Acquiring Robust Representations for Recognition from Image Sequences

  • Christian Wallraven
  • Heinrich Bülthoff
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2191)


We present an object recognition system which is capable of on-line learning of representations of scenes and objects from natural image sequences. Local appearance features are used in a tracking framework to find ‘key-frames’ of the input sequence during learning. In addition, the same basic framework is used for both learning and recognition. The system creates sparse representations and shows good recognition performance in a variety of viewing conditions for a database of natural image sequences.


object recognition model acquisition appearance-based learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A. Baerveldt, “A vision system for object verification and localization based on local features”, Robotics and Autonomous Systems, 34(2-3): 83–92, 2001.zbMATHCrossRefGoogle Scholar
  2. 2.
    D. Jugessur, G. Dudek, “Local Appearance for Robust Object Recognition”, In Proc. CVPR’00, 834–839, 2000.Google Scholar
  3. 3.
    J. Koenderink, A. van Doorn, “The internal representation of solid shape with respect to vision”, Biological Cybernetics, 32, 1979.Google Scholar
  4. 4.
    D. Lowe, “toward a Computational Model for Object Recognition in IT Cortex”, In Proc. BMCV’00, 20–31, 2000.Google Scholar
  5. 5.
    A. Massad, B. Mertsching, and S. Schmalz, “Combining multiple views and temporal associations for 3-D object recognition”, In Proc. ECCV’98, 699–715, 1998.Google Scholar
  6. 6.
    B. Mel, “SEEMORE: Combining color, shape, and texture histogramming in a neurally-inspired approach to visual object recognition”, Neural Computation, 9:777–804, 1997.CrossRefGoogle Scholar
  7. 7.
    M. Pilu, “A direct method for stereo correspondence based on singular value decomposition”, In Proc. CVPR’97, 261–266, 1997.Google Scholar
  8. 8.
    C. Schmid, R. Mohr, “Local Greyvalue Invariants for Image Retrieval”, IEEE TPAMI, 19(5):530–535, 1997.Google Scholar
  9. 9.
    G. Scott, H. Longuet-Higgins, “An algorithm for associating the features of two images”, In Proc. Royal Society of London, B(244):21–26, 1991.CrossRefGoogle Scholar
  10. 10.
    C. Tomasi, T. Kanade, “Detection and tracking of point features”, Carnegie-Mellon Tech Report CMU-CS-91-132, 1991.Google Scholar
  11. 11.
    T. Tuytelaars, L. van Gool, “Content-based image retrieval based on local affinely invariant regions”, In Proc. Visual’ 99, 493–500, 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Christian Wallraven
    • 1
  • Heinrich Bülthoff
    • 1
  1. 1.Max Planck Institute for Biological CyberneticsTübingen

Personalised recommendations