This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Diffusion Mechanism for Obstacle Detection from Size-Change Information
January 1994 (vol. 16 no. 1)
pp. 76-80

A mechanism fur the visual detection of obstacles is presented. A new immediacy measure, representing the imminence of collision between an object and a moving observer, is defined. A diffusion process on the image domain, whose initial condition is determined by the motion field normal to the object's boundary, is shown to converge asymptotically to the immediacy measure. A network of locally connected cells, derived from a finite-difference approximation of the diffusion equation, estimates the immediacy measure from normal velocity and boundary information provided by a motion measurement and segmentation stage. The algorithm's performance on real image sequences is demonstrated.

[1] S. Ullman,The Interpretation of Visual Motion. Cambridge, MA: MIT Press, 1979.
[2] H. C. Longuet-Higgins and K. Prazdny, "The interpretation of a moving retinal image,"Proc. R. Soc. London B, vol. 208, pp. 385-397, 1980.
[3] K. Prazdny, "Egomotion and relative depth map from optical flow,"Biological Cybernetics, vol. 36, pp. 87-102, 1980.
[4] K. Prazdny, "Determining the instantaneous direction of motion from optical flowgenerated by a curvilinearly moving observer,"Computer Graphics and Image Processing, vol. 17, pp. 238-248, 1981.
[5] A. R. Bruss and B. K. P. Horn, "Passive navigation,"Computer Vision, Graphics, and Image Processing, vol. 21, pp. 3-20, 1983.
[6] J. H. Rieger and D. T. Lawton, "Processing differential image motion,"J. Opt. Soc. Am. A, vol. 2, pp. 354-359, Feb. 1985.
[7] A. M. Waxman and K. Wohn, "Image flow theory: A framework for 3-D inference from time-varying imagery," in C. Brown, Ed.,Advances in Computer Vision, Volume 1. New York: Lawrence Braum Associates, 1988.
[8] R. Y. Tsai and T. S. Wang, "Uniqueness and estimation of three-dimensional motion parameters of rigid objects with curved surfaces,"IEEE. Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 13-27, 1984.
[9] G. Adiv, "Determining three-dimensional motion and structure from optical flow generated by several moving objects,"IEEE. Trans. Pattern Anal. Machine Intell., vol. PAMI-7, no. 4, pp. 384-401, July 1985.
[10] A. Verri and T. Poggio, "Against quantitative optical flow,"Int. Conf. Computer Vision, June 1987, pp. 171-180.
[11] G. Adiv, "Inherent ambiguities in recovering 3-D motion and structure from a noise flow field,"IEEE. Trans. Pattern Anal. Machine Intell., vol. PAMI-11, no. 5, pp. 477-489, May 1989.
[12] W. B. Thompson and J. K. Kearney, "Inexact vision,"Workshop on Motion, Representation, and Analysis, pp. 15-22, May 1986.
[13] R. C. Nelson and J. Aloimonos, "Obstacle avoidance using flow field divergence,"IEEE. Trans. Pattern Anal. Machine Intell., vol. PAMI-11, no. 10, pp. 1102-1106, Oct. 1989.
[14] K. I. Beverley and D. Regan, "Texture changes versus size changes as stimuli for motion in depth,"Vision Res., vol. 23, no. 12, pp. 1387-1400, 1983.
[15] R. C. Nelson and J. Aloimonos, "Finding motion parameters from spherical motion fields (or the advantages of having eyes in the back of your head),"Biological Cybernetics, vol. 58, pp. 261-273, 1988.
[16] 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,"Optica Acta, vol. 22, no. 9, pp. 773-791, 1975.
[17] J. J. Koenderink and A. J. van Doorn, "Local structure of movement parallax of the plane,"J. Opt. Soc. of Am. A, vol. 66, no. 7, pp. 717-723, July 1976.
[18] J. Koenderink, "Optic flow,"Vision Res., vol. 26, no. 1, pp. 161-180, 1986.
[19] M. Subbarao, "Interpretation of visual motion: A computational study," Center for Automation Res., Univ. of Maryland, College Park, Tech. Rep. CAR-TR-221, Sept. 1986.
[20] M. Subbarao, "Bounds on translational and angular velocity components from first order derivatives of image flow,"Proc. AAAI '87, pp. 744-748.
[21] A. M. Goodbody,Cartesian Tensors. New York: Wiley, 1982.
[22] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intelligence, vol. 17, pp. 185-203, 1981.
[23] A. N. Tikhonov and V. Y. Arsenin,Solutions of Ill-Posed Problems, Wiley, 1977.
[24] D. L. Ringach, "A diffusion network for obstacle detection based on size-change information," M.S. thesis, Dept. of Elec. Eng., Technion, Israel Inst. of Tech., Haifa, Israel, 1990, in preparation (in Hebrew).
[25] H. Wagner, "Flow-field variables trigger landing in flies,"Nature, vol. 297, pp. 147-148, May 1982.
[26] D. N. Lee, "A theory of visual control of braking based on information about time-to-collision,"Perception, vol. 5, pp. 437-459, 1976.
[27] W. Schift and M. L. Detwiler, "Information used in judging impending collision,"Perception, vol. 8, pp. 647-658, 1979.
[28] M. N. Davies and P. R. Green, "Head-bobbing during walking, running, and flying: Relative motion perception in the pigeon,"J. Exp. Biology, vol. 138, pp. 71-91, 1988.
[29] S. Young and V. A. Taylor, "Visually guided chases in Polyphemus Pediculus,"J. Exp. Biology, vol. 137, pp. 387-398, 1988.
[30] A. Friedman,Generalized Functions and Partial Differential Equations. Englewood Cliffs, NJ: Prentice-Hall Inc., 1963.
[31] A. Friedman,Partial Differential Equations of Parabolic Type. Englewood Cliffs: NJ: Prentice-Hall Inc., 1964.
[32] E. Zauderer,Partial Differential Equations of Applied Mathematics, 2nd Edition, New York: Wiley, 1989.
[33] J. M. Berezanskii,Expansions in Eigenfunctions of Selfadjoint Operators, vol. 17 ofTranslations of Mathematical Monographs. New York: American Mathematical Society, 1968.
[34] H. Weyl, "Über die asymptotische verteilung der eigenwerte,"Gott Nach., pp. 110-117, 1911.
[35] J. R. Kuttler and V. G. Sigillito, "Eigenvalues of the Laplacian in two dimensions,"SIAM Rev., vol. 26, no. 2, pp. 163-193, April 1984.
[36] M. H. Protter, "Can one hear the shape of a drum? Revisited,"SIAM Rev., vol. 29, no. 2, pp. 185-197, 1987.
[37] I. M. Gel'fand and G. E. Shilov,Generalized Functions: Theory of Differential Equations, vol. 3. New York: Academic Press Inc., 1964.
[38] H. F. Weinberger, "An isoperimetric inquality for then-dimensional free membrane problem,"J. Rational Mech. Anal., vol. 5, pp. 533-636, 1956.
[39] L. E. Payne and H. F. Weinberger, "An optimal Poincare inequality for convex domains,"Arch. Rational Mech. Anal., vol. 5, pp. 286-292, 1960.
[40] J. H. Bramble and L. E. Payne, "Bounds in the Neumann problem for second order uniformly elliptic partial differential equations,"Pacific J. Math., vol. 12, pp. 823-833, 1962.
[41] D. W. Fox and W. C. Rheinboldt, "Computational methods for determining lower bounds for eigenvalues of operators in (Hilbert) space,"SIAM Rev., vol. 8, no. 4, pp. 427-462, Oct. 1966.
[42] V. G. Sigillito,Explicit a-priori inequalities with Applications to Boundary Value Problems. New York: Pitman, 1977.
[43] R. C. Nelson and J. Aloimonos, "Using flow field divergence for obstacle avoidance in visual navigation," inProc. DARPA Image Understanding Workshop, April 1988, pp. 548-567.
[44] G. E. Forsythe and W. R. Wasow,Finite-Difference Equations for Partial Differential Equations. New York: Wiley, 1960.
[45] F. B. Hildebrand,Finite-Difference Equations and Simulations. Englewood Cliffs, NJ: Prentice-Hall, 1968.
[46] A. R. Mitchell and D. F. Griffiths,The Finite Difference Method in Partial Differential Equations. New York: Wiley, 1980.
[47] A. Hurlbert and T. Poggio, "A network for image segmentation using color," in D. S. Touretzky, Ed.,Advances in Neural Information Processing Systems I. New York: Morgan Kaufmann, 1989.
[48] T. Meis and U. Marcowitz,Numerical Solution of Partial Differential Equations. New York: Springer-Verlag, 1978.
[49] Y. Barniv, "Velocity filtering applied to optical flow calculations," NASA Tech. Mem. 102802, Aug. 1990.
[50] D. L. Ringach and Y. Baram, "Obstacle detection by diffusion," Computer Science Dept., Technion, Israel Institute of Technology, CIS Report 9220, Nov. 1992.

Index Terms:
image sequences; motion estimation; diffusion; image texture; edge detection; finite difference methods; neural nets; computerised navigation; image segmentation; diffusion mechanism; obstacle detection; size-change information; immediacy measure; imminence of collision; moving observer; image domain; initial condition; locally connected cells; finite-difference approximation; motion measurement; segmentation; image sequences
Citation:
D.L. Ringach, Y. Baram, "A Diffusion Mechanism for Obstacle Detection from Size-Change Information," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 76-80, Jan. 1994, doi:10.1109/34.273715
Usage of this product signifies your acceptance of the Terms of Use.