基于改进的卡尔曼滤波图像雅可比矩阵估计

On-line Estimation for Image Jacobian Matrix Based on Improved Kalman Filter

在分析现有的图像雅可比矩阵卡尔曼在线估计方法的基础上,对状态向量中的速度分量进行再估计,提出一种修正卡尔曼滤波器对目标物体远程运动估计的算法。与直接卡尔曼滤波器的远程运动估计相比,该算法提高了估计精度。将该算法进行仿真,其结果证明了算法的有效性。

By analyzing existing methods of image Jacobian matrix＇s Kalman on-line estimation, a method of object longterm estimation using modified Kalman filter by reestimating the velocity vector of system state vector is presented. Compared with object long-term estimation using Kalman filter directly, this method improves the estimation accuracy. A real-time algorithm using the modified Kalman filter is presented. The simulations results show the effectiveness of this algorithm.