Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Reliable Recovery of Piled Box-like Objects via Parabolically Deformable Superquadrics
 

Summary: Reliable Recovery of Piled Box-like Objects via Parabolically Deformable
Superquadrics
Dimitrios Katsoulas
University of Freiburg, Institute for Pattern Recognition and Image Processing
George Koehler Allee, 052 Freiburg, Germany
dkats@informatik.uni-freiburg.de
Abstract
Automatic unloading of piled box-like objects is un-
doubtedly of great importance to the industry. In this con-
tribution a system addressing this problem is described: We
employ a laser range finder for data acquisition, and glob-
ally deformable Superquadrics [2], [22] for object model-
ing. Our technique is based on a hypothesis generation and
refinement scheme. The vertices of the piled objects are ex-
tracted and Superquadric seeds are aligned at these ver-
tices. The model parameter recovery task is decomposed
into two subproblems, each dealing with a subset of the
model's parameter set. Both region and boundary based in-
formation sources are used for parameter estimation. Com-
pared to a widespread strategy for superquadric recovery

  

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

 

Collections: Computer Technologies and Information Sciences