Abstract

In this paper, we propose a holistic classification scheme for different room types, like office or meeting room, based on 3D features. Such a categorization of scenes provides a rich source of information about potential objects, object locations, and activities typically found in them. Scene categorization is a challenging task. While outdoor scenes can be sufficiently characterized by color and texture features, indoor scenes consist of human-made structures that vary in terms of color and texture across different individual rooms of the same category. Nevertheless, humans tend to have an immediate impression in which room type they are. We suggest that such a decision could be based on the coarse spatial layout of a scene. Therefore, we present a system that categorizes different room types based on 3D sensor data extracted by a Time-of-Flight (ToF) camera. We extract planar structures combining region growing and RANSAC approaches. Then, feature vectors are defined on statistics over the relative sizes of the planar patches, the angles between pairs of (close) patches, and the ratios between sizes of pairs of patches to train classifiers. Experiments in a mobile robot scenario study the performance in classifying a room based on a single percept.

References

  1. 1.
    Strat, T.M., Fischler, M.A.: Context-based vision: Recognizing objects using both 2D and 3D imaging. PAMI 13, 1050–1065 (1991)CrossRefGoogle Scholar
  2. 2.
    McKeown, D.M., Harvey, W.A., McDermott, J.: Rule-based interpretation of aerial imagery. In: Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, pp. 415–430 (1987)Google Scholar
  3. 3.
    Murphy, K., Torralba, A., Freeman, W.T.: Using the forest to see the trees: A graphical model relating features, objects, and scenes. In: Advances in Neural Information Processing Systems, vol. 16 (2003)Google Scholar
  4. 4.
    Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. CVPR 2, 2137–2144 (2006)Google Scholar
  5. 5.
    Szummer, M., Picard, R.W.: Indoor-outdoor image classification. In: CAIVD, pp. 42–51 (1998)Google Scholar
  6. 6.
    Paek, S., Chang, S.F.: A knowledge engineering approach for image classification based on probabilistic reasoning systems. ICME 2, 1133–1136 (2000)Google Scholar
  7. 7.
    Torralba, A.: Contextual priming for object detection. IJCV 53, 153–167 (2003)CrossRefGoogle Scholar
  8. 8.
    Weingarten, J., Gruener, G., Siegwart, R.: A state-of-the-art 3D sensor for robot navigation. In: IROS (2004)Google Scholar
  9. 9.
    Swadzba, A., Liu, B., Penne, J., Jesorsky, O., Kompe, R.: A comprehensive system for 3D modeling from range images acquired from a 3D ToF sensor. In: ICVS (2007)Google Scholar
  10. 10.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Besl, P.J., McKay, N.D.: A method for registration of 3D shapes. PAMI 14, 239–256 (1992)CrossRefGoogle Scholar
  12. 12.
    Nüchter, A., Surmann, H., Hertzberg, J.: Automatic model refinement for 3D reconstruction with mobile robots. In: 3DIM, pp. 394–401 (2003)Google Scholar
  13. 13.
    Lee, S., Jang, D., Kim, E., Hong, S., Han, J.: A real-time 3D workspace modeling with stereo camera. In: IROS, pp. 2140–2147 (2005)Google Scholar
  14. 14.
    Liu, Y., Emery, R., Chakrabarti, D., Burgard, W., Thurn, S.: Using EM to learn 3D models of indoor environments with mobile robots. In: ICML (2001)Google Scholar
  15. 15.
    Lakaemper, R., Latecki, L.J.: Using extended EM to segment planar structures in 3D. In: ICPR, pp. 1077–1082 (2006)Google Scholar
  16. 16.
    Hähnel, D., Burgard, W., Thrun, S.: Learning compact 3D models of indoor and outdoor environments with a mobile robot. Robotics and Autonomous Systems 44, 15–27 (2003)CrossRefGoogle Scholar
  17. 17.
    Adams, R., Bischof, L.: Seeded region growing. PAMI 16, 641–647 (1994)CrossRefGoogle Scholar
  18. 18.
    Fua, P.: From multiple stereo views to multiple 3D surfaces. IJCV 24, 19–35 (1997)CrossRefGoogle Scholar
  19. 19.
    Stamos, I., Allen, P.K.: Geometry and texture recovery of scenes of large scale. CVIU 88, 94–118 (2002)MATHGoogle Scholar
  20. 20.
    Lourenco, A., Freitas, P., Ribeiro, M.I., Marques, J.S.: Detection and classification of 3D moving objects. In: Mediterranean Conf. on Control and Automation (2002)Google Scholar
  21. 21.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Parallel Data Processing 1, 318–362 (1986)Google Scholar
  22. 22.
    Vapnik, V.N.: The Nature of Statistical Learning Theory (1995)Google Scholar
  23. 23.
    Joachims, T.: Learning to Classify Text Using Support Vector Machines. PhD thesis, Cornell University (2002)Google Scholar
  24. 24.
    Fink, G.A.: Developing HMM-based recognizers with ESMERALDA. In: Matoušek, V., Mautner, P., Ocelíková, J., Sojka, P. (eds.) TSD 1999. LNCS (LNAI), vol. 1692, pp. 229–234. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  25. 25.
    Haasch, A., Hohenner, S., Hüwel, S., Kleinehagenbrock, M., Lang, S., Toptsis, I., Fink, G.A., Fritsch, J., Wrede, B., Sagerer, G.: BIRON – The Bielefeld Robot Companion. In: ASER, pp. 27–32 (2004)Google Scholar
  26. 26.
    COGNIRON: The cognitive robot companion (FP6-IST-002020) (2004), http://www.cogniron.org

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Agnes Swadzba
    • 1
  • Sven Wachsmuth
    • 1
  1. 1.Applied Computer Science, Faculty of TechnologyBielefeld UniversityBielefeldGermany

Personalised recommendations