基于ICP与光流法结合的Kinect配准算法

Kinect Registration Algorithm Based on the Combined Optical Flow and ICP Algorithm

为了提高相机跟踪准确性,本文提出光流法和ICP算法结合的算法,重建阶段使用ICP算法重建好场景,然后通过ICP算法初始化得到三维点坐标,再使用光流法跟踪定位相机。实验结果表明,结合点云匹配算法和光流法计算相机姿态,能够充分发挥两个算法的优点,避免各自的缺陷,提高相机跟踪稳定性。

In order to improve the tracking accuracy of the camera,this paper proposes to combine optical flow and ICP algorithm. We use the ICP algorithm to reconstruct the scene and use the optical flow to track camera position. Experimental results show that our method can give full play to the advantages of the two algorithms,and improve the stability of camera tracking obviously.