鲁棒的点云曲线骨骼提取算法

Robust curve-skeleton extraction algorithm of point cloud

为解决复杂点云数据的曲线骨骼提取问题,提出了一种鲁棒的点云曲线骨骼提取算法。该方法首先通过区域分割将点云模型分成多个弱凸面集,减少噪声点对骨骼提取的影响,然后在每个弱凸面集中根据对称点信息提取候选骨骼点,对候选骨骼点进行压缩和平滑,并采用最优平面法对骨骼点进行重定位,最后利用区域分割信息将各区域的骨骼点连接得到最终的曲线骨骼。实验结果表明,该方法不仅能够处理完整和非完整的点云数据,而且能够正确提取包含复杂形状的点云骨骼。

A robust curve-skeleton extraction algorithm of point cloud is proposed to solve the curve skeleton extraction problems of point cloud including complex geometry. First, the point cloud is over-segmented into a set of weak-convex patches which is not sensitive to noises, then candidate skeletal points are extracted by antipodes in each weak convex patches, the candidate skeletal points are compressed and smoothed, and the candidate skeletal points are re-centered by optimal cut plane. Finally, the skeletal points are connected by the segment information to extract the final curve-skeleton.This method is not only able to handle the complete and incomplete point cloud, but also can correctly extract curve-skeleton from point cloud containing complex geometry.