CASIA OpenIR  > 类脑智能研究中心
Unstructured Point Cloud Surface Denoising and Decimation Using Distance RBF K-Nearest Neighbor Kernel
Rixio Morales; Yunhong Wang; Zhaoxiang Zhang
2010-09-21
Conference NamePacific-Rim Conference on Multimedia
Source PublicationPCM 2010
Conference Date21-24 September 2010
Conference PlaceShanghai, China
AbstractIn this work unstructured point clouds, resulting from 3D range acquisition are point wise-processed, using a proposed kd-tree nearest neighbor method, based in a generative data driven, local radial basis function’s (RBF) support:φ(S, pi(xi, yi, zi)), for the point set S : {pi}iI , using surface statistic and a Gaussian convolution kernel, point sets are smoothed according to local surface features. As a minor contribution we also present a point cloud semi-rigid grid decimation method, based on a similar framework, using multi-core hardware, experiment results achieve comparable quality results with existing and more complex methods; time performance and results are presented for comparison.
KeywordUnstructured Point Cloud Smoothing Decimation Rbf Multicore
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13299
Collection类脑智能研究中心
Corresponding AuthorZhaoxiang Zhang
Recommended Citation
GB/T 7714
Rixio Morales,Yunhong Wang,Zhaoxiang Zhang. Unstructured Point Cloud Surface Denoising and Decimation Using Distance RBF K-Nearest Neighbor Kernel[C],2010.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Rixio Morales]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Rixio Morales]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Rixio Morales]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.