基于角度交并比和自适应生命周期的三维多目标跟踪算法

doi:10.19562/j.chinasae.qcgc.2025.06.015

Abstract

Abstract:

For the problems of trajectory error association and premature deletion that intelligent vehicles face when tracking surrounding objects in real traffic environment， a three-dimensional multi-object tracking algorithm based on angle intersection over union and adaptive lifecycle is proposed in this paper. Firstly， low-confidence and overlapping detection boxes are removed using score filtering and non-maximum suppression， respectively， while inter-frame displacement of trajectories is eliminated by combining the constant velocity model and Kalman filter. Secondly， the angle intersection over union is designed by considering the factors of position and angle， and the optimal matching of the bipartite graph is determined through application of the Hungarian algorithm. Finally， an adaptive lifecycle strategy is formulated based on the first principle of the relationship between trajectory interruption and object distance to dynamically manage the trajectory status. The experiments show that the improved method attains 0.07%， 0.27%， and 0.29% Mismatch for Vehicle， Cyclist， and Pedestrian， respectively， on the Waymo dataset， a reduction of 0.03%， 0.18%， and 0.21% compared to the baseline algorithm. On the nuScenes dataset， the proposed method obtains an IDS of 312， a reduction of 49.9% compared to the baseline algorithm. The proposed angle intersection over union and adaptive lifecycle is able to reduce the number of identity switches， while the improved three-dimensional multi-object tracking algorithm can achieve accurate and stable temporal trajectories.

Key words: autonomous driving, LiDAR, 3D multi-object tracking, AIoU, adaptive lifecycle

Xinyu Sun,Lisheng Jin,Zhen Huo,Huanhuan Wang,Yang He,Dong Liu. Three-Dimensional Multi-object Tracking Algorithm Based on Angle Intersection over Union and Adaptive Lifecycle[J].Automotive Engineering, 2025, 47(6): 1169-1176.

Figures/Tables 11

References 20

1	ZHAO J Y， ZHAO W Y， DENG B， et al. Autonomous driving system： a comprehensive survey［J］. Expert Systems with Applications， 2024， 242： 122836.
2	王海，李洋，蔡英凤，等. 基于激光雷达的3D实时车辆跟踪［J］. 汽车工程， 2021， 43（7）： 1013-1021.
	WANG H， LI Y， CAI Y F， et al. 3D real⁃time vehicle tracking based on Lidar［J］. Automotive Engineering， 2021， 43（7）： 1013-1021.
3	PANDHARIPANDE A， CHENG C H， DAUWELS J， et al. Sensing and machine learning for automotive perception： a review［J］. IEEE Sensors Journal， 2023， 23（11）： 11097-11115.
4	程鑫，周经美，刘霈源，等. 基于任务联合的三维车辆检测与跟踪集成算法［J］. 中国公路学报， 2023， 36（9）： 288-301.
	CHENG X， ZHOU J M， LIU P Y， et al. 3D vehicle detection and tracking integration algorithm based on task collaboration［J］. China Journal of Highway and Transport， 2023， 36（9）： 288-301.
5	LIU M， NIU J W， LIU Y. UKF-MOT： an unscented Kalman filter-based 3D multi-object tracker［J］. CAAI Transactions on Intelligence Technology， 2024， 9（4）： 1031-1041.
6	ZHU Z M， NIE J H， WU H， et al. MSA-MOT： multi-stage association for 3D multimodality multi-object tracking［J］. Sensors， 2022， 22（22）： 8650.
7	WENG X S， WANG J R， HELD D， et al. 3D multi-object tracking： a baseline and new evaluation metrics［C］. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. IEEE， 2020： 10359-10366.
8	LIU J N， BAI L P， XIA Y X， et al. GNN-PMB： a simple but effective online 3D multi-object tracker without bells and whistles［J］. IEEE Transactions on Intelligent Vehicles， 2023， 8（2）： 1176-1189.
9	SADLI R， AFKIR M， HADID A， et al. Aggregated euclidean distances for a fast and robust real-time 3D-MOT［J］. IEEE Sensors Journal， 2021， 21（19）： 21872-21884.
10	PANG Z Q， LI Z C， WANG N Y. SimpleTrack： understanding and rethinking 3D multi-object tracking［C］. Proceedings of the European Conference on Computer Vision. Springer， 2022： 680-696.
11	MOHAMMED S A K， RAZAK M Z A， RAHMAN A H A. 3D-DIoU： 3D distance intersection over union for multi-object tracking in point cloud［J］. Sensors， 2023， 23（7）： 3390.
12	WANG Q T， CHEN Y T， PANG Z Q， et al. Immortal Tracker： tracklet never dies［J］. arXiv preprint arXiv：， 2021.
13	BENBARKA N， SCHRODER J， ZELL A. Score refinement for confidence-based 3D multi-object tracking［C］. 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. IEEE， 2021： 8083-8090.
14	LI X Y， LIU D D， WU Y T， et al. Fast-Poly： a fast polyhedral framework for 3D multi-object tracking［J］. IEEE Robotics and Automation Letters， 2024， 9（11）： 10519-10526.
15	熊珍凯，程晓强，吴幼冬，等. 基于激光雷达的无人驾驶3D 多目标跟踪［J］. 自动化学报， 2023， 49（10）： 2073-2083.
	XIONG Z K， CHENG X Q， WU Y D， et al. LiDAR-based 3D multi-object tracking for unmanned vehicles［J］. Acta Automatica Sinica， 2023， 49（10）： 2073-2083.
16	SUN P， KRETZSCHMAR H， DOTIWALLA X， et al. Scalability in perception for autonomous driving： Waymo open dataset［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2020： 2443-2451.
17	CAESAR H， BANKIYI V， LANG A H， et al. nuScenes： a multimodal dataset for autonomous driving［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2020： 11618-11628.
18	SUN X Y， JIN L S， WANG H H， et al. Spatial awareness enhancement based single-stage anchor-free 3D object detection for autonomous driving［J］. Displays， 2024， 85： 102821.
19	CHIU H K， PRIOLETTI A， LI J， et al. Probabilistic 3D multi-object tracking for autonomous driving［J］. arXiv preprint arXiv：， 2020.
20	JIN J Y， ZHANG J D， ZHANG K P， et al. 3D multi-object tracking with boosting data association and improved trajectory management mechanism［J］. Signal Processing， 2024， 218： 109367.

类别	方法	MOTA↑	MOTP↓	Miss↓	Mismatch↓
Vehicle	SimpleTrack^［10］	48.7	17.3	43.5	0.10
Vehicle	AA-MOT	48.7	17.3	43.5	0.07
Cyclist	SimpleTrack^［10］	34.0	25.5	60.1	0.45
Cyclist	AA-MOT	34.1	25.5	60.1	0.27
Pedestrian	SimpleTrack^［10］	46.3	32.8	42.7	0.50
Pedestrian	AA-MOT	46.6	32.8	42.7	0.29

方法	AMOTA↑	AMOTP↓	FRAG↓	IDS↓
AB3DMOT^［7］	50.9％	0.934 m	742	1 138
Probabilistic^［19］	56.1％	0.800 m	606	679
SimpleTrack^［10］	58.9％	0.649 m	544	623
EAFF^［20］	59.5％	0.744 m	481	565
AA-MOT	59.7％	0.616 m	419	312

SimpleTrack	分数过滤	角度交并比	自适应生命周期	AMOTA↑	AMOTP↓	FRAG↓	IDS↓	FPS↑
√				58.9％	0.649 m	544	623	0.42 Hz
√	√			59.6％	0.686 m	562	612	1.12 Hz
√	√	√		59.7％	0.686 m	475	537	1.07 Hz
√	√	√	√	59.7％	0.616 m	419	312	0.50 Hz

[1]	Mingchen Wang,Hai Wang,Yingfeng Cai,Long Chen,Yicheng Li. MSF-Diffuser: A Multi-sensor Adaptive Fusion Autonomous Driving Method Based on Diffusion Model Under BEV [J]. Automotive Engineering, 2025, 47(6): 1122-1132.
[2]	Lingyun Zhu,Haiyang Wang. Autonomous Vehicle Object Detection by LiDAR Point Cloud Feature Completion in Snowfall Scenarios [J]. Automotive Engineering, 2025, 47(6): 1133-1143.
[3]	Qinglu Ma,Qiuwei Jian,Meiqiang Li,Zheng Zou. Lane-Level LiDAR-Visual Fusion SLAM in Autonomous Driving Environment [J]. Automotive Engineering, 2025, 47(6): 1155-1168.
[4]	Chenyu Liu,Hai Wang,Yingfeng Cai,Long Chen. Multi-object Detection Algorithm Based on Camera and Radar Fusion for Autonomous Driving Scenarios [J]. Automotive Engineering, 2025, 47(5): 829-838.
[5]	Qirui Qin,Hai Wang,Yingfeng Cai,Long Chen,Yicheng Li. Real-Time Instance Segmentation Algorithm for Autonomous Driving Based on Instance Activation Maps [J]. Automotive Engineering, 2025, 47(4): 614-624.
[6]	Jinhui Suo, Xiaowei Wang, Peiwen Jiang, Chi Ding, Ming Gao, Yougang Bian. Domain Adaptive Visual Object Detection for Autonomous Driving Based on Multi-granularity Relation Reasoning [J]. Automotive Engineering, 2025, 47(2): 201-210.
[7]	Jiangkun Li,Ruixue Zong,Weiwen Deng,Ying Wang,Juan Ding. Directed Graph-Based Method for Evaluating Similarity in Urban Intersection Scenarios [J]. Automotive Engineering, 2025, 47(1): 23-34.
[8]	Daofei Li,Hao Pan. Application of Scenario Complexity Evaluation in Trajectory Prediction and Automated Driving Decision-Making [J]. Automotive Engineering, 2024, 46(9): 1556-1563.
[9]	Hai Wang,Jianguo Li,Yingfeng Cai,Long Chen. A LiDAR-Based Dynamic Driving Scene Multi-task Segmentation Network [J]. Automotive Engineering, 2024, 46(9): 1608-1616.
[10]	Jianan Zhang,Zhaozheng Hu,Jie Meng,Huahua Hu,Jie Zuo. Distributed Simulation Platform Architecture and Application of Autonomous Driving for Vehicle-Road-Map Collaboration [J]. Automotive Engineering, 2024, 46(8): 1335-1345.
[11]	Le Tao,Hai Wang,Yingfeng Cai,Long Chen. Multi-object Detection Algorithm Based on Point Cloud for Autonomous Driving Scenarios [J]. Automotive Engineering, 2024, 46(7): 1208-1218.
[12]	Linhui Li,Yifan Fu,Ting Wang,Xuecheng Wang,Jing Lian. Trajectory Prediction Method Enhanced by Self-supervised Pretraining [J]. Automotive Engineering, 2024, 46(7): 1219-1227.
[13]	Lisheng Jin,Hongyu Zhang,Baicang Guo. Semi Solid-State LiDAR Object Detection Algorithm Enhanced by Feature Stability Enhancement [J]. Automotive Engineering, 2024, 46(6): 1015-1024.
[14]	Hai Wang,Yuxuan Ding,Tong Luo,Meng Qiu,Yingfeng Cai,Long Chen. A Multi-class Multi-target Tracking Algorithm Combining Motion Speed and Appearance Features in Driving Scenarios [J]. Automotive Engineering, 2024, 46(6): 956-964.
[15]	Jing Huang,Xiangzhen Liu,Xiaoyang Deng,Ran Chen. Research on Intelligent Vehicle Trajectory Planning Based on Multimodal Trajectory Prediction [J]. Automotive Engineering, 2024, 46(6): 965-974.

Three-Dimensional Multi-object Tracking Algorithm Based on Angle Intersection over Union and Adaptive Lifecycle

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 20

Related Articles 15

Metrics

Comments

Recommended 0