An Algorithm for Extracting Geometric Features from Point Cloud

Author

Pang, Xu-Fang ; Pang, Ming-Yong

Author_Institution

Dept. of Educ. Technol., Nanjing Normal Univ., Nanjing, China

Volume

4

fYear

2009

fDate

26-27 Dec. 2009

Firstpage

78

Lastpage

83

Abstract

We proposed a robust algorithm for valley-ridge extraction from point set. Our algorithm separately flag potential valley points and ridge points according to principle curvature of every point, then enhance the valley-ridge points by projecting them onto their local nearest potential valleys or ridges. Using an optimized principal covariance analysis approach, we smooth the projected points, finally valley-ridge lines are obtained after resolving gaps and relaxing the results.

Keywords

covariance analysis; feature extraction; surface fitting; geometric feature extraction; principal covariance analysis; ridge points; valley points; valley-ridge extraction algorithm; Clouds; Data mining; Feature extraction; Least squares approximation; Least squares methods; Multilevel systems; Robustness; Shape; Surface fitting; Surface reconstruction; MLS surface fitting; ridges; valley-ridge extraction; valleys;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Management, Innovation Management and Industrial Engineering, 2009 International Conference on

Conference_Location

Xi´an

Print_ISBN

978-0-7695-3876-1

Type

conf

DOI

10.1109/ICIII.2009.481

Filename

5370283