Improved Target Tracking Algorithm Based on Particle Filtering

摘要：

Aiming at the filter problem of target tracking, the important density function and the re-sampling technique of Particle Filter Algorithm are improved in this paper. An approximation of the likelihood function is selected as the important density function. It not only makes the particles locate in the area of high likelihood, but also makes the current measurement value take part in directly. Further more, combined with re-sampling technique of the regular particle filter, the problem of particle degradation and impoverishment can be solved simultaneously. Simulation shows that the tracking accuracy of this new algorithm is increased by 20％-30％ compared with the general particle filter algorithms.

关键词： target tracking particle filter important density function re-sampling technique

作者: Yanyan Hu Juan Li Changgang Lu

作者单位: School of Communication EngineeringJilin UniversityChangchun, China Center of Test Science Jilin University Changchun, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information System and Computational Intelligence(2011 IEEE信息系统与计算智能国际会议 ICISCI 2011)

会议地点: 哈尔滨

会议语种:英文

页码: 1-4

在线出版日期: 2011-01-18（万方平台首次上网日期，不代表论文的发表时间）