Belief Propagation for Stereo Analysis of Night-Vision Sequences

  • Shushi Guan
  • Reinhard Klette
  • Young W. Woo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5414)


This paper studies different specifications of belief propagation for stereo analysis of seven rectified stereo night-vision sequences (provided by Daimler AG). As shown in [4], Sobel preprocessing of images has obvious impacts on improving disparity calculations. This paper considers other options of preprocessing (Canny and Kovesi-Owens edge operators), and concludes with a recommended setting for belief propagation on those sequences.


Performance evaluation stereo analysis motion analysis real-world sequences driver assistance 


  1. 1.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Analysis Machine Intelligence 8, 679–714 (1986)CrossRefGoogle Scholar
  2. 2.
    .enpeda.. Image Sequence Analysis Test Site (follow the data link),
  3. 3.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Computer Vision 70, 41–54 (2006)CrossRefGoogle Scholar
  4. 4.
    Guan, S., Klette, R.: Belief-propagation on edge images for stereo analysis of image sequences. In: Sommer, G., Klette, R. (eds.) RobVis 2008. LNCS, vol. 4931, pp. 291–302. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Klette, G.: Euclidean distance transform (August 2006),
  6. 6.
    Klette, R.: Lecture notes about belief propagation,
  7. 7.
    Kovesi, P.: Phase congruency detects corners and edges. In: The Australian Pattern Recognition Society Conference: DICTA 2003, pp. 309–318 (2003)Google Scholar
  8. 8.
    Liu, Z., Klette, R.: Performance evaluation of stereo and motion analysis on rectified image sequences. Technical report, Computer Science Department, The University of Auckland (2007)Google Scholar
  9. 9.
    Middlebury Stereo Website,
  10. 10.
    Morrone, M.C., Owens, R.A.: Feature detection from local energy. Pattern Recognition Letters 6, 303–313 (1987)CrossRefGoogle Scholar
  11. 11.
    Robbins, B., Owens, R.A.: 2D feature detection via local energy. Image and Vision Computing 15, 353–368 (1997)CrossRefGoogle Scholar
  12. 12.
    Sobel, I., Feldman, G.: A 3 ×3 isotropic gradient operator for image processing. Presented at a talk at the Stanford Artificial Project in 1968 (unpublished)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Shushi Guan
    • 1
  • Reinhard Klette
    • 1
  • Young W. Woo
    • 2
  1. 1.The .enpeda.. ProjectThe University of AucklandNew Zealand
  2. 2.Dept. of Multimedia Eng.Dong-Eui UniversityBusanKorea

Personalised recommendations