A new segmentation method for point cloud data

Citation
H. Woo et al., A new segmentation method for point cloud data, INT J MACH, 42(2), 2002, pp. 167-178
Citations number
19
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Mechanical Engineering
Journal title
INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
ISSN journal
0890-6955 → ACNP
Volume
42
Issue
2
Year of publication
2002
Pages
167 - 178
Database
ISI
SICI code
0890-6955(200201)42:2<167:ANSMFP>2.0.ZU;2-2
Abstract
In the process of generating a surface model from point cloud data, a segme ntation that extracts the edges and partitions the three-dimensional (3D) p oint data is necessary and plays an important role in fitting surface patch es and applying the scan data to the manufacturing process. Many researcher s have tried to develop segmentation methods by fitting curves or surfaces in order to extract geometric information, such as edges and smooth regions , from the scan data. However, the surface- or curve-fitting tasks take a l ong time and it is also difficult to extract the exact edge points because the scan data consist of discrete points and the edge points are not always included in these data. In this research, a new method for segmenting the point cloud data is proposed. The proposed algorithm uses the octree-based 3D-grid method to handle a large amount of unordered sets of point data, Th e final 3D-grids are constructed through a refinement process and iterative subdivisioning of cells using the normal values of points. This 3D-grid me thod enables us to extract edge-neighborhood points while considering the g eometric shape of a part. The proposed method is applied to two quadric mod els and the results are discussed. (C) 2001 Elsevier Science Ltd. All right s reserved.