Advertisement

Some Room for GLVQ: Semantic Labeling of Occupancy Grid Maps

  • Sven Hellbach
  • Marian Himstedt
  • Frank Bahrmann
  • Martin Riedel
  • Thomas Villmann
  • Hans-Joachim Böhme
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 295)

Abstract

This paper aims at an approach for labeling places within a grid cell environment. For that we propose a method that is based on non-negative matrix factorization (NMF) to extract environment specific features from a given occupancy grid map. NMF also computes a description about where on the map these features need to be applied. We use this description after certain pre-processing steps as an input for generalized learning vector quantization (GLVQ) to achieve the classification or labeling of the grid cells. Our approach is evaluated on a standard data set from University of Freiburg, showing very promising results.

Keywords

NMF GLVQ semantic labeling occupancy grid maps 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mozos, O.M., Triebel, R., Jensfelt, P., Rottmann, A., Burgard, W.: Supervised semantic labeling of places using information extracted from sensor data. RAS 55(5), 391–402 (2007)Google Scholar
  2. 2.
    Shi, L., Kodagoda, S., Dissanayake, G.: Laser range data based semantic labeling of places. In: IROS, pp. 5941–5946. IEEE (2010)Google Scholar
  3. 3.
    Shi, L., Kodagoda, S., Dissanayake, G.: Multi-class classification for semantic labeling of places. In: ICARCV, pp. 2307–2312. IEEE (2010)Google Scholar
  4. 4.
    Sousa, P., Araujo, R., Nunes, U.: Real-Time Labeling of Places using Support Vector Machines. In: ISIE, pp. 2022–2027 (2007)Google Scholar
  5. 5.
    Nieto-Granda, C., Rogers, J.G., Trevor, A.J., Christensen, H.I.: Semantic map partit. in indoor environments using regional analysis. In: IROS, pp. 1451–1456 (2010)Google Scholar
  6. 6.
    Bahrmann, F., Hellbach, S., Böhme, H.J.: Please tell me where I am: A fundament for a semantic labeling approach. In: KI, pp. 120–124 (2012)Google Scholar
  7. 7.
    Pronobis, A., Mozos, O.M., Caputo, B., Jensfelt, P.: Multi-modal semantic place classification. Int J. Robot. Res. 29(2-3), 298–320 (2010)CrossRefGoogle Scholar
  8. 8.
    Koppula, H.S., Anand, A., Joachims, T., Saxena, A.: Semantic labeling of 3d point clouds for indoor scenes. In: NIPS, pp. 244–252 (2011)Google Scholar
  9. 9.
    Anand, A., Koppula, H.S., Joachims, T., Saxena, A.: Contextually guided semantic labeling and search for three-dimensional point clouds. Int. J. Robot. Res. 32(1), 19–34 (2013)CrossRefGoogle Scholar
  10. 10.
    Hellbach, S., Himstedt, M., Boehme, H.J.: Towards Non-negative Matrix Factorization based Localization. In: ECMR (2013)Google Scholar
  11. 11.
    Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Adv. Neural Inf. Process. Syst 13, 556–562 (2001)Google Scholar
  12. 12.
    Eggert, J., Wersing, H., Körner, E.: Transformation-invariant representation and NMF. In: IJCNN, pp. 2535–2539 (2004)Google Scholar
  13. 13.
    Eggert, J., Körner, E.: Sparse Coding and NMF. In: IJCNN, pp. 2529–2533 (2004)Google Scholar
  14. 14.
    Vollmer, C., Hellbach, S., Eggert, J., Gross, H.M.: Sparse coding of human motion trajectories with non-negative matrix factorization. Neurocomp. (2013)Google Scholar
  15. 15.
    Paglieroni, D.W.: Distance transforms: properties and machine vision applications. CVGIP: Graph. Models Image Process. 54(1), 56–74 (1992)Google Scholar
  16. 16.
    Kohonen, T.: The self-organizing map. Proc. of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  17. 17.
    Sato, A., Yamada, K.: Generalized learning vector quantization. In: NIPS, pp. 423–429. MIT Press, Cambridge (1996)Google Scholar
  18. 18.
    Hammer, B., Villmann, T.: Generalized relevance learning vector quantization. Neural Networks 15(8-9), 1059–1068 (2002)CrossRefGoogle Scholar
  19. 19.
    Schneider, P., Biehl, M., Hammer, B.: Adaptive relevance matrices in learning vector quantization. Neural Computation 21, 3532–3561 (2009)zbMATHMathSciNetCrossRefGoogle Scholar
  20. 20.
    Qin, A.K., Suganthan, P.N.: A novel kernel prototype-based learning algorithm. In: ICPR (4), pp. 621–624 (2004)Google Scholar
  21. 21.
    Hammer, B., Strickert, M., Villmann, T.: Supervised neural gas with general similarity measure. Neural Processing Letters 21(1), 21–44 (2005)CrossRefGoogle Scholar
  22. 22.
    Villmann, T., Haase, S.: Divergence-based vector quantization. Neural Computation 23(5), 1343–1392 (2011)zbMATHMathSciNetCrossRefGoogle Scholar
  23. 23.
    Kästner, M., Riedel, M., Strickert, M., Villmann, T.: Class border sensitive generalized learning vector quantization - an alternative to support vector machines. Machine Learning Reports 6(MLR-04-2012), 40–56 (2012)Google Scholar
  24. 24.
    Mozos, O.M.: Semantic Place Labeling with Mobile Robots. PhD thesis, Dept. of Computer Science, University of Freiburg (July 2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sven Hellbach
    • 1
  • Marian Himstedt
    • 1
  • Frank Bahrmann
    • 1
  • Martin Riedel
    • 2
  • Thomas Villmann
    • 2
  • Hans-Joachim Böhme
    • 1
  1. 1.Artificial Intelligence and Cognitive Robotics LabsUniversity of Applied Sciences DresdenDresdenGermany
  2. 2.Computational Intelligence and TechnomathematicsUniversity of Applied Sciences MittweidaMittweidaGermany

Personalised recommendations