Neighbor detection in point clouds using the Boundary Complex

Information

• Publication Type: Bachelor Thesis
• Workgroup(s)/Project(s):
  • Rendering and Modeling
• Date: February 2013
• Date (Start): 1. October 2012
• Date (End): 26. February 2013
• Matrikelnummer: 0927175
• First Supervisor:
  • Michael Wimmer
  • Stefan Ohrhallinger
• Keywords: segmentation, neighbor detection, clustering, boundary complex, point cloud

Abstract

For many applications (e.g. robotic vision) it is important to separate the Point Clouds produced by a 3D scanner into logically associated clusters in order to recognize objects or surfaces. A crucial part of most of the existing segmentation approaches is the definition of neighborhood between points. This thesis describes and evaluates the use of the ‘Boundary Complex’, a spanning connected set of triangles on the point cloud, for neighbor detection in the context of cloud segmentation. The results will be compared to existing neighbor picking approaches.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@bachelorsthesis{brenner_simon-2013-ba,
  title =      "Neighbor detection in point clouds using the Boundary
               Complex",
  author =     "Simon Brenner",
  year =       "2013",
  abstract =   "For many applications (e.g. robotic vision) it is important
               to separate the Point Clouds produced by a 3D scanner into
               logically associated clusters in order to recognize objects
               or surfaces. A crucial part of most of the existing
               segmentation approaches is the definition of neighborhood
               between points. This thesis describes and evaluates the use
               of the ‘Boundary Complex’, a spanning connected set of
               triangles on the point cloud, for neighbor detection in the
               context of cloud segmentation. The results will be compared
               to existing neighbor picking approaches.",
  month =      feb,
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Institute of Computer Graphics and Algorithms, Vienna
               University of Technology ",
  keywords =   "segmentation, neighbor detection, clustering, boundary
               complex, point cloud",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2013/brenner_simon-2013-ba/",
}