This Article 
 Bibliographic References 
 Add to: 
On Smoothness of a Vector Field-Application to Optical Flow
November 1988 (vol. 10 no. 6)
pp. 943-949

Two measures of smoothness of a vector field over a domain are suggested, together with associated smoothing operators that satisfy given constrains. The technique is illustrated using operators that smooth the invariants of optical flow curl and divergence, estimated from intensity profiles of moving nondeformable objects. The operators have been applied with satisfactory results to derived flow estimates with high noise levels.

[1] B. K. P. Horn and B. G. Schunk, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185-203, 1981.
[2] H. Nagel, "On change detection and displacement vector estimation in image sequences,"Pattern Recognition Lett., vol. 1, pp. 55-59, 1982.
[3] C. L. Fennema and W. B. Thompson, "Velocity determination in scenes containing several moving objects,"Comput. Graphics Image Processing, vol. 9, pp. 301-315, 1979.
[4] D. Marr and T. Poggio, "A computational theory of stereo vision,"Proc. Roy. Soc. London, vol. B204.
[5] S. T. Barnard and W. B. Thompson, "Disparity analysis in images,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 333- 340, 1980.
[6] W. E. L. Grimson, "A computer implementation of a theory of human stereo vision," MIT AI Memo 565, 1980.
[7] B. Vemuri, A. Mitiche, and J. K. Aggarwal, "3D object representation utilizing intrinsic surface properties," inProc. SIAM Conf. Geometric Modeling and Robotics, July 1985.
[8] D. Terzopoulos, "Multilevel computational processes for visual surface reconstruction,"Comput. Vision, Graphics, Image Processing, vol. 24, pp. 52-96, 1983.
[9] R. Paquin and E. Dubois, "A spatio-temporal gradient method for estimating the displacement field in time-varying imagery,"Comput. Vision, Graphics, Image Processing, vol. 24, pp. 205-221, 1983.
[10] A. Mitiche, "Computation of optical flow and rigid motion," inProc. Workshop Comput. Vision: Representation and Control, Annapolis, MD, Apr. 30-May 2, 1984.
[11] K. Wohn, H. Xie, and L. S. Davis, "Smoothing optical flow fields," inProc. Image Understanding Workshop, Washington, DC, 1983, pp. 61-63.
[12] E. D. Hildreth and S. Ullman, "The measurement of visual motion," MIT AI Memo 699, Dec. 1982.
[13] E. Hildreth, "Computation underlying the measurement of visual motion,"Artificial Intell., vol. 23, pp. 309-354, 1984.
[14] A. Waxman and K. Wohn, "Contour evolution, neighborhood deformation and global image flow: Planar surfaces in motion," Center Automation Res., Univ. Maryland, Tech. Rep. CAR-TR-58, Apr. 1984; alsoInt. J. Robotics Res., vol. 5, pp. 95-108, 1985.
[15] L. Davis, Zion Wu, and H. Sun, "Contour-based motion estimation,"Comput. Vision Image Processing, vol. 23, pp. 313-326, 1983.
[16] A. N. Tikhonov and V. A. Arsenin,Solutions of Ill-Posed Problems. Washington, DC: Winston, 1977.
[17] T. Poggio and V. Torre, "Ill-posed problems and regularization analysis in early vision," Memo 773, MIT AI Lab., Apr. 1984.
[18] K. Nakayama and J. M. Loomis, "Optical velocity patterns, velocity-sensitive neurons, and space perception: A hypothesis,"Perception, vol. 3, pp. 63-80, 1974.
[19] C. Jerian and R. Jain, "Determining motion parameters for scenes with translation and rotation,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, no. 4, pp. 523-530, July 1984.
[20] W. B. Thompson, "Combining motion and contrast for segmentation,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 543-549, 1980.
[21] J. L. Potter, "Scene segmentation using motion information,"Comput. Graphics Image Processing, vol. 6, pp. 558-581, 1972.
[22] W. B. Thompson and S. T. Barnard, "Lower-level interpretation of visual motion,"Computer, vol. 14, pp. 20-28, 1981.
[23] K. Prazdny, "On the information in optical flows,"Comput. Vision, Graphics, Image Processing, vol. 22, pp. 239-259, 1983.
[24] H. C. Longuet-Higgins and K. Prazdny, "The interpretation of a moving retinal image,"Proc. Roy. Soc. London, vol. B208, pp. 385- 397, 1980.
[25] A. Mitiche, "On combining stereopsis and kineopsis for space perception," inProc. First Conf. Artificial Intelligence Applications, Denver, CO, 1984, pp. 156-160.

Index Terms:
picture processing; smoothness; vector field; optical flow; intensity profiles; optical information processing; picture processing; vectors
A. Mitiche, R. Grisell, J.K. Aggarwal, "On Smoothness of a Vector Field-Application to Optical Flow," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 6, pp. 943-949, Nov. 1988, doi:10.1109/34.9116
Usage of this product signifies your acceptance of the Terms of Use.