基于SIFT特征点的点云配准方法  

Point Cloud Registration Method Based on SIFT Feature Points

作　　者：张少玉 ZHANG Shaoyu(Xi'an Polytechnic University,Xi'an 710048)

机构地区：[1]西安工程大学,西安710048

出　　处：《计算机与数字工程》2018年第3期449-453,共5页Computer & Digital Engineering

摘　　要：点云配准是三维建模过程中的关键问题之一。经典的ICP算法速度较慢,尤其是在点云数据较大的情况下用时更长。因此提出了一种改进方法。首先对两片点云进行体素栅格下采样,其次找出源点云的SIFT特征点并保存成点云,然后调用ICP算法,使用保存的SIFT特征点点云与目标点云进行配准,并通过RANSAC算法去除错误点对,保留变换后的源点云,重复上述过程,用以提高精度,直到满足收敛条件。实验表明,该文方法不仅速度较快,而且精度较好。Point cloud registration is one of the key problems in the process of3D modeling.Classical ICP algorithm is slower,especially in the case of large point cloud data takes longer time.Therefore an improved method is proposed.Firstly get the voxel grid sampling of the two pieces of point cloud,secondly find out the SIFT feature points of the source point cloud and save them into a piece of point cloud,and then call the ICP algorithm,using the saved SIFT feature point point cloud to regist the target point cloud,and remove the false matches through RANSAC algorithm,lastly keep the transformed source point cloud and repeat the above process until meet the convergence condition to improve the precision.Experiments show that the method is not only faster,but also more accurate.

关 键 词：点云配准 ICP算法 SIFT特征点 RANSAC算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]