Advertisement

Conclusion: Current Issues in Analysis of Visual Motion

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

Abstract

It is widely accepted that tasks such as quantitative recovery of depth and threedimensional motion require particularly accurate optical velocities computed by robust and reliable algorithms. Future studies should recognize and address this requirement. Although it is acceptable in many cases, the constraint of invariance to motion of the intensity of reflected light does not account for the subtle intensity variations that often must be taken into consideration if optical velocities are to be computed accurately (Verri and Poggio [1]). Therefore, more accurate model of image brightness formation are needed that are computationally feasible.

Keywords

Computer Vision IEEE Transaction Optical Flow Motion Estimation Machine Intelligence 
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.
    A. Verri and T. Poggio, Motion Field and Optical Flow: Qualitative Properties, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, 1989, pp. 490–498.CrossRefGoogle Scholar
  2. 2.
    A. Tamtaoui and C. Labit, Constrained Disparity and Motion Estimation for 3D TV Image Sequence Coding, Signal Processing: Image Communication, Vol. 4, 1991, pp. 45–54.CrossRefGoogle Scholar
  3. 3.
    A. M. Waxman and J. H. Duncan, Binocular Image Flows, in: Proceedings of the Workshop on Motion: Representation and Analysis, Charleston, SC, pp. 31–38 (1986).Google Scholar
  4. 4.
    A. Mitiche, A Computational Approach to the Fusion of Stereopsis and Kineopsis, in: Motion Understanding: Robot and Human Vision (W. N. Martin and J. K. Aggarwal, eds.), pp. 8199, Kluwer Academic Publishers (1988).Google Scholar
  5. 5.
    E. Hildreth, Computations Underlying the Measurement of Visual Motion, Artificial Intelligence, Vol. 23, 1984, pp. 309–354.MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    A. L. Yuille and N. M. Grzywacz, The Motion Coherence Theory, in: Second International Conference on Computer Vision, Miami, pp. 344–353 (1988).Google Scholar
  7. 7.
    F. Heitz and P. Bouthemy, Multimodal Estimation of Discontinuous Optical Flow Using Markov Random Fields, INRIA-Rennes Technical Report 561, 1991.Google Scholar
  8. 8.
    K. Nakayama and S. Shimojo, Intermediate and Higher Order Aspects of Motion Processing: Temporal and Spatial Pooling of Velocity Signals and the Role of Hidden Lines and Surfaces, in: Neural Mechanisms of Visual Perception (D. Lam and C. Gilbert, eds.), pp. 281–296, Portfolio Publishing Company, The Woodlands, TX (1989).Google Scholar
  9. 9.
    J. Aloimonos, Purposive and Qualitative Active Vision, in: Proceedings of the DARPA Image Understanding Workshop, pp. 816–828 (1990).Google Scholar
  10. 10.
    J. Aloimonos and Z. Durit, Active Egomotion Estimation: A Qualitative Approach, in: Proceedings of the Second International Conference on Computer Vision, Genoa, pp. 497510 (1992).Google Scholar
  11. 11.
    J. Aloimonos, I. Weiss, and A. Bandyopadhyay, Active Vision, in: Proceedings of the 1st International Conference on Computer Vision, London, pp. 35–54 (1987).Google Scholar
  12. 12.
    R. Bajcsy, Active Perception, Proceedings of the IEEE, Vol. 76, No. 8, 1988, pp. 996–1005.CrossRefGoogle Scholar
  13. 13.
    C. M. Brown, Prediction and Cooperation in Gaze Control, Biological Cybernetics, Vol. 63, 1990, pp. 61–70.CrossRefGoogle Scholar
  14. 14.
    G. Sandini and M. Tistarelli, Active Tracking Strategy for Monocular Depth Inference over Multiple Frames, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 1, 1990, pp. 13–27.CrossRefGoogle Scholar
  15. 15.
    F. Chaumette and S. Boukir, Structure from Motion Using an Active Vision Paradigm, in: Proceedings of the Eleventh International Conference on Pattern Recognition, The Hague, pp. 41–44 (1992).Google Scholar
  16. 16.
    A. Bandyopadhyay and D. H. Ballard, Egomotion Perception Using Visual Tracking, Computational Intelligence, Vol. 7, 1991, pp. 39–47.CrossRefGoogle Scholar
  17. 17.
    K. Pahlavan, T. Uhlin, and J. O. Eklundh, Integrating Primary Ocular Processes, in: Proceedings of the Second European Conference on Computer Vision, Genoa, pp. 526–541 (1992).Google Scholar
  18. 18.
    B. Espiau, F. Chaumette, and P. Rives, A New Approach to Visual Servoing, IEEE Transactions on Robotics and Automation, Vol. 8, No. 3, 1992, pp. 313–326.CrossRefGoogle Scholar
  19. 19.
    J. T. Feddema and O. R. Mitchell, Vision-Guided Servoing with Feature-Based Trajectory Generation, IEEE Transactions on Robotics and Automation,Vol. 5, No. 5, 1989, pp. 691700.Google Scholar
  20. 20.
    L. E. Weiss and A. C. Sanderson, Dynamic Sensor-Based Control of Robots with Visual Feedback, IEEE Transactions on Robotics and Automation, Vol. 4, 1990, pp. 39–57.Google Scholar
  21. 21.
    R. D. Rimey and C. M. Brown, Where to Look Next Using a Bayes Net: Incorporating Geometric Constraints, in: Proceedings of the Second European Conference on Computer Vision, Genoa, pp. 542–550 (1992).Google Scholar
  22. 22.
    J. Pearl, On Evidential Reasoning in a Hierarchy of Hypotheses, Artificial Intelligence, Vol. 28, 1986, pp. 9–15.CrossRefGoogle Scholar
  23. 23.
    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
  24. 24.
    C. P. Jerian and R. Jain, Structure and Motion: A Critical Analysis of Methods, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 21, 1991, pp. 572–588.MathSciNetCrossRefGoogle Scholar
  25. 25.
    G. Adiv, Inherent Ambiguities in Recovering 3D Motion and Structure from a Noisy Optical Flow Field, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, 1989, pp. 477–489.CrossRefGoogle Scholar
  26. 26.
    G. S. Young and R. Chellappa, Statistical Analysis of Inherent Ambiguities in Recovering 3D Motion from a Noisy Field, in: Proceedings of the 10th International Conference on Pattern Recognition, Atlantic City, pp. 371–377 (1990).Google Scholar
  27. 27.
    J. L. Barron, A. D. Jepson and J. K. Tsotsos, The Feasibility of Motion and Structure from Noisy Time-Varying Image Velocity Information, International Journal of Computer Vision, Vol. 5, 1990, pp. 239–269.CrossRefGoogle Scholar
  28. 28.
    K. Daniilidis, and H. H. Nagel, Analysis Results on Error Sensitivity of Motion Estimation from Two Views, Image and Vision Computing, Vol. 8, 1990, pp. 297–303.CrossRefGoogle Scholar
  29. 29.
    R. S. Jasinschi, The Properties of Space—Time Sampling and the Extraction of the Optical Flow: the Effects of Motion Uncertainty, Journal of Visual Communications and Image Representation, Vol. 2, 1991, pp. 222–229.CrossRefGoogle Scholar
  30. 30.
    J. Weng, T. S. Huang, and N. Ahuja, 3D Motion Estimation, Understanding, and Prediction from Noisy Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 9, No. 3, 1987, pp. 370–389.CrossRefGoogle Scholar
  31. 31.
    Y. Yasumoto and G. Medioni, Robust Estimation of Three-Dimensional Motion Parameters from a Sequence of Image Frames Using Regularization, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 4, 1986, pp. 464–471.CrossRefGoogle Scholar
  32. 32.
    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
  33. 33.
    H. P. Trivedi, On Computing All the Solutions to the Motion Estimation Problem with Exact and Noisy Data, Image and Vision Computing, Vol. 9, 1991, pp. 229–234.CrossRefGoogle Scholar
  34. 34.
    O. Faugeras, F. Lustman, and G. Toscani, Motion and Structure from Motion from Point and Line Matches, in: Proceedings of the First International Conference on Computer Vision, London, pp. 25–34 (1987).Google Scholar
  35. 35.
    S. Negandaripour and B. K. P. Horn, Determining 3D Motion of Planar Objects from Image Brightness Measurements, in: Proceedings of the International Joint Conference on Artificial Intelligence, Los Angeles, pp. 898–901 (1985).Google Scholar
  36. 36.
    S. Negandaripour and S. Lee, Motion Recovery from Image Sequences Using First-order Optical Flow Information, in: Proceedings of the International Conference on Computer Vision, Princeton, NJ, pp. 132–139 (1991).Google Scholar
  37. 37.
    J. Heel, Direct Estimation of Structure and Motion from Multiple Frames, MIT AI Lab. Memo No. 1190, 1990.Google Scholar
  38. 38.
    F. Meyer and P. Bouthemy, Estimation of Time-to-Collision Maps from First Order Motion Models and Normal Flows, in: Proceedings of the Eleventh International Conference on Pattern Recognition, The Hague, pp. 78–82 (1992).CrossRefGoogle Scholar
  39. 39.
    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
  40. 40.
    S. Carlsson, Information in the Geometric Structure of Retinal Flow Field, in: Proceedings of the Second International Conference on Computer Vision, pp. 629–633 (1988).CrossRefGoogle Scholar
  41. 41.
    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
  42. 42.
    J. J. Koenderink, Optical Flow, Vision Research, Vol. 26, No. 1, 1986, pp. 161–180.CrossRefGoogle Scholar
  43. 43.
    A. Verri, F. Girosi, and V. Torre, Mathematical Properties of the Two-Dimensional Motion Field–from Singular Points to Motion Parameters, Journal of the Optical Society of America A, Vol. 6, No. 5, 1989, pp. 698–712.MathSciNetCrossRefGoogle Scholar
  44. 44.
    W. B. Thompson and J. K. Kearney, Inexact vision, in: Proceedings of the IEEE Workshop on Motion: Representation and Analysis, Charleston, SC, pp. 15–21 (1986).Google Scholar
  45. 45.
    R. C. Nelson and J. Aloimonos, Obstacle Avoidance Using Flow Field Divergence, IEEE Transactions on Pattern Analysis and Machine Intelligence,Vol. 11, No. 10, 1989, pp. 11021106.Google Scholar
  46. 46.
    H. H. Nagel, From Image Sequences towards Conceptual Descriptions, Image and Vision Computing, Vol. 6, No. 2, 1988, pp. 59–74.CrossRefGoogle Scholar
  47. 47.
    W. Burger and B. Bhanu, Qualitative Motion Understanding, in: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 819–821 (1987).Google Scholar
  48. 48.
    E. François and R. Bouthemy, Derivation of Qualitative Information in Motion Analysis, Image and Vision Computing, Vol. 8, No. 4, 1990, pp. 279–287.CrossRefGoogle Scholar
  49. 49.
    W. B. Thompson and T. G. Pong, Detecting Moving Objects, International Journal of Computer Vision, Vol. 4, 1990, pp. 39–57.CrossRefGoogle Scholar
  50. 50.
    R. C. Nelson, Qualitative Detection of Motion by a Moving Observer, International Journal of Computer Vision, Vol. 7, No. I, 1991, pp. 33–46.Google Scholar
  51. 51.
    M. E. Spetsakis and J. Aloimonos, Optimal Motion Estimation, in: IEEE Workshop on Visual Motion, Irvine, CA, pp. 229–237 (1989).Google Scholar
  52. 52.
    M. Subbarao, Interpretation of Image Flow: A Spatio-Temporal Approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 3, 1989, pp. 266–278.MathSciNetCrossRefGoogle Scholar
  53. 53.
    H. Shariat and K. Price, Motion Estimation with More than Two Frames, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 5, 1990, pp. 417–434.CrossRefGoogle Scholar
  54. 54.
    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
  55. 55.
    L. Matthies, T. Kanade, and R. Szeleski, Kalman Filter Based Algorithms for Estimating Depth from Image Sequences, International Journal of Computer Vision, Vol. 3, 1989, pp. 209–236.CrossRefGoogle Scholar
  56. 56.
    J. J. Wu, R. E. Rink, T. M. Caelli, and V. G. Gourishankar, Recovery of the 3D Location and Motion of a Rigid Object through Camera Image: An Extended Kalman Filter Approach, International Journal of Computer Vision, Vol. 3, 1991, pp. 373–394.Google Scholar
  57. 57.
    R. Hummel and V. Sundareswaran, Motion Parameter Estimation from Global Flow Field Data, New York University, Courant Institute Technical Report, 1991.Google Scholar
  58. 58.
    B. Espiau and P. Rives, Closed-Loop Recursive Estimation of 3D Features for a Mobile Vision System, in: Proceedings of the IEEE Conference on Robotics and Automation, Raleigh, NC, pp. 1436–1443 (1987).Google Scholar
  59. 59.
    J. L. Crowley, P. Stelmaszyk, T. Skordas, and P. Puget, Measurement and Integration of 3D Structures by Tracking Edge Lines, International Journal of Computer Vision, Vol. 8, No. 1, 1992, pp. 29–52.CrossRefGoogle Scholar
  60. 60.
    J. A. Webb and J. K. Aggarwal, Structure from Motion of Rigid and Jointed Objects, Artificial Intelligence, Vol. 19, 1982, pp. 107–130.CrossRefGoogle Scholar
  61. 61.
    B. Horowitz and A. Pentland, Recovery of Non-Rigid Motion and Structure, in: Proceedings of the Computer Vision and Pattern Recognition Conference, Hawaii, pp. 325–330 (1991).Google Scholar
  62. 62.
    J. Leese, C. Novak, and B. Clark, An Automated Technique for Obtaining Cloud Motion from Geosynchronous Satellite Data using Cross-Correlation, Journal of Applied Meteorology, Vol. 10, 1971, pp. 118–132.CrossRefGoogle Scholar
  63. 63.
    G. E. Mailloux, F. Langlois, P. L. Simard, and M. Bertrand, Restoration of the Velocity Field of the Heart from Two-Dimensional Echocardiograms, IEEE Transactions on Medical Imaging, Vol. 8, No. 2, 1989, pp. 143–153.CrossRefGoogle Scholar
  64. 64.
    S. K. Mishra, D. B. Goldgof, and T. S. Huang, Motion Analysis and Epicardial Deformation Estimation from Angiography Data, in: Proceedings of the Computer Vision and Pattern Recognition Conference, Hawaii, pp. 331–336 (1991).Google Scholar
  65. 65.
    D. Terzopoulos, Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 7, 1991, pp. 703–714.CrossRefGoogle Scholar
  66. 66.
    A. P. Pentland, Automatic Extraction of Deformable Part Models, International Journal of Computer Vision, Vol. 4, 1990, pp. 107–126.CrossRefGoogle Scholar
  67. 67.
    A. P. Pentland and B. Horowitz, Recovery of Non Rigid Motion and Structure, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 7, 1991, pp. 730–742.CrossRefGoogle Scholar
  68. 68.
    I. Herlin and N. Ayache, Feature Extraction and Analysis Methods for Sequences of Ultrasound Images, in: Proceedings of the Second European Conference on Computer Vision, Genoa, pp. 43–57 (1992).Google Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

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

Personalised recommendations