计算机工程2009，Vol.35Issue(22)：207-209,3.
改进的交互式多模型跟踪算法
Improved Interacting Multiple Model Tracking Algorithm
摘要
Abstract
Aiming at the singleness of implementing the regularized filter in interacting multiple model algorithm, an improved algorithm is proposed, in which Kalman Filter(KF) is used to match the linear part of the system and Particle Filter(PF) is used to match the non-linear part of the system, the degree of occlusion is determined according to the match extent. When the serious occlusion exists, the iterafive multistage Particle Filter is exploited for re-sampling, then combined with Kalman Filter to update the model probability. Experimental results show that the proposed algorithm meets the real-time requirement, improves the speed of the model filter and the estimated accuracy of the object state, and reduces the computing time effectively. It solves the occlusion problem in the process of tracking.关键词
目标跟踪/卡尔曼滤波/粒子滤波/交互式多模型/遮挡Key words
object tracking/Kalman Filter(KF)/Particle Filter(PF)/Interacting Multiple MOdel(IMM)/occlusion分类
信息技术与安全科学引用本文复制引用
刘涛,李明,骆瑞玲..改进的交互式多模型跟踪算法[J].计算机工程,2009,35(22):207-209,3.基金项目
甘肃省自然科学基金资助项目(0803RJZA025) （0803RJZA025）
