Online semantic mapping of urban environments

  • Authors:
  • Nikos Mitsou;Roderick de Nijs;David Lenz;Johannes Frimberger;Dirk Wollherr;Kolja Kühnlenz;Costas Tzafestas

  • Affiliations:
  • Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany,School of Electrical and Computer Engineering, Division of Signals, Control and Robotics ...;Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany;Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany;Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany;Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany;Institute of Automatic Control Engineering (LSR), Technische Universität München, Munich, Germany;School of Electrical and Computer Engineering, Division of Signals, Control and Robotics, National Technical University of Athens, Greece

  • Venue:
  • SC'12 Proceedings of the 2012 international conference on Spatial Cognition VIII
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present an integrated approach for efficient online 3D semantic map building of urban environments and the subsequent extraction of qualitative spatial relationships between the different objects in the scene. We split this process into three stages, where we combine a state of the art image segmentation and classification algorithm with an online clustering algorithm to obtain a coherent representation of the environment. Finally, a graph representation is extracted which can then be used for spatial reasoning and human robot interaction. We present first results from data collected by a mobile robot which operates in city areas.