Predicting Detection Events from Bayesian Scene Recognition

  • Georg Ogris
  • Lucas Paletta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

This work is conceptually based on psychological findings in human perception that highlight the utility of scene interpretation in object detection processes. Objects of interest are embedded in their visual context, i.e., in visual events within their spatial neighborhood. The implication for a detection system is that early recognition of this environment might provide information to directly map to an object event. The original contribution of this work is to outline a detection system that gains prospective information out of rapid scene analysis in order to focus attention on estimated object locations. Scene recognition is outlined on the basis of rapid detection of triplet configurations of landmarks which determine the discriminability of a particular location within the scene. Formulating scene recognition in terms of posterior landmark interpretation enables a recursive integration of target predictions and hence a probabilistic representation for attention based object detection.

Keywords

Video Sequence Object Detection Object Event Scene Recognition Scene Model 
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.

References

  1. 1.
    J. Assfalg, M. Bertini, C. Colombo, and A. Del Bimbo. Semantic annotation of sports videos. IEEE Multimedia, 9(2):52–60, 2002.CrossRefGoogle Scholar
  2. 2.
    S. Belongie, C. Carson, H. Greenspan, and J. Malik. Color-and texture-based image segmentation using EM and its applications to content-based image retrieval. In Proc. International Conference on Computer Vision, pages 675–682. Bombay, India, 1998.Google Scholar
  3. 3.
    I. Biederman, R.J. Mezzanotte, and J.C. Rabinowitz. Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology, 14:143–177, 1982.CrossRefGoogle Scholar
  4. 4.
    G.H. Granlund and A. Moe. Unrestricted recognition of 3-D objects using multilevel triplet invariants. In Proc. Cognitive Vision Workshop, Zürich, Switzerland, September 2002.Google Scholar
  5. 5.
    A. Hollingworth and J.M. Henderson. Accurate visual memory for previously attended objects in natural scenes. Journal of Experimental Psychology: Human Perception and Performance, 28(1):113–136, 2002.CrossRefGoogle Scholar
  6. 6.
    M.R. Naphade and T.S. Huang. A probabilistic framework for semantic video indexing, filtering, and retrieval. IEEE Transactions on Multimedia, 3(1):141–151, 2001.CrossRefGoogle Scholar
  7. 7.
    S. Obdrzalek and J. Matas. Object recognition using local affine frames on distinguished regions. In Proc. British Machine Vision Conference, 2002.Google Scholar
  8. 8.
    G. Ogris. Attention from scene context for object detection in video. MsThesis, Inst. of Digital Image Processing, Joanneum Research, Graz, Austria, 2003.Google Scholar
  9. 9.
    L. Paletta, A. Goyal, and C. Greindl. Selective visual attention in object detection processes. In Proc. Applications of Artificial Neural Networks in Image Processing VIII. SPIE Electronic Imaging, Santa Clara, CA, in print, 2003.Google Scholar
  10. 10.
    L. Paletta and C. Greindl. Context based object detection from video. In Proc. International Conference on Computer Vision Systems, pages 502–512. Graz, Austria, 2003.Google Scholar
  11. 11.
    R. Sims and G. Dudek. Learning visual landmarks for pose estimation. In Proc. International Conference on Robotics and Automation, Detroit, MI, May 1999.Google Scholar
  12. 12.
    Y. Takeuchi and M. Hebert. Finding images of landmarks in video sequences. In Proc. Conference on Computer Vision and Pattern Recognition, 1998.Google Scholar
  13. 13.
    P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Georg Ogris
    • 1
  • Lucas Paletta
    • 1
  1. 1.Institute of Digital Image ProcessingJoanneum ResearchGrazAustria

Personalised recommendations