This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Interpretation of Image Flow: A Spatio-Temporal Approach
March 1989 (vol. 11 no. 3)
pp. 266-278

A general formulation is described for the interpretation of image flow. In the framework of this formulation, computational methods have been derived for image flow interpretation for many important cases, including simple cases of nonrigid and nonuniform motions. It is possible to derive computational methods for other situations not considered explicitly. The formulation is general in that it is applicable to any situation provided that the scene geometry, the scene transformation, and the image flow are all 'smooth' or analytic.

[1] G. Adiv, "Determining 3-D motion and structure from optical flow generated by several moving objects,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 384-401, July 1985.
[2] G. Adiv, "Inherent ambiguities in recovering 3-D motion and structure from a noisy flow field," inProc. DARPA Image Understanding Workshop, Dec. 1985, pp. 399-412.
[3] R. Aris,Vectors, Tensors, and the Basic Equations of Fluid Mechanics. Englewood Cliffs, NJ: Prentice-Hall, 1962.
[4] A. Bandopadhyay and J. Aloimonos, "Perception of rigid motion from spatio-temporal derivatives of optical flow," Dep. Comput. Sci., Univ. Rochester, Tech. Rep. TR157, Mar. 1985.
[5] A. Bandopadhyay, B. Chandra, and D. H. Ballard, "Active navigation: Tracking an environmental point considered beneficial," inProc. IEEE Workshop Motion: Representation and Analysis, 1986, pp. 23- 29.
[6] S. Chen, "Structure from motion without the rigidity assumption," inProc. Third IEEE Workshop Computer Vision: Representation and Control, Oct. 1985, pp. 105-112.
[7] C. L. Fennema and W. B. Thompson, "Velocity determination in scenes containing several moving objects,"Comput. Graphics Image Process., vol. 9, pp. 301-315, 1979.
[8] J. C. Hay, "Optical motions and space perception: An extension of Gibson's analysis,"Psychol. Rev., vol. 73, pp. 550-565, 1966.
[9] E. Hildreth,The Measurement of Visual Motion, Cambridge, MA: MIT Press, 1983.
[10] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185-204, 1981.
[11] K. Kanatani, "Structure from motion without correspondence: General principle," inProc. 9th Int. Joint Conf. Artificial Intelligence, 1985, pp. 886-888.
[12] K. Kanatani, "Group theoretical methods in image understanding," Center Automation Res., Univ. Maryland, Tech. Rep. CAR-TR-214, 1986.
[13] J. J. Koenderink and A. J. van Doorn, "Invariant properties of the motion parallax field due to the movement of rigid bodies relative to an observer,"Opt. Acta, vol. 22, pp. 773-791, 1975.
[14] J. J. Koenderink and A. J. van Doom, "Depth and shape from differential perspective in the presence of bending deformations,"J. Opt. Soc. Amer., vol. A3, pp. 242-249, 1986.
[15] H. C. Longuet-Higgins and K. Prazdny, "The interpretation of a moving retinal image,"Proc. Roy. Soc. London, vol. B 208, pp. 385-397, 1980.
[16] H. C. Longuet-Higgins, "A computer algorithm for reconstructing a scene from two projections,"Nature, vol. 293, pp. 133-135, 1981.
[17] H. C. Longuet-Higgins, "The visual ambiguity of a moving plane,"Proc. Roy. Soc. London, vol. B 223, pp. 165-175, 1984.
[18] A. J. McConnell,Applications of Tensor Analysis. New York: Dover, 1957.
[19] N. Piskunov,Differential and Integral Calculus, vol. I. Moscow: Mir, 1974, p. 264.
[20] M. Subbarao, "Interpretation of image motion fields: Rigid curved surfaces in motion," Center Automation Res., Univ. Maryland, Tech Rep. CAR-TR-199, Apr. 1986.
[21] M. Subbarao, "Interpretation of image motion fields: A spatio-temporal approach," inProc. IEEE Workshop Motion: Representation and Analysis, May 1986, pp. 157-166.
[22] M. Subbarao, "Interpretation of visual motion: A computational study," Ph.D. dissertation, Dep. Comput. Sci., Univ. Maryland, 1986.
[23] M. Subbarao and A. Waxman, "On the uniqueness of image flow solutions for planar surfaces in motion,"Comput. Vision Graphics Image Processing, vol. 36, pp. 208-228, 1986.
[24] W. B. Thompson, K. M. Mutch, and V. A. Berzins, "Dynamic occlusion analysis in optical flow fields,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, no. 4, pp. 374-383, 1985.
[25] R. Y. Tsai and T. S. Huang, "Estimating three-dimensional motion parameters of a rigid planar patch," Coordinated Sci. Lab., Univ. Illinois, Tech. Rep. R-922, Nov. 1981.
[26] R. Y. Tsai and T. S. Huang, "Uniqueness and estimation of three-dimensional motion parameters of rigid objects with curved surfaces,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 13-26, Jan. 1984.
[27] S. Ullman,The Interpretation of Visual Motion. Cambridge, MA: M.I.T. Press, 1979.
[28] S. Ullman, "Maximizing the rigidity: The incremental recovery of 3-D structure from rigid and rubbery motion,"Perception, vol. 13, pp. 255-274, 1984.
[29] A. M. Waxman, "Dynamics of a couple-stress fluid membrane,"Studies Appl. Math., vol. 70, pp. 63-86, 1984.
[30] A. M. Waxman, B. Kamgar-Parsi, and M. Subbarao, "Closed-form solutions to image flow equations for 3-D structure and motion,"Int. J. Comput. Vision, vol. I, no. 3, 1987.
[31] A. M. Waxman and S. Ullman, "Surface structure and three-dimensional motion from image flow kinematics,"Int. J. Robotics Res., vol. 4, no. 3, pp. 72-94, 1985.
[32] A. M. Waxman and K. Wohn, "Contour evolution, neighborhood deformation and global image flow: Planar surfaces in motion,"Int. J. Robotics Res., vol. 4, no. 3, pp. 95-108, 1985.
[33] A. M. Waxman and K. Wohn, "Image flow theory: A framework for 3-D inference from time varying imagery," inAdvances in Computer Vision, C. M. Brown, Ed. Hillside, NJ: Erlbaum, 1986.
[34] K. Wohn, "A contour-based approach to image flow," Ph.D. dissertation, Dep. Comput. Sci., Univ. Maryland, 1984.
[35] K. Wohn and A. M. Waxman, "Contour evolution, neighborhood deformation and local image flow: Curved surfaces in motion," Center Automation Res., Univ. Maryland, Tech. Rep. CAR-TR-134, July 1985.
[36] K. Wohn and J. Wu, "3-D motion recovery from time-varying optical flows." inProc. Fifth Nat. Conf. Artificial Intelligence, Aug. 1986, pp. 671-675.

Index Terms:
image flow interpretation; motion analysis; picture processing; optical flow; pattern recognition; spatio-temporal approach; scene geometry; scene transformation; pattern recognition; picture processing
Citation:
M. Subbarao, "Interpretation of Image Flow: A Spatio-Temporal Approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 3, pp. 266-278, March 1989, doi:10.1109/34.21796
Usage of this product signifies your acceptance of the Terms of Use.