摘要
提出了一种基于k均值(k-means)聚类的点云精简方法。与包围盒法相比,在压缩率近似相同的条件下,kmeans聚类方法能较好地保留细节特征,与原始数据的稠密稀疏分布更加一致,所建模型表面更光滑。
A point cloud simplification method is proposed based on k-means clustering. Compared with the bounding box method with a similar compression rate, the k-means clustering method can preserve the details better, and the result is more consistent with the dense and sparse distribution of the original data. Moreover, the surface of the constructed model is smoother.
作者
贺一波
陈冉丽
吴侃
段志鑫
He Yibo;Chen Ranli;Wu Kan;Duan Zhixin(Department of Architecture and Civil Engineering, Datong Vocational a nd Technical College of Coal,Datong, Shanxi 037003, China;Department of Surveying Engineering, Sh ijiazh uang Institute of Rail way Technology, Sh ijiazhuang,Hebei 050041, China;School of Environment Science a nd Spatial Informatics, Ch ina U)iiversity of Mining and Technology,Xuzhou, Jiangsu 221116, China)
出处
《激光与光电子学进展》
CSCD
北大核心
2019年第9期88-91,共4页
Laser & Optoelectronics Progress
关键词
图像处理
点云精简
K均值聚类
曲面拟合
均方根曲率
压缩率
image processing
point cloud simplification
k-means clustering
surface fitting
root mean square curvature
compression rate
