基于二维图像特征的点云配准方法

为了提高低覆盖率点云的配准精度和收敛速度，提出了一种基于二维图像特征的点云配准方法。首先采用基于区域层次的点云配准算法实现粗配准；然后将三维点云转换成二维图像，再采用SURF算法提取二维图像的特征，并求解其匹配像素点对；最后根据二维匹配点获取相应的三维点云相关点，并计算刚体变换，由此实现点云的快速精确配准。试验结果表明，与迭代最近点（ICP）算法相比，该点云配准方法的配准精度和耗时分别提高了约20%和60%，是一种快速、高精度的点云配准算法。

Point Cloud Registration Method Based on 2D Image Feature

A point cloud registration method is proposed in the paper in order to improve the registration accuracy and convergence rate of low overlapping point clouds.Firstly,a point cloud registration algorithm based on region level is used to complete coarse registration;Secondly,3D point cloud is converted into 2D image,SURF( speeded up robust features) algorithm is used to extract 2D image features, and the matching pixel pairs are solved;Finally,3D corresponding points are gotten according to the 2D matching pixels,and the rigid transformation is solved,then the fast and accurate registration of point cloud are achieved. The experimental results showed that the registration accuracy and convergence rate of proposed point cloud registration method improved about 20% and 60% respectively compared with iterative closest point(ICP)algorithm,it is a high accurate and fast point cloud registration method.