Probabilistic and Sequential Computation of Optical Flow Using Temporal Coherence

IEEE Transactions on Image Processing

Volumn 3, Issue 6, 1994, Pages 773-788

  Chin, Toshio M ^a   William, William C ^b   Willsky, Alan S ^b  

^a UNIVERSITY OF MIAMI   (United States)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTATIONAL METHODS; CONSTRAINT THEORY; ERROR ANALYSIS; ESTIMATION; KALMAN FILTERING; MATHEMATICAL MODELS; OPTICAL FLOWS; OPTIMIZATION; PROBABILITY; SPURIOUS SIGNAL NOISE;

DENSE OPTICAL FLOW FIELDS; IMAGE SEQUENCE PROCESSING; TEMPORAL COHERENT CONSTRAINT;

IMAGE PROCESSING;

EID: 0028547052     PISSN: 10577149     EISSN: 19410042     Source Type: Journal    
DOI: 10.1109/83.336247     Document Type: Article

References (47)

1. B. K. P. Horn and B. G. Schunck, “Determining optical flow,” Artificial Intell., vol. 17, pp. 185–203, 1981.
2. A. Meygret and M. Thonnat, “Segmentation of optical flow and 3D data for the interpretation of mobile objects,” in Third Int. Conf. Comput. Vision, (Osaka, Japan), 1990, pp. 238–245.
3. F. Heitz, P. Perez, E. Memin, and P. Bouthemy, “Parallel visual motion analysis using multiscale Markov random fields,” in Proc. Workshop Visual Motion. (Princeton, NJ), 1991.
4. H. C. Longuet-Higgins and K. Prazdny, “The interpretation of a moving retinal image,” Proc. Royal Soc. London B, vol. 208, pp. 385–397, 1980.
5. B. F. Buxton and H. Buxton, “Monocular depth perception from optical flow by space time signal processing,” Proc. Royal Soc. London B, vol. 218, pp. 27—47, 1983.
6. Y. Yasumoto and G. Medioni, “Robust estimation of three-dimensional motion parameters from a sequence of image frames using regularization,” IEEE Trans. Patt. Anal. Machine Intell., vol. 8, pp. 464–471, 1986.
7. L. D. Cohen and I. Cohen, “A finite element method applied to new active contour models and 3D reconstruction from cross sections,” in Proc. Third Int. Conf. Comput. Vision, (Osaka, Japan), 1990, pp. 587–591.
8. J. L. Prince and E. R. McVeigh, “Motion estimation from tagged MR image sequences,” IEEE Trans. Medical Imaging, vol. 11, pp. 238–249, 1992.
9. W. J. Emery, A. C. Thomas, M. J. Collins, W. R. Crawford, and D. L. Mackas, “An objective method for computing advective surface velocities from sequential infrared satellite images,” J. Geophys. Res., vol. 91, no. 12, pp. 865–878, 1986.
10. K. A. Kelly, “An inverse model for near-surface velocity from infrared images,” J. Phys. Oceanography, vol. 19, pp. 1845–1864, 1989.
11. A. N. Netravali and J. D. Robbins, “Motion-compensated television coding: Part I,” Bell Syst. Tech. J., vol. 58, pp. 631–670, 1979.
12. __, “Motion-compensated coding: Some new results,” Bell Syst. Tech. J., vol. 59, pp. 1735–1745, 1980.
13. B. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” in Proc. DARPA Image Understanding Workshop, 1981, pp. 121–130.
14. F. Glazer, “Hierachical motion detection,” Ph.D. thesis, Univ. of Mass., 1987.
15. H.-H. Nagel and W. Enkelmann, “An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences,” IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp. 565–593, 1986.
16. S. Uras, F. Girosi, A. Verri, and V. Torre, “A computational approach to motion perception,” Biolog. Cybern., vol. 60, pp. 79–97, 1988.
17. P. Anandan, “Measuring visual motion from image sequences,” Ph.D. thesis, Univ. of Mass, Amherst, 1987.
18. D. J. Heeger, “Optical flow using spatiotemporal filters,” Int. J. Comput. Vision, vol. 1, pp. 279–302, 1988.
19. D. J. Fleet and A. D. Jepson, “Computation of component image velocity from local phase information,” Int. J. Comput. Vision, vol. 5, pp. 77–104, 1990.
20. A. M. Waxman, J. Wu, and F. Bergholm, “Convected activation profiles and receptive fields for real time measurement of short range visual motion,” in Proc. CVPR (IEEE) (Ann Arbor, MI), 1988, pp. 717–723.
21. J. L. Barron, D. J. Fleet, S. S. Beauchemin, and T. A. Burkitt, “Performance of optical flow techniques,” Rep. no. 299, Dept. of Comput. Sci., Univ. of Western Ontario, 1991.
22. J. J. Little and A. Verri, “Analysis of differential and matching methods for optical flow,” in Proc. Workshop Visual Motion, (Irvine, CA), 1989, pp. 173–180.
23. E. C. Hildreth, “Computations underlying the measurement of visual motion,” Artif. Intell., vol. 23, pp. 309–354, 1984.
24. R. Szeliski, Baysian Modeling of Uncertainty in Low-level Vision. Norwell, MA: Kluwer, 1989.
25. T. M. Chin, M. R. Luettgen, W. C. Karl, and A. S. Willsky, “An estimation theoretic perspective on image processing and the calculation of optical flow,” in Motion Analysis and Image Sequence Processing, I. Sezan and R. Lagendijk, Eds. Norwell, MA: Kluwer, 1993.
26. T. M. Chin, W. C. Karl, and A. S. Willsky, “Sequential filtering for multi-frame visual reconstruction,” Signal Processing, vol. 28, pp. 311–333, 1992.
27. J. W. Woods and C. H. Radewan, “Kalman filtering in two dimensions,” IEEE Trans. Inform. Theory, vol. IT-23, pp. 473–482, 1977; see also “Correction” in IT-25, pp. 628–629.
28. M. S. Murphy and L. M. Silverman, “Image model representation and line-by-line recursive restoration,” IEEE Trans. Automat. Contr., vol. AC-23, pp. 809–816, 1978.
29. J. W. Woods, “Two-dimensional Kalman filtering,” in Two-Dimensional, Digital Signal Processing I, (T. S. Huang, Ed.) New York: Springer-Verlag, 1981, pp. 155–205.
30. M. Bertero, T. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE, vol. 76, pp. 869—889, 1988.
31. N. M. Grzywacz, J. A. Smith, and A. L. Yuille, “A common theoretical framework for visual motion's spatial and temporal coherence,” in Proc. Workshop Visual Motion, (Irvine, CA), 1989, pp. 148–155.
32. B. D. O. Anderson and J. B. Moore, Optimal Filtering. Englewood Cliffs, NJ: Prentice-Hall, 1979.
33. A. Gelb, Ed., Applied Optimal Estimation. Cambridge, MA: MIT Press, 1974.
34. F. L. Lewis, Optimal Estimation. New York: Wiley, 1986.
35. M. J. Black and P. Anandan, “A model for the detection of motion over time,” in Third Int. Conf. Comput. Vision, (Osaka, Japan), 1990, pp. 33–37.
36. A. Singh, “Incremental estimation of image-flow using a Kalman filter,” in Proc. Workshop Visual Motion (Princeton, NJ), 1991, pp. 36—43.
37. B. C. Levy, M. B. Adams, and A. S. Willsky, “Solution and linear estimation of 2-D nearest-neighbor models,” Proc. IEEE, vol. 78, pp. 627–641, 1990.
38. D. Terzopoulos, “Image analysis using multigrid relaxation models,” IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp. 129–139, 1986.
39. B. C. Levy, R. Frezza, and A. J. Krener, “Modeling and estimation of discrete-time Gaussian reciprocal processes,” IEEE Trans. Automat. Contr., vol. AC-35, pp. 1013–1023, 1990.
40. S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,” IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 721–741, 1984.
41. T. M. Chin, “Dynamic estimation in computational vision,” Ph.D. thesis, Mass. Inst. Technol., Cambridge, MA, 1991.
42. G. H. Golub and C. F. van Loan, Matrix Computations. Baltimore, MD: The Johns Hopkins University Press, 1989.
43. J. K. Kearney, W. B. Thompson, and D. L. Boley, “Optical flow estimation: An error analysis of gradient-based methods with local optimization,” IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 229–244, 1987.
44. D. M. Martinez, “Model-based motion estimation and its application to restoration and interpolation of motion pictures,” Ph.D. thesis, Mass. Inst. Technol., 1986.
45. M. K. Brown and B. Shahraray, “Robust depth estimation from optical flow,” in Proc. Comput. Vision Patt. Recogn. (Tampa, FL), 1988, pp. 641–650.
46. M. C. Potter and J. F. Foss, Fluid Mechanics. Okemos, MI: Great Lakes, 1982.
47. T. M. Chin and A. J. Mariano, “Optimal space-time interpolation of gappy frontal position data,” in 'Aha Huliko'a Hawaiian Winter Workshop (Probability Concepts Phys. Oceanography), 1993.