-122.
[11] Y. Zhang, C. Wang, X. Wang, W. Zeng, and W. Liu, "Fairmot: On the fairness of detection and re-identification in multiple object tracking," International Journal of Computer Vision, vol. 129, pp. 3069-3087, 2021.
[12] Y. Wang, K. Kitani, and X. Weng, "Joint object detection and multi-object tracking with graph neural networks," in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021: IEEE, pp. 13708-13715.
[13] X. Zhou, V. Koltun, and P. Krähenbühl, "Tracking objects as points," in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IV, 2020: Springer, pp. 474-490.
[14] C. Luo, X. Yang, and A. Yuille, "Exploring simple 3d multi-object tracking for autonomous driving," in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10488-10497.
[15] K. Huang and Q. Hao, "Joint multi-object detection and tracking with camera-LiDAR fusion for autonomous driving," in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021: IEEE, pp. 6983-6989.
[16] J. Koh, J. Kim, J. H. Yoo, Y. Kim, D. Kum, and J. W. Choi, "Joint 3d object detection and tracking using spatio-temporal representation of camera image and lidar point clouds," in Proceedings of the AAAI Conference on Artificial Intelligence, 2022, vol. 36, no. 1, pp. 1210-1218.
[17] G. Welch and G. Bishop, "An introduction to the Kalman filter," 1995.
[18] A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, "Vision meets robotics: The kitti dataset," The International Journal of Robotics Research, vol. 32, no. 11, pp. 1231-1237, 2013.
[19] A. Milan, L. Leal-Taixé, I. Reid, S. Roth, and K. Schindler, "MOT16: A benchmark for multi-object tracking," arXiv preprint arXiv:1603.00831, 2016.
[20] A. Vince, "A framework for the greedy algorithm," Discrete Applied Mathematics, vol. 121, no. 1-3, pp. 247-260, 2002.
[21] H. W. Kuhn, "The Hungarian method for the assignment problem," Naval research logistics quarterly, vol. 2, no. 1‐2, pp. 83-97, 1955.
[22] S. Pang, D. Morris, and H. Radha, "CLOCs: Camera-LiDAR object candidates fusion for 3D object detection," in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020: IEEE, pp. 10386-10393.
[23] Y. Zhang et al., "Bytetrack: Multi-object tracking by associating every detection box," in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXII, 2022: Springer, pp. 1-21.
[24] J. Luiten et al., "Hota: A higher order metric for evaluating multi-object tracking," International journal of computer vision, vol. 129, pp. 548-578, 2021.
[25] S. Shi, X. Wang, and H. Li, "Pointrcnn: 3d object proposal generation and detection from point cloud," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 770-779.
[26] J. Ren et al., "Accurate single stage detector using recurrent rolling convolution," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5420-5428.
[27] S. Sharma, J. A. Ansari, J. K. Murthy, and K. M. Krishna, "Beyond pixels: Leveraging geometry and shape cues for online multi-object tracking," in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018: IEEE, pp. 3508-3515.
[28] E. Baser, V. Balasubramanian, P. Bhattacharyya, and K. Czarnecki, "Fantrack: 3d multi-object tracking with feature association network," in 2019 IEEE Intelligent Vehicles Symposium (IV), 2019: IEEE, pp. 1426-1433.
[29] A. Shenoi et al., "Jrmot: A real-time 3d multi-object tracker and a new large-scale dataset," in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020: IEEE, pp. 10335-10342.
[30] J. Luiten, T. Fischer, and B. Leibe, "Track to reconstruct and reconstruct to track," IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 1803-1810, 2020.
[31] X. Weng, Y. Wang, Y. Man, and K. M. Kitani, "Gnn3dmot: Graph neural network for 3d multi-object tracking with 2d-3d multi-feature learning," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6499-6508.
[32] H.-N. Hu et al., "Joint monocular 3D vehicle detection and tracking," in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 5390-5399.
[33] G. Wang, R. Gu, Z. Liu, W. Hu, M. Song, and J.-N. Hwang, "Track without appearance: Learn box and tracklet embedding with local and global motion patterns for vehicle tracking," in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 9876-9886.
[34] J. Pang et al., "Quasi-dense similarity learning for multiple object tracking," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 164-173.
[35] N. F. Gonzalez, A. Ospina, and P. Calvez, "Smat: Smart multiple affinity metrics for multiple object tracking," in Image Analysis and Recognition: 17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part II 17, 2020: Springer, pp. 48-62.
[36] X. Weng, Y. Yuan, and K. Kitani, "Joint 3d tracking and forecasting with graph neural network and diversity sampling," arXiv preprint arXiv:2003.07847, vol. 2, no. 6.2, p. 1, 2020.
[37] K. Bernardin and R. Stiefelhagen, "Evaluating multiple object tracking performance: the clear mot metrics," EURASIP Journal on Image and Video Processing, vol. 2008, pp. 1-10, 2008.
[38] R. Fabbri, L. D. F. Costa, J. C. Torelli, and O. M. Bruno, "2D Euclidean distance transform algorithms: A comparative survey," ACM Computing Surveys (CSUR), vol. 40, no. 1, pp. 1-44, 2008.
[39] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, "Distance-IoU loss: Faster and better learning for bounding box regression," in Proceedings of the AAAI conference on artificial intelligence, 2020, vol. 34, no. 07, pp. 12993-13000.