Article Details

Abstract

To address the problems of inaccurate measurement set partitioning and high computational complexity in traditional group target tracking under clutter environments, this study proposes an improved density peak partitioning method. First, the correlation coefficient and the Gaussian kernel function are introduced to redefine the local density, thereby mitigating truncation distance errors; after clutter measurements with low density are filtered out, the improved density peak algorithm is used to preliminarily partition the measurement set and obtain the initial center. Second, to avoid overlap among measurement subsets, the gamma Gaussian inverse Wishart components with higher weights in the prediction step are selected, and a secondary partitioning process is executed according to the distance between their state means and the initial measurement center under different scenarios, so as to obtain a more precise measurement set partitioning result. Finally, an improved measurement likelihood function is derived, and multi-group target tracking is achieved through a gamma Gaussian inverse Wishart-probability hypothesis density filter. Simulation experiments show that the proposed method can effectively partition the measurement set under clutter environments and significantly improve group target tracking performance at a lower computational cost; compared with existing measurement set partitioning methods, it has a shorter average running time and higher tracking accuracy.

Keywords

group target tracking; density peaks clustering; measurement set partition; Gaussian inverse Wishart distribution; probability hypothesis density

References

1. [1] Jian Jianjuan, Han Leilei, Dong Kai, etc Research on Space Dense Group Target Association and Tracking Algorithm [J]. Fire and Command Control, 2020, 45 (8): 51-56
2. [2] Mihaylova L，Carmi A Y，Septier F，et al. Overview of Bayesian Sequential Monte Carlo Methods for Group and Extended Object Tracking [J].Digital Signal Processing，2014，25：1-16.
3. [3] Gan Linhai, Wang Gang, Liu Jin are busy, wait Overview of Group Target Tracking Technology [J]. Journal of Automation, 2020, 46 (3): 411-426
4. [4] Du Mingyang, Bi Daping, Pan Jifei, etc Adaptive correlation wave gate maneuvering group target tracking algorithm [J]. Journal of Beihang University, 2019, 45 (7): 1435-1443
5. [5] Shen X L，Song Z Y，Fan H Q，et al. Generalized Distance Partitioning for Multiple-Detection Tracking Filter Based on Random Finite Set [J].IET Radar Sonar & Navigation，2017，12（2）：260-267.
6. [6] Liu Fengmei, Ge Hongwei, Yang Jinlong, etc Extended target measurement set partitioning algorithm based on mean shift clustering [J]. Computer Engineering, 2014, 40 (12): 182-187194
7. [7] Yu Haofang, Sun Lifan, Fu Zhumu Multi extended object tracking algorithm based on improved K-means++clustering [J]. Computer Applications, 2020, 40 (1): 271-277
8. [8] Zhao Jia, Chen Lei, Wu Runxiu, etc K-nearest neighbor and weighted similarity density peak clustering algorithm [J]. Control Theory and Applications, 2022, 39 (12): 2349-2357
9. [9] Xu Xiao, Ding Shifei, Ding Ling Research progress on density peak clustering algorithm [J]. Journal of Software, 2022, 33 (5): 1800-1816
10. [10] Chen Hui, Zhao Weiwei Multi extended object tracking algorithm based on density fuzzy C-means measurement set partitioning [J]. Journal of Lanzhou University of Technology, 2018, 44 (3): 96-102
11. [11] Yan B，Xu N，Xu L P，et al. An Improved Partitioning Algorithm Based on FCM Algorithm for Extended Target Tracking in PHD Filter [J].Digital Signal Processing，2019，90：54-70.
12. [12] Jin Biao, Li Cong, Zhang Zhenkai A group target trajectory initiation method assisted by echo amplitude information [J]. Radar Journal, 2020, 9 (4): 723-729
13. [13] Mahler R. PHD Filters for Nonstandard Targets, I: Extended Targets [C]//2009 12th International Conference on Information Fusion，2009：915-921.
14. [14] Mahler R P S. Multitarget Bayes Filtering via First-order Multitarget Moments [J].IEEE Transactions on Aerospace and Electronic Systems，2003，39（4）：1152-1178.
15. [15] Koch J W. Bayesian Approach to Extended Object and Cluster Tracking Using Random Matrices [J].IEEE Transactions on Aerospace & Electronic Systems，2008，44（3）：1042-1059.
16. [16] Granstrom K，Lundquist C，Orguner O. A PHD Filter for Multiple Extended Targets Using Random Matrices [J].IEEE Transactions on Aerospace and Electronic Systems，2012，48（4）：3268-3286.
17. [17] Granstrom K，Orguner U. On Spawning and Combination of Extended/group Targets Modeled with Random Matrices [J].IEEE Transactions on Signal Processing，2012，61（3）：678-692.
18. [18] Zhang Yuan, Yang Jinlong, Xu Yue Grid driven PHD/CPHD filtering multi-target tracking algorithm [J]. Information and Control, 2020, 49 (5): 527-535
19. [19] Wang Yun, Hu Guoping, Gan Linhai Group target tracking algorithm based on multi model GGIW-CPHD filtering [J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2017, 45 (2): 89-94
20. [20] He Xiangyu, Li Jing, Yang Shuqiang, etc Extended target tracking algorithm based on ET-PHD filter and variational Bayesian approximation [J]. Computer Applications, 2020, 40 (12): 3701-3706
21. [21] Chen Jinguang, Zhao Tiantian, Wang Mingming, etc An improved algorithm with labeled GM-PHD for cross target scenarios [J]. Computer Engineering, 2018, 44 (6): 316-320
22. [22] Cai Ruhua, Yang Biao, Wu Sunyong Multi sensor box particle PHD filtering multi-target tracking algorithm [J]. Infrared Technology, 2020, 42 (4): 385-392
23. [23] Ma Shuhua, You Hairong, Tang Liang, etc An adaptive density peak clustering algorithm [J]. Journal of Northeastern University (Natural Science Edition), 2022, 43 (6): 761-768
24. [24] Tang Fengyang, Qin Renchao, Xiong Jian Density Peak Clustering Algorithm Based on Local Density Information Entropy Mean [J]. Computer Measurement and Control, 2022, 30 (3): 192-197203
25. [25] Sun Lin, Qin Xiaoying, Xu Jiucheng, etc Density peak clustering algorithm based on K-nearest neighbor and optimized allocation strategy [J]. Journal of Software, 2022, 33 (4): 1390-1411

Funding

Key Major Construction of Tianping College, Suzhou University of Science and Technology in 2024 (2024TPZY-03); Project of Teaching and Research Reform at Tianping College, Suzhou University of Science and Technology in 2025 (2025TJGB-05); 2024 Key Course Construction Project of Tianping College, Suzhou University of Science and Technology (2024TPKC-04)

About the authors

Zhang Lu (March 1997-), female, Han ethnicity, from Lvliang, Shanxi, full-time teacher, teaching assistant, master's student, research interests include signal and information processing technologies.