Advertisement

Optical Flow Interpretation

  • Amar Mitiche
Part of the Advances in Computer Vision and Machine Intelligence book series (ACVM)

Abstract

Our goal is to study the relation between rigid body motion in space and the motion induced by projection on a plane. We are particularly interested in computational schemes that take rigid point structures into account. A rigid point structure is a finite subfamily of points of a rigid body.

Keywords

Rigid Body Optical Flow Machine Intelligence Markov Random Field Rigid Motion 
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.
    J. J. Gibson, The Perception of the Visual World, Houghton Mifflin, Boston (1950).Google Scholar
  2. 2.
    J. J. Gibson, Optical Motions and Transformations as Stimuli for Visual Perception, Psychological Review, Vol. 64, 1957, pp. 288–295.CrossRefGoogle Scholar
  3. 3.
    K. Nakayama and J. M. Loomis, Optical Velocity Patterns, Velocity-Sensitive Neurons, and Space Perception: A Hypothesis, Perception, Vol. 3, 1974, pp. 63–80.CrossRefGoogle Scholar
  4. 4.
    J. J. Koenderink and A. J. van Doom, Invariant Properties of the Motion Parallax Field due to the Movement of Rigid Bodies Relative to an Observer, Optica Acta, Vol. 22, 1975, pp. 773–791.CrossRefGoogle Scholar
  5. 5.
    J. J. Koenderink and A. J. van Doom, Local Structure of Movement Paralax of the Plane, Journal of the Optical Society of America, A, Vol. 66, 1976, pp. 717–723.CrossRefGoogle Scholar
  6. 6.
    W. F. Clocksin, Perception of Surface Slant and Edge Labels from Optical Flow: A Computational Approach, Perception, Vol. 9, 1980, pp. 253–269.CrossRefGoogle Scholar
  7. 7.
    D. D. Hoffman, Inferring Local Surface Orientation from Motion Fields, Journal of the Optical Society of America A, Vol. 72, 1982, pp. 888–892.Google Scholar
  8. 8.
    H. C. Longuet-Higgins and K. Prazdny, The Interpretation of a Moving Retinal Image, Proceedings of the Royal Society of London B, Vol. 208, 1980, pp. 385–397.CrossRefGoogle Scholar
  9. 9.
    K. Prazdny, Egomotion and Relative Depth Map from Optical Flow, Biological Cybernetics, Vol. 36, 1980, pp. 87–102.MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    K. Prazdny, On the Information in Optical Flows, Computer Vision, Graphics, and Image Processing, Vol. 22, 1983, pp. 239–259.CrossRefGoogle Scholar
  11. 11.
    A. R. Bross and B. K. P. Hom, Passive navigation, Computer Vision, Graphics and Image Processing, Vol. 21, 1983, pp. 3–20.CrossRefGoogle Scholar
  12. 12.
    G. Adiv, Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 7, 1985, pp. 384–401.CrossRefGoogle Scholar
  13. 13.
    J. H. Rieger and D. T. Lawton, Processing Differential Image Motion, Journal of the Optical Society of America, A, Vol. 2, 1985, pp. 354–360.CrossRefGoogle Scholar
  14. 14.
    A. M. Waxman and S. Ullman, Surface Structure and Three-Dimensional Motion from Image Flow Kinematics, International Journal of Robotics Research, Vol. 4, 1985, pp. 72–94.CrossRefGoogle Scholar
  15. 15.
    M. Subbarao and A. M. Waxman, On the Uniqueness of Image Flow Solutions for Planar Surfaces in Motion, in: Proceedings of the IEEE Workshop on Computer Vision: Representation and Control, Bellaire, MI, pp. 129–140 (1986).Google Scholar
  16. 16.
    S. Negandaripour and B. K. P. Horn, Direct Passive Navigation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 9, No. 1, 1987, pp. 168–176.CrossRefGoogle Scholar
  17. 17.
    S. J. Maybank, The Angular Velocity Associated with the Optical Flow Field Due to a Rigid Moving Body, Proceedings of the Royal Society of London A, Vol. 401, 1985, pp. 317–326.MathSciNetCrossRefGoogle Scholar
  18. 18.
    S. J. Maybank, Algorithm for Analyzing Optical Flow Based on the Least Squares Method, Image and Vision Computing, Vol. 4, 1986, pp. 38–42.CrossRefGoogle Scholar
  19. 19.
    K. Kanatani, Structure and Motion from Optical Flow under Orthographic Projection, Computer Vision, Graphics, and Image Processing, Vol. 35, 1986, pp. 181–199.zbMATHCrossRefGoogle Scholar
  20. 20.
    X. Zhuang and R. M. Haralick, Rigid Body Motion and the Optical Flow Image, in: Proceedings of the First International Conference on Artificial Intelligence Applications, Denver, pp. 366–375 (1984).Google Scholar
  21. 21.
    X. Zhuang, T. S. Huang, and N. Ahuja, A Simplified Linear Optic Flow Motion Algorithm, Computer Vision, Graphics, and Image Processing, Vol. 42, 1988, pp. 334–343.CrossRefGoogle Scholar
  22. 22.
    A. Mitiche, X. Zhuang, and R. M. Haralick, Interpretation of Optical Flow by Rotation Decoupling, in: Proceedings of the IEEE Workshop on Motion, Miami Beach, FL, pp. 195200 (1987).Google Scholar
  23. 23.
    C. Lee, R. M. Haralick, and X. Zhuang, Recovering 3D Motion Parameters from Image Sequences with Gross Errors, in: Proceedings of the IEEE Workshop on Visual Motion, Irvine, CA, pp. 46–53 (1989).Google Scholar
  24. 24.
    P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outliers Detection, John Wiley, New York (1987).CrossRefGoogle Scholar
  25. 25.
    H. C. Longuet-Higgins, The Visual Ambiguity of a Moving Plane, in: Proc. Royal Society London B, pp. 233 ( 165–175 ). 1984Google Scholar
  26. 26.
    R. Y. Tsai and T. S. Huang, Estimating Three-Dimensional Motion Parameters of a Rigid Planar Patch, IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 29, No. 6, 1981, pp. 1147–1152.Google Scholar
  27. 27.
    R. Y. Tsai, T. S. Huang, and W. Zhu, Estimating Three-Dimensional Motion Parameters of a Rigid Planar Patch, II: Singular Value Decomposition, IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 30, No. 4, 1982, pp. 525–534.Google Scholar
  28. 28.
    O. Faugeras and S. J. Maybank, Motion from Point Matches: Multiplicity of Solutions, International Journal of Computer Vision, Vol. 4, 1990, pp. 225–246.CrossRefGoogle Scholar
  29. 29.
    M. Subbarao and A. M. Waxman, On the Uniqueness of Image Flow Solutions for Planar Surfaces in Motion, Computer Vision, Graphics, and Image Processing, Vol. 36, 1986, pp. 208–228.Google Scholar
  30. 30.
    B. K. P. Horn and B. G. Schunck, Determining Optical Flow, Artificial Intelligence, Vol. 17, 1981, pp. 185–203.CrossRefGoogle Scholar
  31. 31.
    S. Negandaripour, Direct Passive Navigation, PhD Thesis, Department of Mechanical Engineering, MIT, 1986.Google Scholar
  32. 32.
    A. M. Waxman, B. Kamgar-Parsi, and M. Subbarao, Closed-Form Solutions to Image Flow Equations for 3D Structure and Motion, International Journal of Computer Vision, Vol. 1, No. 3, 1987, pp. 239–258.CrossRefGoogle Scholar
  33. 33.
    B. K. P. Horn, Motion Fields Are Hardly Ever Ambiguous, International Journal of Computer Vision, Vol. 1, 1987, pp. 259–274.CrossRefGoogle Scholar
  34. 34.
    G. Adiv, Inherent Ambiguities in Recovering 3D Motion and Structure from a Noisy Optical Flow Field, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, pp. 70–77 (1985).Google Scholar
  35. 35.
    A. Mitiche, On Combining Stereopsis and Kineopsis for Space Perception, in: First International Conference on Artificial Intelligence Applications, Denver, pp. 156–160 (1984).Google Scholar
  36. 36.
    A. Mitiche and G. Habelrih, Interpretation of Straight Line Correspondences Using Angular Relations, Pattern Recognition, Vol. 22, 1989, pp. 299–308.CrossRefGoogle Scholar
  37. 37.
    A. Mitiche, Three-Dimensional Space from Optical Correspondence, Computer Vision, Graphics, and Image Processing, Vol. 42, 1988, pp. 306–317.Google Scholar
  38. 38.
    W. Richard, Structure from Stereo and Motion, Journal of the Optical Society of America A, Vol. 2, 1985, pp. 343–349.CrossRefGoogle Scholar
  39. 39.
    A. M. Waxman and S. Sinha, Dynamic Stereo: Passive Ranging to Moving Objects from Relative Image Flows, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, 1986, pp. 406–412.CrossRefGoogle Scholar
  40. 40.
    A. M. Waxman and J. Duncan, Binocular Image Flows: Steps Toward Stereo-Motion Fusion, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, 1986, pp. 715–729.CrossRefGoogle Scholar
  41. 41.
    K. Sugihara and N. Sugie, Recovery of Rigid Structure from Orthographically Projected Optical Flow, Computer Vision, Graphics, and Image Processing,Vol. 27, 1984, pp. 309320.Google Scholar
  42. 42.
    H. Tsukune and J. K. Aggarwal, Analysing Orthographic Projection of Multiple 3D Velocity Vector Fields in Optical Flow, in: Proceedings of the Computer Vision and Pattern Recognition Conference, San Francisco, pp. 510–517 (1985).Google Scholar
  43. 43.
    J. Barron, A Survey of Approaches for Determining Optical Flow, Environmental Layout, and Egomotion, University of Toronto Dept. of Computer Science Technical Report 84–5, 1984.Google Scholar
  44. 44.
    S. Ullman, Maximizing Rigidity: The Incremental Recovery of 3D Structure from Rigid and Non-Rigid Motion, Perception, Vol. 13, 1984, pp. 255–274.CrossRefGoogle Scholar
  45. 45.
    E. C. Hildreth and N. Grzywacz, The Incremental Recovery of Structure from Motion: Position vs. Velocity Based Formulations, in: Proceedings of the IEEE Workshop on Motion: Representation and Analysis, pp. 137–143 (1986).Google Scholar
  46. 46.
    T. J. Broida and R. Chellapa, Estimation of Object Motion Parameters from Noisy Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 1, 1986, pp. 90–99.CrossRefGoogle Scholar
  47. 47.
    T. J. Broida and R. Chellappa, Estimating the Kinematics and Structure of a Rigid Object from a Sequence of Monocular Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 6, 1991, pp. 497–513.CrossRefGoogle Scholar
  48. 48.
    J. Aloimonos and C. M. Brown, Direct Processing of Curvilinear Sensor Motion from a Sequence of Perspective Images, in: Proceedings of the IEEE Workshop on Computer Vision: Representation and Analysis, Annapolis, MD, pp. 72–77 (1984).Google Scholar
  49. 49.
    B. K. P. Horn and E. J. Weldon, Direct Methods for Recovering Motion, International Journal of Computer Vision, Vol. 2, 1988, pp. 51–76.CrossRefGoogle Scholar
  50. 50.
    H. C. Longuet-Higgins, A Computer Algorithm for Reconstructing a Scene from Two Projections, Nature, Vol. 293, 1981, pp. 133–135.CrossRefGoogle Scholar
  51. 51.
    R. Y. Tsai and T. S. Huang, Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 6, No. 1, 1984, pp. 13–26.MathSciNetCrossRefGoogle Scholar
  52. 52.
    S. Ullman, Two-Dimensionality of the Correspondence Process in Apparent Motion, Perception, Vol. 7, 1978, pp. 405–426.CrossRefGoogle Scholar
  53. 53.
    K. Mutch, I. M. Smith, and A. Yonas, The Effect of Two-Dimensional and Three-Dimensional Distance on Apparent Motion, Perception, Vol. 3, 1983, pp. 305–312.CrossRefGoogle Scholar
  54. 54.
    S. Geman and D. D. Geman, Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 6, No. 6, 1984, pp. 721–741.zbMATHCrossRefGoogle Scholar
  55. 55.
    J. Konrad and E. Dubois, Bayesian Estimation of Motion Vector Fields, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 9, 1992, pp. 910–927.CrossRefGoogle Scholar
  56. 56.
    D. Geiger and F. Girosi, Parrallel and Deterministic Algorithms from MRFs: Surface Reconstruction and Integration, in: Proceedings of the First European Conference on Computer Vision, Antibes, France, pp. 89–98 (1989).Google Scholar
  57. 57.
    R. Laganiere and A. Mitiche, Direct Bayesian Estimation of Visual Motion, INRSTélécommunications Technical Report 92–27, 1992.Google Scholar

Bibliography

  1. 1.
    D. H. Ballard and O. A. Kimball, Rigid Body Motion from Optical Flow and Depth, Computer Vision, Graphics, and Image Processing, Vol. 22, 1983, pp. 95–115.Google Scholar
  2. 2.
    T. C. Chou and K. Kanatani, Recovering 3D Rigid Motion without Correspondence, in: Proceedings of the First International Conference on Computer Vision, London, pp. 534538 (1987).Google Scholar
  3. 3.
    J. J. Gibson, P. Olum, and F. Rosenblatt, Parallax and Perspective During Aircraft Landings, American Journal of Psychology, Vol. 68, 1958, pp. 372–385.CrossRefGoogle Scholar
  4. 4.
    E. J. Gibson, J. J. Gibson, O. W. Smith, and H. Flock, Motion Parallax as a Determinant of Perceived Depth, Journal of Experimental Psychology, Vol. 58, 1959, pp. 40–51.CrossRefGoogle Scholar
  5. 5.
    D. D. Hoffman and B. E. Flinchbaugh, The Interpretation of Biological Motion, Biological Cybernetics, Vol. 42, 1982, pp. 195–204.zbMATHGoogle Scholar
  6. 6.
    B. K. P. Horn, Robot Vision, MIT Press, Cambridge, MA (1986).Google Scholar
  7. 7.
    R. Jain, Direct Computation of the Focus of Expansion, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 5, No. 1, 1983, pp. 58–64.CrossRefGoogle Scholar
  8. 8.
    C. Jerian and R. Jain, Determining Motion Parameters for Schemes with Translation and Rotation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 6, No. 4, 1984, pp. 523–529.CrossRefGoogle Scholar
  9. 9.
    G. Johansson, Visual Motion Perception, Scientific American, Vol. 232, 1975, pp. 76–88.CrossRefGoogle Scholar
  10. 10.
    J. J. Koenderink, Space, Form and Optical Deformations, in: Brain Mechanisms and Spatial Vision ( D. J. Ingle, M. Jeannerod, and D. N. Lee, Eds.), pp. 31–58, Nijhoff, Amsterdam (1985).CrossRefGoogle Scholar
  11. 11.
    J. J. Koenderink and A. J. van Doom, Depth and Shape from Differential Perspective in the Presence of Bending Deformations, Journal of the Optical Society of America A, Vol. 3, 1986, pp. 242–249.CrossRefGoogle Scholar
  12. 12.
    J. J. Koenderink, Optical Flow, Vision Research, Vol. 26, No. 1, 1986, pp. 161–180.CrossRefGoogle Scholar
  13. 13.
    D. T. Lawton, Motion Analysis via Local Translational Motion, in: Proceedings of the Workshop on Computer Vison, Rindge, NH, pp. 59–72 (1982).Google Scholar
  14. 14.
    K. Nakayama and J. M. Loomis, Optical Velocity Patterns, Velocity-sensitive Neurons, and Space Perception, Perception, Vol. 3, 1974, pp. 63–80.CrossRefGoogle Scholar
  15. 15.
    K. Nakayama, Biological Image Motion Processing: A Review, Vision Research, Vol. 25, 1985, pp. 625–660.CrossRefGoogle Scholar
  16. 16.
    B. Neumann, Optical Flow, Computer Graphics, Vol. 18, No. 1, 1984, pp. 17–19.CrossRefGoogle Scholar
  17. 17.
    K. Prazdny, Determining the Instantaneous Direction of Motion from Optical Flow Generated by a curvilinearly Moving Observer, Computer Graphics and Image Processing, Vol. 17, 1981, pp. 238–248.CrossRefGoogle Scholar
  18. 18.
    J. H. Rieger and D. H. Lawton, Determining the Instantaneous Axis of Translation from Optical Flow Generated by Arbitrary Sensor Motion, in: Proceedings of the Workshop on Motion: Representation and Perception, Toronto, pp. 33–41 (1983).Google Scholar
  19. 19.
    M. Subbarao and A. M. Waxman, On the Uniqueness of Image Flow Solutions for Planar Surfaces in Motion, in: Proceedings of the IEEE Workshop on Computer Vision: Representation and Control, Bellaire, MI, pp. 129–140 (1986).Google Scholar
  20. 20.
    M. Subbarao, Solution and Uniqueness of Image Flow Equations for Rigid Curved Surfaces in Motion, in: Proceedings of the First International Conference on Computer Vision, London, pp. 687–692 (1987).Google Scholar
  21. 21.
    H. Wallach and D. N. O’Connell, The Kinetic Depth Effect, Journal of Experimental Psychology, Vol. 45, 1953, pp. 205–217.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Amar Mitiche
    • 1
  1. 1.INRS-TelecommunicationsMontrealCanada

Personalised recommendations