Color stereo vision: Use of appearance constraint and epipolar geometry for feature matching

  • Ming Xie
  • Lai Yuan Liu
Stereo Vision
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1035)


The difficult problem of stereo vision is how to establish correspondence between features extracted from a pair of images. The difficulty is due to ambiguities or inconsistence of available information in images. In this paper, we investigate stereo correspondence problem in the framework of color stereo vision. We propose the use of an appearance constraint and generalized epipolar geometry to develop a matching algorithm.


Vision Computing Stereo Vision Stereo Match Color Region Color Edge 
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]
    Ayache, N and Faverjon, B.: Efficient registration of stereo images by matching graph descriptions of edge segments. International Journal of Computer Vision 1, (1987), 107–131.Google Scholar
  2. [2]
    Bachelder, I. A. and Ullman. S.: Contour matching using local affine transformations. IEEE International Conference on Computer Vision and Pattern Recognition, (1993). 798–801.Google Scholar
  3. [3]
    Brint, A. T. and Brady. M.: Stereo matching of curves. Journal of Image and Vision Computing 8, (1990), 50–56.Google Scholar
  4. [4]
    Cohen, L. Vinet, L. Sander, P. T. and Gagalowicz, A.: Hierarchical region based stereo matching. IEEE International Conference on Computer Vision and Pattern Recognition, (1989), 416–421.Google Scholar
  5. [5]
    Costabile, M. F. Guerra, C. and Pieroni. G. G.: Matching shapes: a case study in time-varying images. Computer Vision, Graphics and Image Processing 29, (1985), 296–310.Google Scholar
  6. [6]
    Deriche, R and Faugeras. O.: 2-D curve matching using high curvature points: Application to stereo vision. International Conference on Pattern Recognition, (1990). 240–242.Google Scholar
  7. [7]
    Ellis, T. Abbood, A. and Brillault. B.: Ellipse detection and matching with uncertainty. Image and Vision Computing 10, (1992), 271–276.Google Scholar
  8. [8]
    Faugeras, O.: Three Dimensional Vision: A Geometrical Viewpoint. MIT Press, (1993), 189–199.Google Scholar
  9. [9]
    Fua, P.: A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision and Applications 6, (1993), 35–49.Google Scholar
  10. [10]
    Grimson, W. E. L.: Computational experiments with a feature based stereo algorithm. IEEE Trans. on PAMI 7, (1985), 17–34.Google Scholar
  11. [11]
    Grosky, W. I. and Jain, R.: A pyramid-based approach to segmentation applied to region matching. IEEE Trans. on PAMI 8, (1986), 639–650.Google Scholar
  12. [12]
    Horaud, R. and Skordas, T.: Structural matching for stereo vision. International Conference on Pattern Recognition, (1988), 439–445.Google Scholar
  13. [13]
    Limozin, P. L. and Giraudon, G.: Stereo matching using contextual line region primitives. International Conference on Pattern Recognition, (1986). 974–977.Google Scholar
  14. [14]
    Luong, Q. T.: Color In Computer Vision. in Handbook of Pattern Recognition and Computer Vision (Eds. C.H. Chen, L. F. Pau, P. S. P. Wang), (1993), 311–368.Google Scholar
  15. [15]
    Marr, D. and Poggio, T.: Cooperative Computation of Stereo Disparity. Science 194, (1976)Google Scholar
  16. [16]
    Pollard, S. B. Porrill, J. Mayhew, J. E. W. and Frisby, J. P.: Disparity gradient, Lipschitz continuity, and computing binocular correspondences. CVGIP: Image Understanding, (1989), 197–214.Google Scholar
  17. [17]
    Porrill, J and Pollard, S.: Curve matching and stereo calibration. Image and Vision Computing 9, (1991), 45–50.Google Scholar
  18. [18]
    Sherman, D. and Peleg, S.: Stereo by incremental matching of contours. IEEE Trans. on PAMI 12, (1990), 1102–1107.Google Scholar
  19. [19]
    Weng, J. Ahuja, N. and Huang, T. S.: Two-view matching. International Conference on Computer Vision, (1988), 64–73.Google Scholar
  20. [20]
    Zhang, D. Z. Perspective invariant description of planar point set and their application in matching. International Conference on Pattern Recognition, (1986), 1266–1268.Google Scholar
  21. [21]
    Zhang, Z. Deriche, R. Faugeras, O. and Luong, Q. T.: A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. International Conference on Automation, Robotics and Computer Vision, (1994), 1102–1106.Google Scholar
  22. [22]
    Xie, M.: A Cooperative Strategy For The Matching of Multi-level Edge Primitives. Journal of Image and Vision Computing Vol. 13(2), (1995), 89–99.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Ming Xie
    • 1
  • Lai Yuan Liu
    • 1
  1. 1.School of Mechanical & Production EngineeringNanyang Technological UniversitySingapore

Personalised recommendations