首页 | 官方网站   微博 | 高级检索  
     

A new fast algorithm for multitarget tracking in dense
作者姓名:Weihua QIN  Fei HU  Chaoyin QIN
作者单位:[1]Deparmaent of Computer Science and Engineering, Norflawestem Polytechnic University, Xi'an Shaaanxi 710072, China; [2]Department of Applied Mathematics, Northwestern Polytedmic University, Xi'an Shanxi 710072, China
摘    要:A fast joint probabilistic data association (FJPDA) algorithm is proposed in tiffs paper. Cluster probability matrix is approximately calculated by a new method, whose elements βi^t(K) can be taken as evaluation functions. According to values of βi^t(K), N events with larger joint probabilities can be searched out as the events with guiding joint probabilities, tiros, the number of searching nodes will be greatly reduced. As a result, this method effectively reduces the calculation load and nnkes it possible to be realized on real-thne, Theoretical ,analysis and Monte Carlo simulation results show that this method is efficient.

关 键 词:多目标跟踪  概率矩阵  搜索树  数据联合  快速算法
收稿时间:2004-10-09
修稿时间:2005-09-05

A new fast algorithm f or multitarget t racking in dense clutter
Weihua QIN,Fei HU,Chaoyin QIN.A new fast algorithm for multitarget tracking in dense[J].Journal of Control Theory and Applications,2005,3(4):383-386.
Authors:Weihua QIN  Fei HU  Chaoyin QIN
Affiliation:(1) Department of Computer Science and Engineering, Northwestern Polytechnic University, 710072 Xi’an, Shaanxi, China;(2) Department of Applied Mathematics, Northwestern Polytechnic University, 710072 Xi’an, Shaanxi, China
Abstract:A fast joint probabilistic data association (FJPDA) algorithm is proposed in this paper. Cluster probability matrix is approximately calculated by a new method, whose elements β i t (K) can be taken as evaluation functions. According to values of β i t (K) events with larger joint probabilities can be searched out as the events with guiding joint probabilities, thus, the number of searching nodes will be greatly reduced. As a result, this method effectively reduces the calculation load and makes it possible to be realized on real-time. Theoretical analysis and Monte Carlo simulation results show that this method is efficient. Weihua QIN was born in Xi’an, China, In 1963. He received the M.S. degree in electrical and computer engineering from Xidian University in 1995. He is currendy working for his Ph.D. degree in department of computer science and engineering from Northwestern Polytechnic University. During 1984 to 1992, he was an engineer at Loran-C transmitter. During 1995 to 2001, he was a senior engineer at Loran-C receiver. Since 2001, he has been working at the tactical data — link system. His main research interests include data processing, multiple target tracking, multi-sensor information fusion and radio navigation. E-mail: Qin8878@163.com Fei HU was born in Xi’an, China, In 1968. He received the B. S. degree and Ph. D. degree in Computer Software from Northwestern Polytechnic University in 1993 and 1998, respectively. As a professor and executive vice dean he works with the Software College, Northwestern Polytechnic University. His research interest lies in the areas of computer control, software testing, and real time systems. E-mail: hufei@nwpu.edu.en. Chaoyin QEV was born in Xi’an, China, In 1958. He received the B. S. degree in Applied Mathematics and Ph. D. degree in Control Theory and Control Engineering from Northwestern Polytechnic University in 1987 and 19%, respectively. He is currendy an associate professor I of Northwestern Polytechnic University. His main research interests are in control theory and its application, and multi-sensor information fusion. E-mail: Qinhuayu@nwpu.edu.en.
Keywords:Data association  Multitarget tracking  Cluster probability matrix  Search-tree
本文献已被 CNKI 维普 SpringerLink 等数据库收录!
点击此处可从《控制理论与应用(英文版)》浏览原始摘要信息
点击此处可从《控制理论与应用(英文版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号