Advertisement

Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform

  • Seung-Bin Im
  • Sung-Bae Cho
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4179)

Abstract

Scene understanding is an important problem in intelligent robotics. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty, and powerful to model high-level contexts like the relationship between places and objects. In this paper, we propose a context-based Bayesian method with SIFT for scene understanding. At first, image pre-processing extracts features from vision information and objects-existence information is extracted by SIFT that is rotation and scale invariant. This information is provided to Bayesian networks for robust inference in scene understanding. Experiments in complex real environments show that the proposed method is useful.

Keywords

Hide Markov Model Bayesian Network Object Recognition False Recognition Scene Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Korpipaa, P., Koskinen, M., Peltola, J., Mäkelä, S., Seppänen, T.: Bayesian approach to sensor-based context awareness. Personal and Ubiquitous Computing Archive 7(4), 113–124 (2003)CrossRefGoogle Scholar
  2. 2.
    Torralba, A., Mutphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: IEEE Int. Conf. Computer Vision, vol. 1(1), pp. 273–280 (2003)Google Scholar
  3. 3.
    Marengoni, M., Hanson, A., Zilberstein, S., Riseman, E.: Decision making and uncertainty management in a 3D reconstruction system. IEEE Trans. Pattern Analysis and Machine Intelligence 25(7), 852–858 (2003)CrossRefGoogle Scholar
  4. 4.
    Luo, J., Savakis, A.E., Singhal, A.: A Bayesian network-based framework for semantic image understanding. Pattern Recognition 38(6), 919–934 (2005)CrossRefGoogle Scholar
  5. 5.
    Strat, T.M., Fischler, M.A.: Context-based vision: Recognizing objects using information from both 2-D and 3-D imagery. IEEE Trans. Pattern Analysis and Machine Intelligence 13(10), 1050–1065 (1991)CrossRefGoogle Scholar
  6. 6.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Intl. J. Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  7. 7.
    Oliver, N., Garg, A., Horvitz, E.: Layered representations for learning and inferring office activity from multiple sensory channels. Computer Vision and Image Understanding 96(2), 163–180 (2004)CrossRefGoogle Scholar
  8. 8.
    Neapolitan, R.E.: Learning Bayesian Network. Prentice hall series in Artificial Intelligence (2003)Google Scholar
  9. 9.
    Portilla, J., Simoncelli, E.P.: A parametric texture model based on joint statistics of complex wavelets coefficients. Intl. J. Computer Vision 40(1), 49–71 (2000)MATHCrossRefGoogle Scholar
  10. 10.
    Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Machine Learning 9(4), 309–347 (1992)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Seung-Bin Im
    • 1
  • Sung-Bae Cho
    • 1
  1. 1.Dept. of Computer ScienceYonsei UniversitySeoulKorea

Personalised recommendations