Abstract
This chapter describes work toward understanding the fundamentals of image flow and presents algorithms for estimating the image flow field. Image flow is the velocity field in the image plane that arises due to the projection of moving patterns in the scene onto the image plane. The motion of patterns in the image plane may be due to the motion of the observer, the motion of objects in the scene, or both. The motion may also be apparent motion where a change in the image between frames gives the illusion of motion. The image flow field can be used to solve important vision problems provided that it can be accurately and reliably computed. Potential applications are discussed in Section 2.1.2.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ames, W.F., (1977) Numerical Methods for Partial Differential Equations, 2nd ed., New York: Academic Press.
Barlow, H.B., Hill, R.M., and Levick, W.R., (1964) ‘Retinal ganglion cells responding selectively to direction and speed of image motion in the rabbit,’ J. of Physiology, vol. 173, pp. 377–407.
Barlow, H.B. and Levick, W.R., (1965) ‘The mechanism of directionally selective units in rabbit’s retina,’ J. of Physiology, vol. 178, pp. 477–504.
Barrow, H.G. and Tenenbaum, J.M., (1978) ‘Recovering intrinsic scene characteristics from images,’ in Computer Vision Systems, A.R. Hanson and E.M. Riseman (eds.), Academic Press, New York.
Batali, J. and Ullman, S., (1979) ‘Motion detection and analysis,’ in Image Understanding, L.S. Baumann (ed.), Science Applications, Arlington, Virginia, pp. 69–75
Bers, K.H., Bohner, M., and Gerlach, H., (1980) ‘Object detection in image sequences,’ Proc. Int. Joint Conf. Pattern Recognition, pp. 1317–1319.
Blake, A., (1984) ‘Reconstructing a visible surface,’ Proc. Nat. Conf Artificial Intelligence, pp. 23–26.
Braddick, O., (1974) ‘A short-range process in apparent motion,’ Vision Research, vol. 14, pp. 519–527.
Brady, M., and Horn, B.K.P., (1981) ‘Rotationally symmetric operators for surface interpolation,’ Memo 654, Artificial Intelligence Laboratory, M.I.T.
Buckner, E., (1976) ‘Elementary movement detectors in an insect visual system,’ Biological Cybernetics, vol. 24, pp. 85–101.
Buxton, B.F., Buxton, H., Murray, D.W., and Williams, N.S., (1983) ‘3D solutions to the aperture problem,’ Tech. Rep., GEC Research Laboratories.
Cafforio, C., and Rocca, F., (1976) ‘Methods for measuring small displacements of television images,’ IEEE Trans. on Information Theory, vol. IT-22, pp. 573–579.
Canny, J.F., (1983) ‘Finding edges and lines in images,’ Tech. Rep. 720, Artificial Intelligence Laboratory, M.I.T.
Clocksin, W.F., (1978) ‘Determining the orientation of surfaces from optical flow,’ Proc. 3rd AISB Conf, pp. 93–102.
Clocksin, W.F., (1980) ‘Perception of surface slant and edge labels from optical flow: A computational approach.’ Perception, vol. 9, pp. 253–269.
Courant, R. and Hilbert, D., (1937) Methods of Mathematical Physics, vol. 1, Wiley-Interscience, New York.
Davis, L.S., Wu, Z., and Sun, H., (1981) ‘Contour-based motion estimation,’ Tech. Rep., Computer Vision Laboratory, University of Maryland.
Fennema, C.L., and Thompson, W.B., (1979) ‘Velocity determination in scenes containing several moving objects,’ Computer Graphics and Image Proccessinf, vol. 9, pp. 301–315.
Flinchbaugh, B.E., and Chandrasekaran, B., (1981) ‘A theory of spatiotemporal aggregation for vision,’ Artificial Intelligence, vol. 17, pp. 387–407. reprinted in Computer Vision, M. Brady (ed.), North-Holland, Amsterdam.
Geman, S., and Geman, D., (1984) ‘Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,’ IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-6, pp. 721–741.
Grimson, W.E.L., (1981a) From Images to Surfaces: A Computational Study of the Human Early Vision System, M. I. T. Press, Cambridge.
Grimson, W.E.L., (198lb) ‘A computational theory of visual surface interpolation,’ Memo 613, Artificial Intelligence Laboratory, M.I.T.
Grimson, W.E.L., (1981c) ‘The implicit constraints of the primal sketch,’ Memo 663, Artificial Intelligence Laboratory, M.I.T.
Grimson, W.E.L., (1983) ‘Surface consistency constraints in vision,’ Computer Vision, Graphics and Image Processing, vol. 24, pp. 28–51.
Haskell, (1974) ‘Frame-to-frame coding of television pictures using two-dimensional Fourier transforms,’ IEEE Trans. on Information Theory, vol. IT-20, pp. 119–120.
Hildreth, E.C., (1984) ‘The computation of the velocity field,’ Proc. Royal Society London, B, vol. 221, pp. 189–220.
Hildreth, E.C., and Ullman, S., (1982) ‘The measurement of visual motion,’ Memo 699, Artificial Intelligence Laboratory, M.I.T.
Hirzinger, G., Landzettel, K., and Snyder, W., (1980) ‘Automated TV tracking of moving objects: The DFVLR tracker and related approaches,’ Proc. Int. Joint Conf Pattern Recognition, pp. 1255–1261.
Hoffman, D.D., (1980) ‘Inferring shape from motion fields,’ Memo 592, Artificial Intelligence Laboratory, M.I.T.
Horn, B.K.P., and Bruss, A.R., (1983) ‘Passive navigation,’ Computer Vision, Graphics and Image Processing, vol. 21, pp. 3–20.
Horn, B.K.P., and Schunck, B.G., (1981) ‘Determining optical flow,’ Artificial Intelligence, vol. 17, reprinted in Computer Vision, M. Brady (ed.), North-Holland, Amsterdam, pp. 185–203.
Jain, R., Martin, W.N., and Aggarwal, J.K., (1979) ‘Segmentation through the detection of changes due to motion,’ Computer Graphics and Image Processing, vol. 11, pp. 13–34.
Jain, R., Militzer, D., and Nagel, H.-H., (1977) ‘Separating non-stationary from stationary scene components in a sequence of real world TV-images,’ Proc, Int. Joint Conf. Artificial Intelligence, pp. 612–618.
Jain, R., and Nagel, H.-H., (1979) ‘On the analysis of accumulative difference pictures from image sequences of real world scenes,’ IEEE Trans. on Pattern Analalysis and Machine Intelligence, vol. PAMI-1, pp. 206–214.
Jain, R., (1983) ‘Difference and accumulative difference pictures in dynamic scene analysis,’ Rep. GMR-4548, General Motors Research Laboratories.
Jones, R.A., and Rashid, H., (1981) ‘Residual recursive displacement estimation,’ Proc Conf. Pattern Recognition and Image Processing, pp. 508–509.
Koenderink, J.J., and van Doom, A.J., (1975) ‘Invariant properties of the motion parallax field due to the movement of rigid bodies relative to an observer,’ Optica Acta, vol. 22, pp. 773–791.
Koenderink, J.J., and van Doom, A.J., (1976) ‘Local structure of movement parallax of the plane,’ J. Optical Society America, vol. 66, pp. 717–723.
Limb, J.O., and Murphy, J.A., (1975a) ‘Measuring the speed of moving objects from television signals,’ IEEE Trans. on Communication, vol. COM-23, pp. 474–478.
Limb, J.O., and Murphy, J.A., (1975b) ‘Estimating the velocity of moving images in television signals,’ Computer Graphics and Image Processing, vol. 4, pp. 311–327.
Longuet-Higgins, H.C., and Prazdny, K., (1980) The interpretation of moving retinal image,’ Proc. Royal Society London, vol. B 208, pp. 385–397.
Marr, D., and Hildreth, E., (1980) ‘Theory of edge detection,’ Proc. Royal Society London, vol. B 207, pp. 187–217.
Marr, D., and Ullman, S., (1981) ‘Directional selectivity and its use in early visual processing,’ Proc. Royal Society London, vol. B 211, pp. 151–180.
Mutch, K.M., and Thompson, W.B., (1984) ‘Analysis of accretion and deletion at boundaries in dynamic scenes,’ Tech. Rep. 84–7, Department of Computer Science, University of Minnesota, Minneapolis.
Nagel, H.-H., (1980) ‘From digital picture processing to image analysis,’ Proc. Int. Conf. Image Analysis and Processing.
Nakayama, K., and Loomis, J., (1974) ‘Optical velocity patterns, velocity-sensitive neurons, and space perception: A hypothesis,’ Perception, vol. 3, pp. 63–80.
Netravali, A.N., and Robbins, J.D., (1979) Motion-compensated television coding: Part I,’ Bell System Tech. J., vol. 58, pp. 631–670.
Nevatia, R., (1982) Machine Perception, Prentice-Hall, Englewood Cliffs, NJ.
Poggio, T., and Reichardt, W., (1976) ‘Visual control of orientation behavior in the fly,’ Quart. Rev. of Biophysics, vol. 9, pp. 377–438.
Poggio, T., (1985) ‘Early vision: From computational structure to algorithms and parallel hardware,’ Computer Vision, Graphics and Image Processing, vol. 31, pp. 139–155.
Prazdny, K., (1980) ‘Egomotion and relative depth map from optical flow,’ Biological Cybernetics, vol. 36, pp. 87–102.
Price, C., Snyder, W., and Rajala, S., (1981) ‘Computer tracking of moving objects using a Fourier-domain filter based on a model of the human visual system,’ Proc, Conf Pattern Recognition and Image Processing, pp. 98–102.
Reichardt, W., and Poggio, T., (1979) ‘Figure-ground discrimination by relative movement in the visual system of the fly,’ Biological Cybernetics, vol. 35, pp. 81–100.
Richter, J., and Ullman, S., (1980) ‘A model for the spatio-temporal organization of X and Y-type ganglion cells in the primate retina,’ Memo 573, Artificial Intelligence Laboratory, M.I.T.
Roach, J.W. and Aggarwal, J.K., (1979) ‘Computer tracking of objects moving in space.’ IEEE Trans. on Pattern Analalysis and Machine Intelligence, vol. PAMI-1, pp. 127–135.
Schalkoff, R.J., and McVey, E.S., (1982) ‘A model and tracking algorithm for a class of video targets,’ IEEE Trans. on Pattern Analalysis and Machine Intelligence, vol. PAMI-4, pp. 2–10.
Schetzen, M., (1980) The Voltera and Wiener Theories of Nonlinear Systems, John Wiley & Sons, New York.
Schunck, B.G., (1983) ‘Motion segmentation and estimation,’ Department of Electrical Engineering and Computer Science, M. I. T., PhD. Dissertation.
Schunck, B.G., (1984a) ‘The motion constraint equation for optical flow,’ Proc. Int. Joint Conf. on Pattern Recognition, Montreal, pp. 20–22.
Schunck, B.G., (1984b) ‘Motion segmentation and estimation by constraint line clustering,’ Proc. 2nd IEEE Workshop on Computer Vision, Annapolis, Maryland, pp. 58–62.
Schunck, B.G., (1984c) ‘Surface-based smoothing of optical flow fields,’ Proc. Conf. on Intelligent Systems and Machines, Oakland University, Rochester, Michigan, pp. 107–111.
Schunck, B.G., and Horn, B.K.P., (1981) ‘Constraints on optical flow computation,’ Proc. Conf. Pattern Recognition and Image Processing, pp. 205–210.
Snyder, W.E., Rajala, S.A., and Hirzinger, G., (1980) ‘Image modelling: The continuity assumption and tracking,’ Proc. Int. Joint Conf. Pattern Recognition, pp. 1111–1114.
Stuller, J.A., and Netravali, A.N., (1979) ‘Transform domain motion estimation,’ Bell System Tech. J., vol. 58, pp. 1673–1702.
Stuller, J.A., Netravali, A.N., and Robbins, J.D., (1980) ‘Interframe television coding using gain and displacement compensation,’ Bell System Tech. J., vol. 59, pp. 1227–1240.
Terzopoulos, D., (1982) ‘Multilevel reconstruction of visual surfaces: Variational principles and finite element representations,’ Memo 671, Artificial Intelligence Laboratory, M.I.T.
Terzopoulos, D., (1983) ‘Multilevel computational processes for visual surface reconstruction,’ Computer Vision, Graphics and Image Processing, vol. 24, pp. 52–96.
Thompson, W.B., Mutch, K.M., and Berzins, V.A., (1984) ‘Dynamic occlusion analysis in optical flow fields,’ Tech. Rep. 84–6, Department of Computer Science, University of Minnesota.
Tsai, R.Y., and Huang, T.S., (1982) ‘Uniqueness and estimation of three-dimensional motion parameters of rigid objects with curved surfaces,’ Proc. Conf. Pattern Recognition and Image Processing, pp. 112–118.
Tsai, R.Y., Huang, T.S., and Zhu, W.-L., (1982) ‘Estimating three-dimensional motion parameters of a rigid planar patch, II: Singular value decomposition,’ IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. ASSP-30, pp. 525–534.
Ullman, S., (1979a) ‘The interpretation of structure from motion,’ Proc. Royal Society London, vol. B 203, pp. 405–426.
Ullman, S., (1979b) The Interpretation of Visual Motion, M. I. T. Press, Cambridge.
Ullman, S., (1979c) ‘Relaxation and constrained optimization by local processes,’ Computer Graphics and Image Processing, vol. 10, pp. 115–125.
Waxman, A., and Ullman, S., (1983) ‘Surface structure and 3-d motion from image flow: A kinematic analysis,’ Tech. Rep., Center for Automation Research, University of Maryland.
Waxman, A.M. and Sinha, S.S., (1984) ‘Dynamic stereo: Passive ranging to moving objects from relative image flows,’ Tech. Rep., Computer Vision Laboratory, University of Maryland.
Waxman, A.M., (1984) ‘An image flow paradigm,’ Tech. Rep., Computer Computer Vision Laboratory, University of Maryland.
Waxman, A.M., and Wohn, K., (1984) ‘Contour evolution, neighborhood deformation and global image flow: Planar surfaces in motion,’ Computer Vision Laboratory, University of Maryland.
Yalamanchili, S., Martin, W.N., and Aggarwal, J.K., (1982) ‘Extraction of moving object descriptions via differencing,’ Computer Vision, Graphics and Image Processing, vol. 18, pp. 188–201.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Kluwer Academic Publishers
About this chapter
Cite this chapter
Schunck, B.G. (1988). Image Flow: Fundamentals and Algorithms. In: Martin, W.N., Aggarwal, J.K. (eds) Motion Understanding. The Kluwer International Series in Engineering and Computer Science, vol 44. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1071-6_2
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1071-6_2
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8413-0
Online ISBN: 978-1-4613-1071-6
eBook Packages: Springer Book Archive