Presentation 2001/6/14
A probabilistic Approach to Surface Extraction from Range Data
Hidekazu Hirayu, Caihua Wang, Hideki Tanahashi, Yoshinori Niwa, Kazuhiko Yamamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we proposed a new method to model complex range data using parametric model. We first compute local surface curvatures by quadratic fitting of local surfaces, and then extract curved surfaces and plane regions from the range data by examining the probability distribution of local surface curvatures. Next, we obtain the parameters of individual equations for plane and curved surface regions. After the parameters of individual equations are obtained, we test the possibility of integration of neighboring regions. Experimental results on real range data show the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) local surface fitting / feature space / segmentation / fitting error / integration
Paper # PRMU2001-29
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/6/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A probabilistic Approach to Surface Extraction from Range Data
Sub Title (in English)
Keyword(1) local surface fitting
Keyword(2) feature space
Keyword(3) segmentation
Keyword(4) fitting error
Keyword(5) integration
1st Author's Name Hidekazu Hirayu
1st Author's Affiliation Office of Regional Intensive Research Project, Softopia Japan, JST()
2nd Author's Name Caihua Wang
2nd Author's Affiliation Office of Regional Intensive Research Project, Softopia Japan, JST
3rd Author's Name Hideki Tanahashi
3rd Author's Affiliation Office of Regional Intensive Research Project, Softopia Japan, JST
4th Author's Name Yoshinori Niwa
4th Author's Affiliation Office of Regional Intensive Research Project, Softopia Japan, JST
5th Author's Name Kazuhiko Yamamoto
5th Author's Affiliation Department of Information Science, Faculty of Engineering, Gifu University
Date 2001/6/14
Paper # PRMU2001-29
Volume (vol) vol.101
Number (no) 124
Page pp.pp.-
#Pages 6
Date of Issue