This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Contour-Based Recovery of Image Flow: Iterative Transformation Method
August 1991 (vol. 13 no. 8)
pp. 746-760

The authors present an iterative algorithm for the recovery of 2-D motion, i.e., for the determination of a transformation that maps one image onto another. The local ambiguity in measuring the motion of contour segments (the aperture problem) implies a reliance on measurements along the normal direction. Since the measured normal flow does not agree with the actual normal flow, the full flow recovered from this erroneous flow also possesses substantial error, and any attempt to recover the 3-D motion from such full flow fails. The proposed method is based on the observation that a polynomial approximation of the image flow provides sufficient information for 3-D motion computation. The use of an explicit flow model results in improved normal flow estimates through an iterative process. The authors discuss the adequacy and the convergence of the algorithm. The algorithm was tested on some synthetic and some simple natural time-varying images. The image flow recovered from this scheme is sufficiently accurate to be useful in 3-D structure and motion computation.

[1] P. Anandan, "A unified perspective on computational techniques for the measurement of visual motion," inProc. IEEE 1'st Intl. Conf. Computer Vision, June 1987, pp. 219-230.
[2] E. H. Adelson and J. R. Bergen, "Spatiotemporal energy models for the perception of motion,"J. Opt. Soc. Amer., vol. A2, pp. 284-299, Feb. 1985.
[3] R. Brockett, "Grammians, generalized inverses, and the least squares approximation of optical flow," inProc. IEEE Conf. Robotics Automat.(Raleigh), 1987;J. Visual Commun. Image Representations, vol. 1, no. 1, pp. 1-9, 1990.
[4] P. J. Burt, C. Yen and X. Wu, "Local correlation measures for motion analysis," inProc. IEEE Conf. Computer Vision Patt. Rec., June 1982, pp. 269-274.
[5] S. Carlsson, "Sketch based representations in image coding," Ph.D. Dissertation. Elec. Engr. TRITA-TTT 8613, Roval Inst. Technol., Stockholm, Sweden, Oct. 1986.
[6] C. Fennema and W. B. Thompson, "Velocity determination in scenes containing several moving objects,"Comput. Vision Graphics Image Proc., vol. 9, pp. 301-315, 1979.
[7] W. E. L. Grimson, "Computational experiments with a feature based stereo algorithm,"IEEE Trans. Pattern Anal. Machine Intell., vol. 7, no. 1, pp. 17-34, Jan. 1985.
[8] D. Heeger, "Optical flow from spatiotemporal filters," inProc. IEEE 1'st Intl. Conf. Comput. Vision, pp. 181-190, June 1987.
[9] J.K. Kearny, W.B. Thompson, and D.L. Boley, "Optical flow estimation: An error analysis of gradient-based methods with local optimization,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 229-244, Mar. 1987.
[10] E. Hildreth, "Computation underlying the measurement of visual motion,"Artificial Intell., vol. 23, pp. 309-354, 1984.
[11] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Art. Intell., vol. 17, pp. 185-204, 1981.
[12] J. J. Koenderink and A. J. van Doorn, "Invariant properties of the motion parallel field due to the movement of rigid bodies relative to an observer,"Optica Acta, vol. 22, pp. 773-791, 1975.
[13] H. Longuet-Higgins and K. Prazdny, "The interpretation of a moving retinal Image,"Proc. Royal Soc. London B, vol. 208, pp. 385-397, 1980.
[14] J. O. Limb and J. A. Murphy, "Estimating the velocity of moving images in television signals,"Comput. Vision Graphics Image Proc., vol. 4, pp. 311-327, 1975.
[15] D. Marr and E. C. Hildreth, "Theory of edge detection,"Proc. Royal Soc. London B, vol. 207, pp. 187-217, 1980.
[16] D. Marr and S. Ullman, "Directional selectivity and its use in early visual processing," inProc. Royal Soc. London B, vol. 211, pp. 151-180, 1981.
[17] B. G. Schunck, "The image flow contraint equation,"Comput. Vision Graphics Image Proc., vol. 35, pp. 20-46, 1986.
[18] B. G. Schunck, "Image flow segmentation and estimation by constraint line clustering,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 10, pp. 1010-1027, 1989.
[19] A. M. Waxman and S. Ullman, "Surface structure and 3-D motion from image flow: A kinematic analysis,"Int. J. Robotics Res., vol. 4, pp. 72-94, 1985.
[20] A. M. Waxman and K. Wohn, "Contour evolution, neighborhood deformation and global image flow: Planar surfaces in motion,"Int. J. Robotics Res., vol. 4, pp. 95-108, 1985.
[21] K. Wohn, "Spatio-temporal multi-resolution pyramid for image motion analysis," Grasp Lab. Tech. Rep., Comput. Inform. Sci. Dept., Univ. Pennsylvania, Feb. 1990.
[22] K. Wohn and A. Waxman, "The analytic structure of image flows: Segmentation,"Comput. Vision Graphics Image Proc., vol. 49, pp. 127-151, Feb. 1990.
[23] K. Wohn and J. Wu, "3-D motion recovery from time-varying optical flows," inProc. AAAI-86, Aug. 1986, pp. 670-675.
[24] J. Wu, R. Brockett, and K. Wohn, "A contour-based recovery of image flow: Iterative method," Tech. Rep. MS-CIS-88-91, Comput. Inform. Sci. Dept., Univ. Pennsylvania, Nov. 1988.

Index Terms:
synthetic images; contour-based recovery; image flow; Iterative transformation method; 2-D motion; local ambiguity; aperture problem; polynomial approximation; 3-D motion; convergence; natural time-varying images; iterative methods; picture processing; polynomials
Citation:
K.Y. Wohn, J. Wu, R.J. Brockett, "A Contour-Based Recovery of Image Flow: Iterative Transformation Method," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 8, pp. 746-760, Aug. 1991, doi:10.1109/34.85666
Usage of this product signifies your acceptance of the Terms of Use.