现阶段,卡尔曼滤波是信息融合领域中广泛使用的融合算法,它在线性高斯模型下能得到最优估计,但在非线性非高斯的模型下不能达到理想的效果.在这种情况下,非线性目标跟踪已被人们广泛重视.扩展卡尔曼滤波器(EKF)是将卡尔曼滤波器(KF)进行Taylor展开,算法简单,计算快捷,适用于非线性程度不强,高斯的环境下.不敏卡尔曼滤波(UKF)是先对状态向量的后验概率密度函数(PDF)进行近似化然后再在标准卡尔曼滤波框架下进行递推滤波.粒子滤波是一种基于蒙特卡罗模拟和递推贝叶斯估计的滤波方法.这种滤波的方法和其他滤波的方法一样,都是可以通过系统的模型方程从测量空间一步步递推得到其相应的状态空间.它可以处理模型方程为非线性、噪声分布为非高斯分布的问题,在许多领域得到了成功的应用.论文中通过仿真试验,进行跟踪性能的比较,结果证明在复杂的非高斯非线性环境中,粒子滤波器的性能要明显优于扩展卡尔曼滤波器.%At this stage, Kalman filter has been widely used in the field of information fusion. It can get the optimal estimate in the linear Gauss model, but it can not be achieved the desired results in non-linear, non-Gaussian models. In this case, the nonlinear target-tracking method has been extensive researched. Extended Kalman filter(EKF) based on local linearization of KF, for Taylor expansion, the algorithm is simple, fast computation speed, is applied to the nonlinear degree is not strong, Gauss environment. Unscented Kalman filter(UKF) is the state vector of the posterior probability density function(PDF) are approximation and then in the standard Kalman filter framework of recursive filtering. Particle filter is a method based on recursive Bayesian filter and Monte Carle simulation. The method is suitable for any non-linear, non-Gaussian system that could be represented with state model. It has been successfully applied in many areas. In this paper, through the simulation experiment, the results prove the tracking performance of PF is much better than EKF in complex environment
展开▼
