Mathematical morphology filters applied to an image skeletonization method to generation of topological maps

  • Authors:

  • Janderson R. Oliveira;Edson A. S. Filho;Roseli A. F. Romero

  • Affiliations:

  • University of Sao Paulo, São Carlos/SP, BR;University of Sao Paulo, São Carlos/SP, BR;University of Sao Paulo, São Carlos/SP, BR

  • Venue:
  • Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The environment mapping has been a great challenge of many researchers of the mobile robot autonomous navigation area. There are two important paradigms for mapping, metric and topological mapping. Diverse mapping methods that combine the advantages of each paradigm have been proposed. A simple alternative is to combine the metric mapping technique known as Occupancy Grid with an image skeletonization method to topological mapping. However, due noises inherent to the own robot ability of capturing sensor signals, the topological map generated through this combination presents several unnecessary topological lines, hindering consequently the task of autonomous navigation. Therefore, the aim of this work is to propose a set of mathematical morphology filters to generation of topological maps suitable for real environments, seeking to reduce influence of noises in performed mapping. Several experiments have been performed to verify the efficiency of the proposed approach. The application this mathematical morphology filters demonstrated to be an useful method to the creation of topological maps free of noises.