The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding

Volumn 63, Issue 1, 1996, Pages 75-104

  Black, Michael J ^a   Anandan, P ^b  

^a PALO ALTO RESEARCH CENTER   (United States)

^b SARNOFF CORPORATION   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; CONSTRAINT THEORY; IMAGE PROCESSING; OPTICAL FLOWS; PARAMETER ESTIMATION;

BRIGHTNESS CONSTANCY ASSUMPTION; MULTIPLE MOTIONS; MULTIPLE PARAMETRIC MOTION MODELS; OPTICAL FLOW RECOVERY; PARAMETRIC FLOW; PIECEWISE SMOOTH FLOW; ROBUST ESTIMATION; SPATIAL SMOOTHNESS ASSUMPTION;

IMAGE ANALYSIS;

EID: 0029772518     PISSN: 10773142     EISSN: None     Source Type: Journal    
DOI: 10.1006/cviu.1996.0006     Document Type: Article

References (59)

1. G. Adiv, Recovering motion parameters in scenes containing multiple moving objects, in Proc. Int. Conf. on Pattern Recognition, Washington, DC, June 1983, pp. 399-400.
2. P. Anandan, A computational framework and an algorithm for the measurement of visual motion, Int. J. Comput. Vision 2, 1989, 283-310.
3. J. L. Barron, D. J. Fleet, and S. S. Beauchemin, Performance of Optical Flow Techniques, Technical Report RPL-TR-9107, Univ. of Western Ontario, July 1993.
4. J. R. Bergen, P. Anandan, K. J. Hanna, and R. Hingorani, Hierarchical model-based motion estimation, in Proc. of Second European Conference on Computer Vision, ECCV-92 (G. Sandini, Ed.), Lecture Notes in Computer Science, Vol. 588 pp. 237-252, Springer-Verlag, Berlin/ New York, 1992.
5. J. R. Bergen, P. J. Burt, R. Hingorani, and S. Peleg, A three-frame algorithm for estimating two-component image motion, IEEE Trans. Pattern Anal. Mach. Intell. 14(9), Sept. 1992, 886-896.
6. M. J. Black, Robust Incremental Optical Flow, Ph.D. thesis, Yale Univ., New Haven, CT, 1992; Research Report YALEU/DCS/ RR-923.
7. M. J. Black and P. Anandan, Constraints for the early detection of discontinuity from motion, in Proc. National Conf. on Artificial Intelligence, AAAI-90, Boston, MA, 1990, pp. 1060-1066.
8. M. J. Black and P. Anandan, A model for the detection of motion over time, in Proc. Int. Conf. on Computer Vision, ICCV-90, Osaka, Japan, Dec. 1990, pp. 33-37.
9. M. J. Black and P. Anandan, Robust dynamic motion estimation over time, in Proc. Computer Vision and Pattern Recognition, CVPR-91, Maui, HI, June 1991, pp. 296-302.
10. M. J. Black and P. Anandan, A framework for the robust estimation of optical flow, in Proc. Int. Conf. on Computer Vision, ICCV-93, Berlin, Germany, May 1993, pp. 231-236.
11. M. J. Black and A. Rangarajan, The outlier process: Unifying line processes and robust statistics, in Proc. Computer Vision and Pattern Recognition, CVPR-94, Seattle, WA, June 1994, pp. 15-22.
12. A. Blake and A. Zisserman,Visual Reconstruction. The MIT Press, Cambridge, MA, 1987.
13. P. J. Burt, J. R. Bergen, R. Hingorani, R. Kolczynski, W. A. Lee, A. Leung, J. Lubin, and H. Shvaytser, Object tracking with a moving camera: An application of dynamic motion analysis, in : Proceedings of the Workshop on Visual Motion, Irvine, CA, Mar. 1989, pp. 2-12.
14. N. Cornelius and T. Kanada, Adapting optical flow to measure object motion in reflectance and X-ray image sequences, in Proc. ACM Siggraph/Sigart Interdisciplinary Workshop on Motion: Representation and Perception, Toronto, Ont., Canada, Apr. 1983, pp. 50-58.
15. T. Darrell and A. Pentland, Discontinuity Models and Multi-Layer Description Networks. Technical Report 162, MIT Media Lab Vision and Modeling Group, May 1991.
16. C. L. Fennema and W. B. Thompson, Velocity determination in scenes containing several moving objects, Comput. Graphics Image Process. 9, 1979, 301-315.
17. D. J. Fleet and A. D. Jepson, Computation of component image velocity from local phase information, Int. J. Comput. Vision 5, 1990, 77-104.
18. D. Geiger and F. Girosi, Parallel and deterministic algorithms from MRFs: Surface reconstruction, IEEE Trans. Pattern Anal. Mach. Intell. 13(5), May 1991, 401-412.
19. S. Geman and D. Geman, Stochastic relaxation, Gibbs distributions and Bayesian restoration of images, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-6(6), Nov. 1984, 721-741.
20. S. Geman and D. E. McClure, Statistical methods for tomographic image reconstruction, Bull. Int. Statist. Inst. LII-4, 1987, 5-21.
21. F. Glazer, Hierarchical Motion Detection, Ph.D. thesis, Univ. of Massachusetts, Amherst, MA, 1987; COINS TR 87-02.
22. F. R. Hampel, E. M. Ronchetti, P. J. Rousseeuw, and W. A. Stahel, Robust Statistics: The Approach Based on Influence Functions, Wiley, New York, 1986.
23. J. G. Harris, C. Koch, E. Staats, and J. Luo, Analog hardware for detecting discontinuities in early vision, Int. J. Comput. Vision 4(3), June 1990, 211-223.
24. D. J. Heeger, Model for the extraction of image flow, J. Opt. Soc. Am. 4(8), Aug. 1987, 1455-1471.
25. J. Heel, Temporally integrated surface reconstruction, in Proc. IEEE Int. Conf. on Comp. Vision, ICCV-90, Osaka, Japan, Dec. 1990, pp. 292-295.
26. B. K. P. Horn, Robot Vision, The MIT Press, Cambridge, MA, 1986.
27. B. K. P. Horn and B. G. Schunck, Determining optical flow, Artif. Intell. 17(1-3), Aug. 1981, 185-203.
28. P. J. Huber, Robust Statistics, Wiley, New York, 1981.
29. M. Irani, B. Rousso, and S. Peleg, Detecting and tracking multiple moving objects using temporal integration, in Proc. of Second European Conference on Computer Vision, ECCV-92 (G. Sandini, Ed.), Lecture Notes in Computer Science, Vol. 588, pp. 282-287, Springer-Verlag, Berlin/New York, 1992.
30. A. Jepson and M. J. Black, Mixture models for optical flow computation, in Proc. Computer Vision and Pattern Recognition, CVPR-93, New York, June 1993, pp. 760-761.
31. 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. Pattern Anal. Mach. Intell. 9, 1987, 229-244.
32. J. Konrad and E. Dubois, Multigrid Bayesian estimation of image motion fields using stochastic relaxation, in Int. Conf. on Computer Vision, 1988, pp. 354-362.
33. Y. G. Leclerc, Constructing simple stable descriptions for image partitioning, Int. J. Comput. Vision 3(1), 1989, 73-102.
34. B.D. Lucas and T. Kanade, An iterative image registration technique with an application to stereo vision, in Proc. 7th IJCAI, Vancouver, B. C., Canada, 1981, pp.674-679.
35. S. Madarasmi, D. Kersten, and T. C. Pong, Multi-layer surface segmentation using energy minimization, in Proc. Computer Vision and Pattern Recognition, CVPR-93, New York, June 1993, pp. 774-775.
36. J. Marroquin S. Mitter, and T. Poggio, Probabilistic solution of illposed problems in computational vision, J. Am. Stat. Assoc. 82(397), Mar. 1987, 76-89.
37. P. Meer, D. Mintz, A. Rosenfeld, and D. Y. Kim, Robust regression methods for computer vision: A review, Int. J. Comput. Vision 6(1), 1991, 59-70.
38. D. W. Murray and B. F. Buxton, Scene segmentation from visual motion using global optimization, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-9(2), Mar. 1987, 220-228.
39. H. H. Nagel, On the estimation of optical flow: Relations between different approaches and some new results, Artif. Intell. 33(3), Nov. 1987, 299-324.
40. H. H. Nagel and W. Enkelmann, An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(5), Sept. 1986, 565-593.
41. S. Negahdaripour and C. Yu, A generalized brightness change model for computing optical flow, in Proc. Int. Conf. on Computer Vision, ICCV-93, Berlin, Germany, May 1993, pp. 2-11.
42. M. Okutomi and T. Kanada, A locally adaptive window for signal matching, Int. J. Comput. Vision 7(2), Jan. 1992, 143-162.
43. P. Perona and J. Malik, Scale-space and edge detection using anisotropic diffusion, IEEE Trans. Pattern Anal. Mach. Intell. 12(7), July 1990, 629-639.
44. T. Poggio, V. Torre, and C. Koch, Computational vision and regularization theory, Nature 317(26), Sept. 1985, 314-319.
45. W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes in C: The Art of Scientific Computing, Cambridge Univ. Press, Cambridge, 1988.
46. A. Rangarajan and R. Chellappa, A continuation method for image estimation using the adiabatic approximation, in Markov Random Fields: Theory and Applications (R. Chellappa and A. Jain, Eds.), Academic Press, San Diego, 1993.
47. P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection, Wiley, New York, 1987.
48. B. G. Schunck, Image flow segmentation and estimation by constraint line clustering, IEEE Trans. Pattern Anal. Mach. Intell. 11(10), Oct. 1989, 1010-1027.
49. M. Shizawa and K. Mase, Principle of superposition: A common computational framework for analysis of multiple motion, in Proc. IEEE Workshop on Visual Motion, Princeton, NJ, Oct. 1991, pp. 164-172.
50. D. Shulman and J. Hervé, Regularization of discontinuous flow fields, in Proc. Workshop on Visual Motion, Irvine, CA, Mar. 1989, pp. 81-85, IEEE Comput. Soc. Press, Los Alamitos, CA, 1989.
51. A. Singh, Optical Flow Computation: A Unified Perspective, IEEE Comput. Soc. Press, Los Alamitos, CA, 1992.
52. G. Strang, Linear Algebra and Its Applications, Academic Press, New York, 1976.
53. W. B. Thompson, K. M. Mutch, and V. A. Berzins, Dynamic occlusion analysis in optical flow fields, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-7(4), July 1985, 374-383.
54. Y. Tian and M. Shah, MRF-Based Motion Estimation and Segmentation, Technical Report CS-TR-92-13, Univ. of Central Florida, Orlando, FL, July 1992.
55. S. Uras, F. Girosi, A. Verri, and V. Torre, A computational approach to motion perception, Biol. Cybernet. 60, 1989, 79-97.
56. R. S. Varga, Matrix Iterative Analysis, Prentice-Hall, Englewood Cliffs, NJ, 1962.
57. J. Y. A. Wang and E. H. Adelson, Layered representation for motion analysis, in Proc. Computer Vision and Pattern Recognition, CVPR-93, New York, June 1993, pp. 361-366.
58. A. M. Waxman and K. Wohn, Contour evolution, neighbourhood deformation and global image flow: Planar surface in motion, Int. J. Robotics Res. 4, 1985, 95-108.
59. J. Weber and J. Malik, Robust computation of optical flow in a multiscale differential framework, in Proc. Int. Conf. on Computer Vision, ICCV-93, Berlin, Germany, May 1993, pp. 12-20.