Detecting Scene Elements Using Maximally Stable Colour Regions

  • David Obdržálek
  • Stanislav Basovník
  • Lukáš Mach
  • Andrej Mikulík
Conference paper

DOI: 10.1007/978-3-642-16370-8_10

Volume 82 of the book series Communications in Computer and Information Science (CCIS)
Cite this paper as:
Obdržálek D., Basovník S., Mach L., Mikulík A. (2010) Detecting Scene Elements Using Maximally Stable Colour Regions. In: Gottscheber A., Obdržálek D., Schmidt C. (eds) Research and Education in Robotics - EUROBOT 2009. EUROBOT 2009. Communications in Computer and Information Science, vol 82. Springer, Berlin, Heidelberg

Abstract

Image processing for autonomous robots is nowadays very popular. In our paper, we show a method how to extract information from a camera attached on a robot to acquire locations of targets the robot is looking for. We apply maximally stable colour regions (a method originally used for image matching) to obtain an initial set of candidate regions. This set is then filtered using application specific filters to find only the regions that correspond to scene elements of interest. The presented method has been applied in practice and performs well even under varying illumination conditions since it does not rely heavily on manually specified colour thresholds. Furthermore, no colour calibration is needed.

Keywords

Autonomous robot Maximally Stable Colour Regions 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • David Obdržálek
    • 1
  • Stanislav Basovník
    • 1
  • Lukáš Mach
    • 1
  • Andrej Mikulík
    • 1
  1. 1.Faculty of Mathematics and PhysicsCharles University in PraguePraha 1Czech Republic