融合k-means聚类和Hausdorff距离的散乱点云精简算法

Scattered Point Cloud Simplification Algorithm Integrating k-means Clustering and Hausdorff Distance

针对点云精简算法在处理点云数据时特征保留不完整和对小曲率点云精简造成数据空洞的问题,提出了一种融合k-means聚类和Hausdorff距离的点云精简算法。该算法在八叉树算法的基础上构建点云数据的拓扑关系,首先计算所有点云数据点的主曲率,然后计算点云数据点主曲率的Hausdorff距离,根据精简目标要求设定Hausdorff距离阈值,实现点云特征提取,最后对非特征区域进行k-means聚类提取特征点,并将两次提取的特征点融合得到精简结果。实验结果表明,该算法能较完整地保留模型的特征信息,并能避免形成空洞现象。

Aiming at the incomplete retention of features during the point cloud data procession by point cloud simplification algorithm,and data holes caused by small-curvature point cloud simplification algorithm,this paper proposes a new point cloud simplification algorithm integrated k-means clustering and Hausdorff distance.The topological adjacency is established in the new simplification algorithm based on the OcTree algorithm.Then the principal curvatures of all point cloud is calculated and the Hausdorff distance of the principal curvatures is calculated,and the Hausdorff distance threshold set by the requirements of the reduced target is used to extracted the point cloud feature.Finally,k-means clustering is performed on non-feature regions to extract feature points,and the extracted feature points are merged to obtain reduced results.Results show that the proposed algorithm can retain the feature information of the model more completely and avoid the void phenomena.