Shape Recognition in 3D Point-Clouds

V. Skala (Editoren)
In proceedings of The 16-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2008, UNION Agency-Science Press, Feb. 2008
Präsentiert: The 16-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2008 (WSCG'2008)
 

Abstract

While the recent improvements in geometry acquisition techniques allow for the easy generation of large and detailed point cloud representations of real-world objects, tasks as basic as for example the selection of all windows in 3D laser range data of a house still require a disproportional amount of user interaction. In this paper we address this issue and present a flexible framework for the rapid detection of such features in large point clouds. Features are represented as constrained graphs that describe configurations of basic shapes, e.g. planes, cylinders, etc. Experimental results in various scenarios related to the architectural domain demonstrate the feasibility of our approach.

Bilder

Paper herunterladen

Paper herunterladen

Bibtex

@INPROCEEDINGS{schnabel-2008-shape,
      author = {Schnabel, Ruwen and Wessel, Raoul and Wahl, Roland and Klein, Reinhard},
      editor = {Skala, V.},
       title = {Shape Recognition in 3D Point-Clouds},
   booktitle = {The 16-th International Conference in Central Europe on Computer Graphics, Visualization and
                Computer Vision'2008},
        year = {2008},
       month = feb,
   publisher = {UNION Agency-Science Press},
    abstract = {While the recent improvements in geometry acquisition techniques allow for the easy generation of
                large and detailed point cloud representations of real-world objects, tasks as basic as for example
                the selection of all windows in 3D laser range data of a house still require a disproportional
                amount of user interaction. In this paper we address this issue and present a flexible framework for
                the rapid detection of such features in large point clouds. Features are represented as constrained
                graphs that describe configurations of basic shapes, e.g. planes, cylinders, etc. Experimental
                results in various scenarios related to the architectural domain demonstrate the feasibility of our
                approach.},
        isbn = {978-80-86943-15-2},
  conference = {The 16-th International Conference in Central Europe on Computer Graphics, Visualization and
                Computer Vision'2008 (WSCG'2008)}
}