|
|
论文:2017,Vol:35,Issue(4):629-634 |
|
|
引用本文： |
|
|
陈晓, 李亚安, 蔚婧, 李余兴. 基于最大熵模糊聚类的快速多目标跟踪算法研究[J]. 西北工业大学学报 |
|
|
Chen Xiao, Li Yaan, Yu Jing, Li Yuxing. A Fast Multi-Target Tracking Algorithm Based on Maximum Entropy Fuzzy Clustering[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于最大熵模糊聚类的快速多目标跟踪算法研究 |
|
| 陈晓, 李亚安, 蔚婧, 李余兴 |
|
| 西北工业大学 航海学院, 陕西 西安 710072 |
| 摘要: |
| 为了提高杂波环境中多目标跟踪的实时性和精确性，利用最大熵数据模糊聚类方法得到的模糊隶属度表示目标与量测之间的关联概率，同时分析了公共量测对目标的影响，引入影响因子重建互联概率矩阵，结合概率数据关联算法实现多目标的状态估计。该算法避免了对确认矩阵的拆分，解决了联合概率数据关联算法随着目标和回波数目增加而导致的计算量爆炸性增长问题。针对不同杂波密度环境下的临近平行目标和小角度交叉目标的跟踪进行了仿真分析，仿真结果表明：最大熵模糊聚类联合概率数据关联算法是一种有效的快速数据关联算法，在密集杂波环境中跟踪性能依然优于联合概率数据关联算法和经验联合概率数据关联算法，在一定程度上可以避免航迹融合。 |
| 关键词:
多目标跟踪
联合概率数据关联
经验联合概率数据关联
最大熵模糊聚类联合概率数据关联
|
|
| A Fast Multi-Target Tracking Algorithm Based on Maximum Entropy Fuzzy Clustering |
|
| Chen Xiao, Li Yaan, Yu Jing, Li Yuxing |
|
| School of Marine Science and Technology, Northwestern Ploytechnical University, Xi'an 710072, China |
| Abstract: |
| In order to improve the real-time and the accuracy of tracking multi-target in dense clutter environment,a new data association algorithm based on maximum entropy fuzzy clustering data association was introduced in this paper, which uses fuzzy membership matrix to express the association probability between target and measurement. At the same time, the effect of the public measurement to the target was analyzed, which uses impact factor to reconstruct association probability matrix, combining with the probabilistic data association algorithm to estimate the state of target. This algorithm avoids the splitting the confirmation matrix, so it can solve the problem of the high computational load of the joint probabilistic data association algorithm with the increase of the clutter and target. In addition, simulation and analysis are carried out for tracking parallel targets and cross targets in different clutter density environment. Simulation shows that this algorithm is an efficient and fast data association algorithm, and the tracking performance is superior to the joint probabilistic data association algorithm and the cheap joint probabilistic data association algorithm in dense clutter environment, and also can avoiding the tracking coalescence to a certain extent. |
| Key words:
multi-target tracking
joint probabilistic data association algorithm(JPDA)
cheap joint probabilistic data association algorithm(CJPDA)
maximum entropy fuzzy clustering joint probabilistic data association(MEF-JPDA)
fuzzy clustering
target tracking
MATLAB
|
|
| 收稿日期: 2017-02-08
修回日期:
|
| DOI: |
| 基金项目: 2017-02-28国家自然科学基金（51179157、51409214、11574250）赞助 |
| 通讯作者:
Email： |
| 作者简介: 陈晓(1986—),女,西北工业大学博士研究生,主要从事目标跟踪及非线性滤波研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 陈晓 在本刊中的所有文章 |
| 李亚安 在本刊中的所有文章 |
| 蔚婧 在本刊中的所有文章 |
| 李余兴 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Öksüz K. The Comparison of the Performances of Global Nearest Neighbor and Probability Hypothesis Density Filter for Varying Clutter Rates[C]//Proceedings of the 2016 24th Signal Processing and Communication Application Conference, Zonguldak, Turkey, 2016: 677-680
[2] Mcgee J A, Luginbuhl T E, Dibiase J H, et al. A Modified PDAF Algorithm for Measurement Covariances that Vary within a Time Scan[J]. IEEE Trans on Aerospace and Electronic Systems, 2012, 48(1): 906-912
[3] Habtemariam B, Tharmarasa R, Thayaparan T, Mallick M, Kirubarajan T. A Multiple-Detection Joint Probabilistic Data Association Filter[J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7(3): 461-471
[4] Reid D B. An Algorithm for Tracking Multiple Targets[J]. IEEE Trans on Automatic Control, 1979, 24(6): 843-854
[5] Mahler R. PHD Filters of Higher Order in Target Number[J]. IEEE Trans on Aerospace and Electronic Systems, 2007, 43(4): 1523-1543
[6] Mahler R, Vo B T, Vo B N. Forward-Backward Probability Hypothesis Density Smoothing[J]. IEEE Trans on Aerospace and Electronic Systems, 2012, 48(1): 707-728
[7] Zhi Liu, Minghui Wang. A Multi-Sensor Fusion Algorithm with Feedback Based on Fuzzy C-Means and Maximum Entropy Principle[C]//2010 International Conference on Intelligent System Design and Engineering Application, Changsha, China, 2010: 80-84
[8] Son H S, Park J B, Joo Y H. Tracking Algorithm Compensating Acceleration for 3D Maneuvering Target with PSO-FCM[C]//2012 IEEE International Conference on Fuzzy Systems, Brisbane, Australia, 2012: 1-7
[9] Gong Maoguo, Su Linzhi, Jia Meng. Fuzzy Clustering with a Modified MRF Energy Function for Change Detection in Synthetic Aperture Radar Images[J]. IEEE Trans on Fuzzy Systems, 2014,22(4): 98-109
[10] Qian Pengjiang, Jiang Yizhang, Deng Zhaohong, et al. Cluster Prototypes and Fuzzy Memberships Jointly Leveraged Cross-Domain Maximum Entropy Clustering[J]. IEEE Trans on Cybernetics,2016,46(1):181-193
[11] Peter X Liu, Max Q, Meng H. Online Data-Driven Fuzzy Clustering with Applications to Real-Time Robotic Tracking[J]. IEEE Trans on Fuzzy Systems,2004, 12(4): 516-523
[12] Li Liangqun, Ji Hongbing, Gao Xinbo. Maximum Entropy Fuzzy Clustering with Application to Real-Time Target Tracking[J]. Signal Processing, 2006, 86(2006): 3432-3447
[13] Turkmen I, Guney K. Cheap Joint Probabilistic Data Association with Adaptive Neuro-Fuzzy Inference System State Filter for Tracking Multiple Targets in Clustered Environment[J]. International journal of Electronics and Communications, 2004, 58(2004): 349-357 |
|
|
|
|
|
|
|
