Advertisement

International Journal of Computer Vision

, Volume 10, Issue 1, pp 7–25 | Cite as

Conics-based stereo, motion estimation, and pose determination

  • Song De Ma
Article

Abstract

Stereo vision, motion and structure parameter estimation, and pose determination are three important problems in 3-D computer vision. The first step in all of these problems is to choose and to extract primitives and their features in images. In most of the previous work, people usually use edge points or straight line segments as primitives and their local properties as features. Few methods have been presented in the literature using more compact primitives and their global features. This article presents an approach using conics as primitives. For stereo vision, a closed-form solution is provided for both establishing the correspondence of conics in images and the reconstruction of conics in space. With this method, the correspondence is uniquely determined and the reconstruction is global. It is shown that the method can be extended for higher degree (degree≥3) planar curves.For motion and structure parameter estimation, it is shown that, in general, two sequential images of at least three conics are needed in order to determine the camera motion. A complicated nonlinear system must be solved in this case. In particular, if we are given two images of a pair of coplanar conics, a closed-form solution of camera motion is presented. In a CAD-based vision system, the object models are available, and this makes it possible to recognize 3-D objects and to determine their poses from a single image.For pose determination, it is shown that if there exist two conics on the surface of an object, the object's pose can be determined by an efficient one-dimensional search. In particular, if two conics are coplanar, a closed-form solution of the object's pose is presented.

Uniqueness analysis and some experiments with real or synthesized data are presented in this article.

Keywords

Computer Vision Nonlinear System Vision System Line Segment Sequential Image 
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.
    N. Ayache and B. Faverjon, Efficient registration of stereo images by matching graph descriptions of edge segments,Intern. J. Comput. Vis. 1(2):107–131, 1987.Google Scholar
  2. 2.
    N. Ayache and F. Lustman, Trinocular stereo vision for robotics,IEEE Trans. Patt. Anal. Mach Intell. 13(1):73–85, 1991.Google Scholar
  3. 3.
    H.H. Baker, and T.O. Binford, Depth from edge and intensity based stereo,Proc. 7th Intern. Joint Conf. Artif. Intell., Vancouver, Canada, pp. 631–636, 1981.Google Scholar
  4. 4.
    G. Borgefors, Hierarchical chamber matching: A parametric edge matching algorithm,IEEE Trans. Patt. Anal. Mach. Intell. 10(6):849–865, 1988.Google Scholar
  5. 5.
    A.T. Brint and M. Brady, Stereo matching curves,Image Vis. Comput. 8(1):50–55, 1990.Google Scholar
  6. 6.
    J.F. Canny, A computational approach to edge detection,IEEE Trans. Patt. Anal. Mach. Intell. 8(6):679–698, 1986.Google Scholar
  7. 7.
    E.W. Chionh, R.N. Goldman, and J.R. Miller, Using multivariate resultant to find the intersection of three quadric surfaces,ACM Trans. Graphics 10(4):378–400, 1991.Google Scholar
  8. 8.
    L.S. Davis, Z. Wu and H. Sun, Contour based motion estimation,Comput. Vis. Graph. Image Process. 23:313–326, 1983.Google Scholar
  9. 9.
    R. Deriche, Using Canny's criteria to derive a recursive implemented optical edge detector,Intern. J. Comput. Vis. 1(2):167–187, 1987.Google Scholar
  10. 10.
    M. Dhome, M. Richetin, J.T. Lapresté and G. Rives, Determination of the attitude of 3-D object from a single perspective view,IEEE Trans. Patt. Anal. Mach. Intell. PAMI 11(12): 1265–1278, 1989.Google Scholar
  11. 11.
    O.D. Faugeras and F. Lustman, Motion and structure from motion in a piecewise planar environment,Inern. J. Patt. Recog. Artif. Intell. 2(3):485–508, 1988.Google Scholar
  12. 12.
    O.D. Faugeras and S. Maybank, Motion from point matches: Multiplicity of solutions.Intern. J. Comput. Vis. 4:225–246, 1990.Google Scholar
  13. 13.
    D.A. Forsyth, J.L. Munday, A. Zisserman and C.M. Brown, Invariance: a new framework for vision,Proc. 3rd Intern. Conf. Comput. Vis. Osaka, pp. 598–605, 1990.Google Scholar
  14. 14.
    D.A. Forsyth, J.L. Munday, A. Zisserman and C.M. Brown, Projective invariant representation using implicit algebraic curves,Image and Vis. Comput. 9(2):130–136, 1991.Google Scholar
  15. 15.
    W.E.L. Grimson, Computational experiments with a feature based stereo algorithm,IEEE Trans. Patt. Anal. Mach. Intell. PAMI 7(1):17–34, 1985.Google Scholar
  16. 16.
    R.M. Haralick, Digital step edges from zero crossings of second directional derivatives,IEEE Trans. Patt. Anal. Mach. Intell. PAMI 6(1):58–68, 1984.Google Scholar
  17. 17.
    R.M. Haralick and Y.H. Chu, Solving Camera Parameters from the perspective projection of a parameterized curve,Patt. Recog. 17(6):637–645, 1984.Google Scholar
  18. 18.
    R. Horaud and T. Skordas, Stereo correspondence through feature grouping and maximal cliques,IEEE Trans. Patt. Anal. Mach. Intell. PAMI 11 (11):1168–1180, 1989.Google Scholar
  19. 19.
    R.A. Horn and C.R. Johnson,Matrix Analysis. Cambridge University Press: Cambridge, 1985.Google Scholar
  20. 20.
    P.V.C. Hough, Method and means for recognizing complex pattern, U.S. Patent, 3069654, 1962.Google Scholar
  21. 21.
    D. Huttenlocher and S. Ullman, Object recognition using alignment,Proc. 1st Intern. Conf. Comput. Vis., London, pp. 102–111, 1987.Google Scholar
  22. 22.
    D.J. Kriegman and J. Ponce, On recognizing and positioning curved 3-D objects from image contours,IEEE Trans. Patt. Anal. Mach. Intell. PAMI-12(12): 1127–1137, 1990.Google Scholar
  23. 23.
    Y. Liu and T.S. Huang, Estimation of rigid body motion using straight line correspondences: Further results,Proc. 8th Intern. Conf. Patt. Recog., Paris, pp. 306–307, 1986.Google Scholar
  24. 24.
    H.C. Longuet-Higgins, A computer algorithm for reconstructing a scene from two perspective projections,Nature 293:133–135, 1981.Google Scholar
  25. 25.
    H.C. Longuet-Higgins, Configurations that defeat the eight-point algorithm mental processes,Studies in Cognitive Science, MIT Press: Cambridge, MA, pp. 395–397, 1987.Google Scholar
  26. 26.
    Y. Lu and R.C. Jain, Behavior of edges in scale space,IEEE Trans. Patt. Anal. Mach. Intell. PAMI 11 (4):337–356, 1989.Google Scholar
  27. 27.
    S.D. Ma, S.H. Si and Z.Y. Chen, Quadric curve based stereo,Proc. IAPR Conf., Hague, The Netherlands, 1992.Google Scholar
  28. 28.
    S.D. Ma, Recognizing and positioning 3-D object based on quadratic curves, 2nd Pacific RIM Intern Conf. on AI, Korea, 1992.Google Scholar
  29. 29.
    F. Macaulay,The Algebraic Theory of Modular Systems. Cambridge, England: Cambridge Univ. Press, 1916.Google Scholar
  30. 30.
    D. Marr and T. Poggio, A computational theory of human stereo vision,Proc. Roy. Soc. London B 204:301–328, 1979.Google Scholar
  31. 31.
    G. Medioni and R. Nevatia, Segment-based stereo matching,Comput. Vis. Graph. Image Process. 31:2–18, 1985.Google Scholar
  32. 32.
    E.L. Merritt, Explicity three point resection in space,Photogrammetric Engineering 15(4):649–655, 1949.Google Scholar
  33. 33.
    H.H. Nagel, Image sequences, ten years—From phenomenology towards a theoretical foundation,Proc. 8th Intern. Conf. Patt. Recog., Paris, pp. 1174–1185, 1986.Google Scholar
  34. 34.
    N.M. Nasrabadi, Y. Lin and J.L. Chiang, Stereo vision correspondence using a multi-channel graph matching technique,Proc. Intern. Conf. Robot. Autom., Philadelphia, pp. 1804–1808, 1988.Google Scholar
  35. 35.
    G. Poggio and T. Poggio, The analysis of steropsis,Annu. Rev. Neurosci., 7:379–412, 1984.Google Scholar
  36. 36.
    T. Poggio, V. Torre and C. Koch, Computational vision and regularization theory,Nature, 317:314–319, 1985.Google Scholar
  37. 37.
    J. Porrill and S. Pollard, Curve matching and stereo calibration,Image Vis. Comput. 9(1):45–50, 1991.Google Scholar
  38. 38.
    L. Robert and O. Faugeras, Curve-based stereo: Figural continuity and curvature,Proc. Hawaii, pp. 57–61, 1991.Google Scholar
  39. 39.
    G. Salmon,Modern Higher Algebra. Hodges, Smith: Dublin Ireland, 1866.Google Scholar
  40. 40.
    H.S. Sawhney, J. Oliensis and A.R. Hanson, Description and reconstruction from image trajectories of rotational motion,Proc. 3rd Intern. Conf. Comput. Vis., Osaka, pp. 494–498, 1990.Google Scholar
  41. 41.
    J.G. Semple and G.T. Kneebone,Algebraic Projective Geometry. Clarendon Press: Oxford, 1952. Reprinted 1979.Google Scholar
  42. 42.
    S.H. Shi, Recognition and pose determination of the curved surface objects, Master thesis, National Pattern Recognition Laboratory, Chinese Academy of Sciences, Beijing, China, 1991.Google Scholar
  43. 43.
    J. Shun and S. Castan, An optical linear operator for edge detection,Proc. Conf. Comput. Vis. Patt. Recog., Miami, FL., pp. 109–114, 1986.Google Scholar
  44. 44.
    T.M. Silberberg, D.A. Harwood and L.S. Davis, Object recognition using oriented model points,Comput. Vis., Graph Image Process., 35:47–71, 1986.Google Scholar
  45. 45.
    M. Spetsakis and J. Aloimonos, Structure from motion using line correspondences,Intern. J. Comput. Vis., 4(3):171–183, 1990.Google Scholar
  46. 46.
    R. Srinivasan, K.R. Ramakrishnan and P.S. Sastry, A contour-based stereo algorithm,Proc. 1st Intern. Conf. Comput. Vis., London, pp. 677–681, 1987.Google Scholar
  47. 47.
    I.D. Svalbe, Natural representations for straight lines and the hough transform on discrete arrays,Trans. Patt. Anal. Mach. Intell., 11(9):941–950, 1989.Google Scholar
  48. 48.
    J. Tang and S.D. Ma, Straight line and conics detection,Tech. Rep., National Pattern Recognition Laboratory, Chinese Academy of Sciences, Beijing, 1991.Google Scholar
  49. 49.
    R.Y. Tsai and T.S. Huang, Estimating three-dimensional motion parameters of a rigid planar patch,IEEE Trans. Acoust., Speech, Sign. Process., 29:1147–1152, 1981.Google Scholar
  50. 50.
    R.Y. Tsai, T.S. Huang and W.L. Zhu, Estimating three-dimensional motion parameters of a rigid planar patch II: Singular value decomposition,IEEE Trans. Acoust. Speech Sign. Process., 30:525–534, 1982.Google Scholar
  51. 51.
    R.Y. Tsai and T.S. Huang, Uniqueness and estimation of 3-D motion parameters of rigid bodies with curved surfaces,IEEE Trans. Patt. Anal. Mach. Intell., 6(1):13–27, 1984.Google Scholar
  52. 52.
    G.Q. Wei, Z. He and S.D. Ma, Fusing the matching and motion estimation of rigid point patterns,Proc. IEEE Robot. Autom., Ohio, pp. 2017–2021, 1990.Google Scholar
  53. 53.
    J. Weng, T.S. Huang and N. Ahuja, Motion and structure from line correspondence: Closed-form solution, uniqueness and optimization,IEEE Trans. Patt. Anal. Mach. Intell. 14(3):318–336, 1992.Google Scholar
  54. 54.
    B.C. Yen and T.S. Huang, Determining 3-D motion and structure of a rigid body using straight line correspondences,Image Sequence Processing and Dynamic Scene Analysis, Springer-Verlag: Heidelberg Germany, 1983.Google Scholar

Copyright information

© Kluwer Academic Publishers 1993

Authors and Affiliations

  • Song De Ma
    • 1
  1. 1.National Pattern Recognition Laboratory, Institute of AutomationChinese Academy of SciencesBeijingP.R. China

Personalised recommendations