基于自适应粒子滤波的摄像机位姿估计方法

New camera pose estimation method based on adaptive particle filter

提出一种基于自适应粒子滤波的摄像机位姿估计方法。该方法首先利用相邻两帧传递模型的噪声方差动态调整传递模型,接着利用内点统计方法计算粒子权值,在对权值作归一化运算之后,利用粒子加权和计算摄像机位置和姿态。实验结果表明该方法很大程度上提高了基于标识的摄像机位姿估计系统的健壮性与稳定性。

A new adaptive particle filter based camera pose estimation method was implemented. The noise variance between two adjacent ＇frames to update the prediction model dynamically, and then interior points statistical method was used to calculate the weight. After normalizing the weight, the position and orientation of the camera were calculated. Experimental results show that this method improves the robustness and practicability of marker-based systems.