一种轮廓跟踪的UPF方法
首发时间:2005-12-28
摘要:针对通用目标轮廓跟踪中CONDENSATION 粒子算法的不足,提出一种轮廓跟踪的UPF方法。通过将Unscented 卡尔曼滤波器与粒子滤波的结合,并实时考虑观测值,可以精确的、实时的跟踪目标区域,并且对背景干扰具有很强的鲁棒性。
For information in English, please click here
One Method of Object Contour-tracking Based on Unscented Particle Filter
Abstract:One method of object contour-tracking based on unscented particle filter is proposed in the paper, considered on the deficiency of CONDENSATION method on the object contour-tracking. In the algorithm it is used that is combining Unscented Kalman Filter with Particle filter and observation values are taken into account in, so real-time object contour is tracked accurately. what is more, the method is of strong robusticity on background disturbance.
Keywords: contour tracking, Unscented Particle Filter method, robusticity
论文图表:
引用
No.4725296381135742****
同行评议
共计0人参与
勘误表
一种轮廓跟踪的UPF方法
评论
全部评论0/1000