A Modified Area Based Local Stereo Correspondence Algorithm for Occlusions

  • Jungwook Seo
  • Ernie W. Hill
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3773)

Abstract

Area based local stereo correspondence algorithms that use the simple ’winner takes all’ (WTA) method in the optimization step perform poorly near object boundaries particularly in occluded regions. In this paper, we present a new modified area based local algorithm that goes some way towards addressing this controversial issue. This approach utilizes an efficient strategy by adding the concept of a computation skip threshold (CST) to area based local algorithms in order to add the horizontal smoothness assumption to the local algorithms. It shows similar effects to Dynamic Programming(DP) and Scanline Optimization(SO) with significant improvements in occlusions from existing local algorithms. This is achieved by assigning the same disparity value of the previous neighboring point to coherent occluded points. Experiments were carried out comparing the new algorithm to existing algorithms using the standard stereo image pairs and our own images generated by a Scanning Electron Microscope (SEM). The results show that the horizontal graphical performance improves similarly to DP particularly in occlusions but the computational speed is faster than existing local algorithms, due to skipping unnecessary computations for many points in the WTA step.

Keywords

Local Algorithm Stereo Vision Occlude Region Stereo Image Pair Disparity Range 
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.

References

  1. 1.
    Szeliski, R., Scharstein, D.: A taxonomy and evaluation of dense twoframe stereo correspondence algorithms. IJCV 47, 7–42 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Intille, S.S., Bobick, A.F.: Large occlusion stereo. IJCV 33(3), 181–200 (1999)CrossRefGoogle Scholar
  3. 3.
  4. 4.
    Marr, D.: Vision. W. H. Freeman and Company, New York (1982)Google Scholar
  5. 5.
    Scharstein, D.: View Synthesis Using Stereo Vision. In: Scharstein, D. (ed.) View Synthesis Using Stereo Vision. LNCS, vol. 1583, p. 41. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  6. 6.
    Hannah, M.J., Bolles, R.C., Baker, H.H.: The JISCT stereo evaluation. In: DARPA Image Understanding Workshop, pp. 263–274 (1993)Google Scholar
  7. 7.
    Black, M.J., Anandan, P.: A framework for the robust estimation of optical flow. In: ICCV, pp. 231–236 (1993)Google Scholar
  8. 8.
    Black, M.J., Anandan, P.: A stereo matching algorithm with an adaptive window: theory and experiment. In: Proc. Image Understanding Workshop, pp. 383–389.Google Scholar
  9. 9.
    Kanade, T.: Development of a video-rate stereo machine. In: Image Understanding Workshop, pp. 549–557 (1994)Google Scholar
  10. 10.
    Kanade, T., Matthies, L., Szeliski, R.: Kalman filter-based algorithms for estimating depth from image sequences. IJCV 3, 209–236 (1989)CrossRefGoogle Scholar
  11. 11.
    Gavrila, D., Sunyoto, H., Mark, W.: A Comparative Study of Fast Dense Stereo Vision Algorithms. In: IEEE Intelligent vehicles symposium, Parma, Italy (2004)Google Scholar
  12. 12.
    Garibaldi, J.M., Hirschmuller, H., Innocent, P.R.: Real-Time Correlation-Based Stereo Vision with Reduced Border Errors. IJCV 47(1/2/3), 229–246 (2002)MATHGoogle Scholar
  13. 13.
    Murray, D., Little, J.: Using Real-Time Stereo Vision for Mobile Robot Navigation. Autonomous Robots 8, 161–171 (2000)CrossRefGoogle Scholar
  14. 14.
    Venkateswar, V., Chellappa, R.: Hierarchical Stereo and Motion Correspondence Using Feature Groupings. Int’l J.Computer Vision 15, 245–269 (2000)CrossRefGoogle Scholar
  15. 15.
    Randriamasy, S., Gagalowicz, A.: Region Based Stereo Matching Oriented Image Processing. In: Proc. Computer Vision and Pattern Recognition, pp. 736–737 (1991)Google Scholar
  16. 16.
    Birchfield, S., Tomasi, C.: Multiway Cut for Stereo and Motion with Slanted Surfaces. In: Proc. Int’l Conf. Computer Vision, vol. 1, pp. 489–495 (1999)Google Scholar
  17. 17.
    Shi, J., Tomasi, C.: Good Features to Track. In: Proc. Computer Vision and Pattern Recognition (1994)Google Scholar
  18. 18.
    Veksler, O., Boykov, Y., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE TPAMI 23(11), 1222–1239 (2001)Google Scholar
  19. 19.
    Terzopoulos, D.: Regularization of inverse visual problems involving discontinuities. IEEE TPAMI 8(4), 413–424 (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Jungwook Seo
    • 1
  • Ernie W. Hill
    • 1
  1. 1.Department of Computer ScienceUniversity of ManchesterManchesterUK

Personalised recommendations