An Improved Particle Filter Algorithm Based on Neural Network for Visual Tracking

摘要：

Due to the shortcoming of constructing importance density in general particle filter, we propose an improvedalgorithm based on neural network to optimize the choice of importance density. It is proved to be more efficient than the general algorithm in the same sample size. This algorithm adjusts the samples drawn from prior density with generalregression neural network (GRNN), and makes them approximate the importance density. Finally, the newalgorithm is used to solve the target-tracking problem.Simulation shows that the proposed algorithm makes the resultmore precise than the general particle filter.

作者: Wen Qin Qicong Peng

作者单位: School of Communication and Information Engineering University of Electronic Science and Technology of China Chengdu, Sichuan, China

会议类型: 国际会议

会议名称: 2007年通信、电路与系统国际会议(2007 International Conference on Communications,Circuits and Systems Proceedings)

会议地点: 日本福冈

会议语种:英文

在线出版日期: 2007-07-11（万方平台首次上网日期，不代表论文的发表时间）