Segmentation from motion: Combining Gabor- and Mallat-wavelets to overcome aperture and correspondence problem

  • Laurenz WiskottEmail author
Segmentation and Grouping
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)


A segmentation-from-motion algorithm is presented, which is designed to be part of a general object recognition system. The key idea is to integrate information from Gabor- and Mallat-wavelet transform to overcome the aperture and the correspondence problem. The assumption is made that objects move fronto-parallel. Gabor-wavelet responses allow precise estimation of image flow vectors with low spatial resolution. A histogram over this image flow field is evaluated, its local maxima providing motion hypotheses. These serve to reduce the correspondence problem on the Mallat-wavelet transform, which provides the required high resolution. The segmentation reliability is improved by integration over time. The system can segment even small, disconnected, and openworked objects of arbitrary number, such as dot patterns. Several examples demonstrate the performance of the system and show, that the algorithm behaves reasonably even if the assumption of fronto-parallel motion is strongly violated.


Segmentation Result Image Flow Modulus Maximum Flow Vector Edge Pixel 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Daugman, J. G. Complete discrete 2-D Gabor transform by neural networks for image analysis and compression. IEEE Transactions on Acoustics, Speech and Signal Processing 36, 7 (July 1988), 1169–1179.Google Scholar
  2. [2]
    Horn, B. K. P., and Schunck, B. G. Determining optical flow. Artificial Intelligence 17 (1981), 185–203.CrossRefGoogle Scholar
  3. [3]
    Mallot, S., and Zhong, S. Characterization of signals from multiscale edges. IEEE Transactions on Pattern Analysis and Machine Intelligence 14, 7 (1992), 710–732.CrossRefGoogle Scholar
  4. [4]
    Theimer, W. M., and Mallot, H. A. Phase-based binocular vergence control and depth reconstruction using active vision. CVGIP: Image Understanding 60, 3 (Nov. 1994), 343–358.CrossRefGoogle Scholar
  5. [5]
    Wiskott, L. Segmentation from motion: Combining Gabor-and Mallat-wavelets to overcome aperture and correspondence problem. Tech. Rep. IR-INI 96-10, Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany, 1996.Google Scholar
  6. [6]
    Wiskott, L., Fellous, J.-M., Krüger, N., and Von Der Malsburg, C. Face recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, accepted for publication., 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  1. 1.Institut für Neuroinformatik Ruhr-Universität BochumBochumGermany

Personalised recommendations