基于关键点的边界增强改进点云配准算法

Improved point cloud alignment algorithm with key point based boundary enhancement

针对点云配准出现的误匹配、耗时长、精度不高等问题,提出一种基于关键点E-ISS(edge based intrinsic shape signatures)的边界增强点云配准算法。首先对源点云和目标点云进行采样、主方向变换、关键点提取、网格边界点云提取,并将特征点和边界点云融合为一个新的特征点集E-ISS。对其建立快速直方图统计特征,利用算法进行配准。最后与几何采样后的配准结果、提取关键点的配准结果对比表明,所提出的改进方法在相同配准效果下,配准时间稳定在4.83 s,欧拉适应度得分为0.29,配准的均方根误差在0.093 mm内,解决了配准发动机叶片的过程中出现局部最优而导致配准失败的现象,为后续的叶片损伤定位奠定了基础。

A boundary-enhanced point cloud alignment algorithm based on key point E-ISS(edge based intrinsic shape signatures)is proposed to address the problems of mis-matching,time-consuming and low accuracy in point cloud alignment.Firstly,the source and target point clouds are sampled,principal direction transformed,key points extracted,and grid boundary point clouds extracted,and the feature points and boundary point clouds are fused into a new feature point set E-ISS,for which fast point feature histograms are established,and the alignment is performed using algorithm.Finally,the comparison with the alignment results after geometric sampling and extraction of key points shows that the proposed improved method has a stable alignment time of 4.83 s,the Euler adaptation score of 0.29,and the alignment error within 0.093 mm under the same alignment effect,which greatly solves the phenomenon of alignment failure due to local optimum in the process of aligning engine blades and provides a basis for subsequent blade damage positioning.