基于随机有限集的UPF-CPHD多目标跟踪

doi:10.3969/j.issn.1000-436x.2012.12.019

通信学报 ›› 2012, Vol. 33 ›› Issue (12): 147-153.doi: 10.3969/j.issn.1000-436x.2012.12.019

基于随机有限集的UPF-CPHD多目标跟踪

王慧斌,陈哲,王鑫,马玉

河海大学计算机与信息学院，江苏南京 211100

出版日期:2012-12-25 发布日期:2017-07-15
基金资助:
国家自然科学基金资助项目

Random finite sets based UPF-CPHD multi-object tracking

Hui-bin WANG,Zhe CHEN,Xin WANG,Yu MA

College of Computer and Information Engineering,Hohai University,Nanjing 211100,China

Online:2012-12-25 Published:2017-07-15
Supported by:
The National Natural Science Foundation of China

摘要/Abstract

摘要：

摘要：提出一种基于随机有限集的无迹粒子基数概率假设密度滤波（UPF-CPHD,unscented particle filter-cardinality probability hypothesis density）的多目标跟踪方法。在粒子滤波框架下采用随机有限集（RFS,random finite sets）对多目标状态和观测进行描述。在UPF滤波框架下引入CPHD算法同时递推目标状态和目标数目，并计算最新观测信息，估计结果更加精确，弥补PHD 估计目标数目不可靠的缺点。仿真实验表明，UPF-CPHD 多目标跟踪方法能够降低超过50%的目标数目估计误差，并提高目标状态的估计精度。

关键词: 随机有限集, 多目标跟踪, 无迹粒子滤波, 基数概率假设密度滤波

Abstract:

A multiple tracking method based on UPF-CPHD was proposed,in which the state and observation of the object were both described by the random finite sets (RSF).The CPHD algorithm was also introduced into the UPF framework to simultaneously deduce the object state and object number,making the estimation more precise.The experimental results show that the proposed UPF-CPHD algorithm is able to improve the estimation accuracy of the object number and state,as well as enhance the object tracking results.

Key words: random finite sets, multi-object tracking, unscented particle filter, cardinality probability hypothesis density

王慧斌,陈哲,王鑫,马玉. 基于随机有限集的UPF-CPHD多目标跟踪[J]. 通信学报, 2012, 33(12): 147-153.

Hui-bin WANG,Zhe CHEN,Xin WANG,Yu MA. Random finite sets based UPF-CPHD multi-object tracking[J]. Journal on Communications, 2012, 33(12): 147-153.

图/表 6

图1

图2

图3

图4

图5

图6

参考文献 13

[1]	ZHANG J W , XIU J J , HE Y ,et al. Distributed interacted multisensor joint probabilistic data association algorithm based on D-S theory[J]. Science in China Series F:Information Sciences, 2006,49(2): 219-227.
[2]	刘宗香, 谢维信, 黄敬雄 . 模糊观测数据的关联和目标跟踪[J]. 信号处理, 2005,21(4): 335-354. LIU Z X , XIE W X , HUANG J X . Data association and target tracking with the fuzzy measurements[J]. Signal Processing, 2005,21(4): 335-354.
[3]	徐晓滨, 文成林, 刘荣利 . 基于随机集理论的多源信息统一表示与建模[J]. 电子学报, 2008,36(6): 1174-1181. XU X B , WEN C L , LIU R L . The unified method of describing and modeling multisource information based on random set theory[J]. Acta Electronica Sinica, 2008,36(6): 1174-1181.
[4]	MAHLER R . A theoretical foundation for the stein-winter probability hypothesis density (PHD) multi-target tracking approach[A]. MSS Nat’l Symp on Sensor and Data Fusion[C]. 2000.
[5]	PASHA S A , BA-NGU V , TUAN H D ,et al. A Gaussian mixture PHD filter for jump Markov system model[J]. IEEE Transactions on Aerospace and Electronic Systems, 2009,45(3): 919-936.
[6]	吕学斌, 游志胜, 周群彪 ,等. 基于无迹变换的概率假设密度滤波算法[J]. 系统仿真学报, 2009,21(3): 845-850. LV X B , YOU Z S , ZHOU Q B ,et al. Probability hypothesis density filter based on unscented transformation and its appli ion to multi-target tracking[J]. Journal of System Simulation, 2009,21(3): 845-850.
[7]	SIDENBLADH H , WIRKANDER S L . Tracking random sets of vehicles in terrain[A]. USA:IEEE Workshop on Multi-Object Tracking[C]. Madison,Wisconsin, 2003. 221-228
[8]	徐立中, 丁晓峰, 王鑫 ,等. 基于信赖域的序贯拟蒙特卡洛滤波算法[J]. 电子学报, 2011,39: 24-30. XU L Z , DING X F , WANG X ,et al. Trust region based sequential quasi-monte carlo filter[J]. Acta Electronica Sinica, 2011,39: 24-30.
[9]	徐立中, 李敏, 石爱业 ,等. 受昆虫视觉启发的多光谱遥感影像特征检测器模型[J]. 电子学报, 2011,39: 2497-2501. XU L Z , LI M , SHI A Y ,et al. Feature detector model for multi-spectral remote sensing image inspired by insect visua system[J]. Acta Electronica Sinica, 2011,39: 2497-2501.
[10]	MAHLER R . PHD filters of higher order in target number[J]. IEEE Transactions on Aerospace and Electronic Systems, 2007,43(4): 1523-1543.
[11]	VO B T , VO B N , CANTONI A . Analytic implementations of the cardinalized probability hypothesis density filter[J]. IEEE Transactions on Signal Processing, 2007,55(7): 3553-3567.
[12]	RUI Y , CHEN Y . Better proposal distributions:object tracking using unscented particle filte[A]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Reco nition[C]. 2001. 786-793.
[13]	HOFFMAN J , MAHLER R . Multitarget miss distance via optimal assignment[J]. IEEE Trans Sys,Man,and Cybernetics Part A (S10834427), 2004,34(3): 327-336.

基于随机有限集的UPF-CPHD多目标跟踪

Random finite sets based UPF-CPHD multi-object tracking

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 13

相关文章 2

Metrics

推荐阅读 0

[1]	柳超,张志国,孙进平. 基于幅度信息的海上多目标稳健跟踪方法[J]. 通信学报, 2019, 40(2): 60-69.
[2]	龙云利,盛卫东,徐晖,安玮. 锥扫型光学传感器像平面多目标轨迹跟踪[J]. 通信学报, 2011, 32(9): 123-128.