Three-dimensional vehicle multi-target tracking based on trajectory optimization

被引：0

作者：

Cai, Hua ^{[1
]}

Kou, Ting-Ting ^{[1
,2
]}

Yang, Yi-Ning ^{[3
]}

Ma, Zhi-Yong ^{[4
]}

Wang, Wei-Gang ^{[4
]}

Sun, Jun-Xi ^{[5
]}

机构：

[1] School of electronic information engineering, Changchun University of Science and Technology, Changchun

[2] Industrial College of Artificial Intelligence, Changchun University of Architecture, Changchun

[3] National Key Laboratory of Electromagnetic Space Security, Tianjin

[4] No.2 Department of Urology, The First Hospital of Jilin University, Changchun

[5] School of Information Science and Technology, Northeast Normal University, Changchun

来源：

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2024年 / 54卷 / 08期

关键词：

3D Kalman filter; computer version; improved Hungarian algorithm; multi-target tracking; trajectory optimization;

D O I：

10.13229/j.cnki.jdxbgxb.20221373

中图分类号：

学科分类号：

摘要：

In order to solve the problem of poor tracking effect of multi-target tracking algorithm in the case of occlusion，a multi-target tracking algorithm based on 3D point cloud detection is proposed. The 3D target detector based on point cloud is used to detect the vehicle target and obtain the location information of the 3D target；The target position in the next frame is predicted by tracking the target position in the current frame through a three-dimensional Kalman filter；The intersection ratio of 3D center point space distance and cross-union ratio of bird's eye view is fused as the weight，and the improved Hungarian algorithm is used for data association；Aiming at the problem of label switching before and after occlusion，a trajectory optimization algorithm is proposed. Experiments were conducted on KITTI dataset，and the vehicle tracking accuracy and tracking accuracy reached 84.71% and 86.63% respectively. Under the same threshold，this method is 6.28% and 0.39% higher than AB3DMOT respectively. Experimental results show that this algorithm can effectively improve the performance of 3D multi-target tracking. © 2024 Editorial Board of Jilin University. All rights reserved.

引用

页码：2338 / 2347

页数：9

共 22 条

[1]

Qu you, Li Wen-hui, Multi target tracking method based on multi task joint learning, Journal of Jilin University(Engineering and Technology Edition), 53, 10, pp. 2932-2941, (2023)

[2]

Ding Gui-peng, Tao Gang, Pang Chun-qiao, Et al., Lightweight siamese network target tracking algo⁃ rithm based on ananchor free, Journal of Jilin Uni⁃ versity (Science Edition), 61, 4, pp. 890-898, (2023)

[3]

Cai Hua, Chen Guang-qiu, Liu Guang-wen, Et al., Novelty fragments-based target tracking with multi⁃ ple instance learning under occlusions, Journal of Ji⁃ lin University (Engineering and Technology Edition), 47, 1, pp. 281-287, (2017)

[4]

Li Xiao-feng, Ren Jie, Li Dong, Hierarchical match⁃ ing algorithm of visual image for mobile robots based on deep reinforcement learning, Journal of Jilin University (Science Edition), 61, 1, pp. 127-135, (2023)

[5]

Zhang W, Zhou H, Sun S, Et al., Robust multi- mo⁃ dality multi-object tracking, 2019 IEEE/CVF In⁃ ternational Conference on Computer Vision (ICCV), pp. 2365-2374, (2019)

[6]

Shenoi A, Patel M, Gwak J Y, Et al., JRMOT: a re⁃ al-time 3D multi-object tracker and a new large-scale dataset, 2020 IEEE/RSJ International Confer⁃ ence on Intelligent Robots and Systems (IROS), pp. 10335-10342, (2020)

[7]

Weng X S, Wang J R, Heldet D, Et al., 3D multi-ob⁃ ject tracking: a baseline and new evaluation metrics [C], 2020 IEEE/RSJ International Conference on In⁃ telligent Robots and Systems (IROS), pp. 10359-10366, (2020)

[8]

Yin T, Zhou X, Krahenbuhl P., Center-based 3D ob⁃ ject detection and tracking[C], 2021 IEEE/CVF Conference on Computer Vision and Pattern Recogni⁃ tion (CVPR), pp. 11779-11788, (2021)

[9]

Chen X, Kundu K, Zhang Z, Et al., Monocular 3D object detection for autonomous driving, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2147-2156, (2016)

[10]

Li B Y, Sheng L, Zeng X Y, Et al., GS3D: an effi⁃ cient 3D object detection framework for autonomous driving, 2019 IEEE/CVF Conference on Com⁃ puter Vision and Pattern Recognition (CVPR), pp. 1019-1028, (2019)

← 1 2 3 →