Two-Dimensional Channel Representation for Multiple Velocities

  • Hagen Spies
  • Per-Erik Forssén
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


We present a two-dimensional information representation, where small but overlapping Gaussian kernels are used to encode the data in a matrix. Apart from points we apply this to constraints that restrict the solution to a linear subspace. A localised decoding scheme accurately extracts multiple solutions together with an estimate of the covariances. We employ the method in optical flow computations to determine multiple velocities occurring at motion discontinuities.


Optical Flow Channel Matrix Vector Plot Multiple Motion Optical Flow Computation 
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.


  1. [1]
    Granlund, G.H.: An associative perception-action structure using a localized space variant information representation. In: Proceedings of Algebraic Frames for the Perception-Action Cycle (AFPAC), Kiel, Germany (2000)Google Scholar
  2. [2]
    Forssen, P.E.: Sparse representations for medium level vision. Licentiate Thesis LiU-Tek-Lic-2001:06, Linköping University, Sweden (2001)Google Scholar
  3. [3]
    Shizawa, M., Mase, K.: Simultaneous multiple optical flow estimation. In: ICPR, Atlantic City, NJ, USA (1990) 274–278Google Scholar
  4. [4]
    Nestares, O., Navarro, R.: Probabilistic estimation of optical flow in multiple band-pass directional channels. Image and Vision Comp. 19 (2001) 339–351CrossRefGoogle Scholar
  5. [5]
    Mota, C., Stuke, I., Barth, E.: Analytic solutions for multiple motions. In: ICIP. Volume 2., Thessaloniki, Greece (2001) 917–920Google Scholar
  6. [6]
    Andersson, K., Knutsson, H.: Multiple hierarchical motion estimation. In: SPPRA, Crete, Greece (2002) 80–85Google Scholar
  7. [7]
    Beauchemin, S.S., Barron, J.L.: On the fourier properties of discontinuous motion. Journal of Mathematical Imaging and Vision 13 (2000) 155–172zbMATHCrossRefMathSciNetGoogle Scholar
  8. [8]
    Weiss, Y., Fleet, D.: Velocity likelihoods in biological and machine vision. In Rao, R. P. N., Olshausen, B. A., Lewicki, M. S., eds.: Probabilistic Models of the Brain: Perception and Neural Function. MIT Press (2001) 81–100Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Hagen Spies
    • 1
    • 2
  • Per-Erik Forssén
    • 1
  1. 1.Computer Vision Laboratory Dept. of Electrical EngineeringLinköping UniversityLinköpingSweden
  2. 2.ContextVision ABLinköpingSweden

Personalised recommendations