Cortical Multiscale Line-Edge Disparity Model

  • J. M. F. Rodrigues
  • J. A. Martins
  • R. Lam
  • J. M. H. du Buf
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7324)

Abstract

Most biological approaches to disparity extraction rely on the disparity energy model (DEM). In this paper we present an alternative approach which can complement the DEM model. This approach is based on the multiscale coding of lines and edges, because surface structures are composed of lines and edges and contours of objects often cause edges against their background. We show that the line/edge approach can be used to create a 3D wireframe representation of a scene and the objects therein. It can also significantly improve the accuracy of the DEM model, such that our biological models can compete with some state-of-the-art algorithms from computer vision.

Keywords

Stereo Pair Computer Vision Algorithm Horizontal Disparity Stereo Correspondence Disparity 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Middlebury stereo vision – evaluation page, http://vision.middlebury.edu/stereo/eval/ (last retrieved January 2012)
  2. 2.
    Cignoni, P., Corsini, M., Ranzuglia, G.: Meshlab: an open-source 3D mesh processing system. In: ERCIM News, pp. 45–46 (2008)Google Scholar
  3. 3.
    Hubel, D.H.: Eye, Brain and Vision. Scientific American Library series, vol. 22. Scientific American Library, New York (1995)Google Scholar
  4. 4.
    Martins, J.A., Rodrigues, J.M.F., du Buf, J.M.H.: Disparity energy model using a trained neuronal population. In: Proc. IEEE Int. Symp. on Signal Proc. and Inform. Technology, pp. 261–266 (2011)Google Scholar
  5. 5.
    Mutti, F., Gini, G.: Bio-inspired disparity estimation system from energy neurons. In: Proc. IEEE Int. Conf. on Appl. Bionics and Biomechanics, pp. 1–6 (2010)Google Scholar
  6. 6.
    Pugeault, N., Woergoetter, F., Krueger, N.: Disambiguating multi-modal scene representations using perceptual grouping constraints. PLoS ONE 5(6), e10663 (2010)Google Scholar
  7. 7.
    Rodrigues, J., du Buf, J.M.H.: Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection. BioSystems 86, 75–90 (2006)CrossRefGoogle Scholar
  8. 8.
    Rodrigues, J., du Buf, J.M.H.: Multi-scale lines and edges in V1 and beyond: brightness, object categorization and recognition, and consciousness. BioSystems 95, 206–226 (2009)CrossRefGoogle Scholar
  9. 9.
    Scharstein, D.: High-accuracy stereo depth maps using structured light. In: Proc. IEEE Comp. Soc. Conf. on Comp. Vision and Pattern Recogn., pp. 195–202 (2003)Google Scholar
  10. 10.
    Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. 1–8 (2007)Google Scholar
  11. 11.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. of Computer Vision 47, 7–42 (2002)MATHCrossRefGoogle Scholar
  12. 12.
    Szeliski, R.: Stereo correspondence. In: Computer Vision, pp. 467–503. Springer, London (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • J. M. F. Rodrigues
    • 1
  • J. A. Martins
    • 1
  • R. Lam
    • 1
  • J. M. H. du Buf
    • 1
  1. 1.Vision Laboratory, LARSySUniversity of the AlgarveFaroPortugal

Personalised recommendations