
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
R.S. Jasinschi, "Intrinsic Constraints in SpaceTime Filtering: A New Approach to Representing Uncertainty in LowLevel Vision," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 3, pp. 353366, March, 1992.  
BibTex  x  
@article{ 10.1109/34.120330, author = {R.S. Jasinschi}, title = {Intrinsic Constraints in SpaceTime Filtering: A New Approach to Representing Uncertainty in LowLevel Vision}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {14}, number = {3}, issn = {01628828}, year = {1992}, pages = {353366}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.120330}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Pattern Analysis and Machine Intelligence TI  Intrinsic Constraints in SpaceTime Filtering: A New Approach to Representing Uncertainty in LowLevel Vision IS  3 SN  01628828 SP353 EP366 EPD  353366 A1  R.S. Jasinschi, PY  1992 KW  spatial sampling rates; CramerRao inequality; parameter estimation; intrinsic constraints; picture processing; spacetime filtering; lowlevel vision; optical flow; motion uncertainty; temporal sampling rates; parameter estimation; pattern recognition; picture processing; spatial filters VL  14 JA  IEEE Transactions on Pattern Analysis and Machine Intelligence ER   
Describes how, in the process of extracting the optical flow through spacetime filtering, one has to consider the constraints associated with the motion uncertainty, as well as the spatial and temporal sampling rates of the sequence of images. The motion uncertainty satisfies the CramerRao (CR) inequality, which is shown to be a function of the filter parameters. On the other hand, the spatial and temporal sampling rates have lower bounds, which depend on the motion uncertainty, the maximum support in the frequency domain, and the optical flow. These lower bounds on the sampling rates and on the motion uncertainty are constraints that constitute an intrinsic part of the computational structure of spacetime filtering. The author shows that if he uses these constraints simultaneously, the filter parameters cannot be arbitrarily determined but instead have to satisfy consistency constraints. By using explicit representations of uncertainties in extracting visual attributes, one can constrain the range of values assumed by the filter parameters.
[1] E. H. Adelson and J. R. Bergen, "Spatiotemporal energy models for the perception of motion,"J. Opt. Soc. Am. A, vol. 2, pp. 284299, 1985.
[2] A. J. Ahumada and A. B. Watson, "A look at motion in the frequency domain,"NASA Tech. Mem. 84352, 1983.
[3] A. J. Ahumada and A. B. Watson, "Model of human visualmotion sensing,"J. Opt. Soc. Am. A, vol. 2, pp. 322342, 1985.
[4] S. M. Anstis, "The perception of apparent motion."Phil. Trans. R. Soc. Lond. B, vol. 290, pp. 153168, 1981.
[5] S. Amari,DifferentialGeometrical Methods in Statistics. New York: SpringerVerlag, 1985.
[6] A. N. Arsenyn and V. Y. Tikhonov,Solution to IllPosed Problems. New York: Winston, 1977.
[7] R. Bracewell,The Fourier Transform and Its Applications. New York: McGrawHill, 1965.
[8] O. J. Braddick, "A shortrange process in apparent motion,"Vision Res., vol. 14, pp. 519527, 1974.
[9] O. J. Braddick, "Lowlevel and highlevel processes in apparent motion,"Phil. Trans. R. Soc. Lond. B, pp. 137151, 1981.
[10] J. J. Chang and B. Julesz, "Displacement limits for spatial frequency filtered randomdot cinematograms in apparent motion,"Vision Res., vol. 23, pp. 13791385, 1983.
[11] F. H. C. Crick, D. C. Marr, and T. Poggio, "An information processing approach to understanding the visual cortex," Artificial Intell. Lab., MIT, Cambridge, MA, Memo 557, 1980.
[12] L. S. Davis, Z. Wu, and H. Sun, "Contour based motion estimation,"Comput. Graph. Image Processing, vol. 23, pp. 313326, 1983.
[13] J. G. Daugman, "Six formal properties of twodimensional anisotropic visual filters: Structural principles and frequency orientation selectivity,"IEEE Trans. Syst. Man Cybern., vol. SMC13, pp. 882887, 1983.
[14] Z. Duric´and Y. Aloimonos, "Passive navigation: An active and purposive solution," Univ. of Maryland Tech. Rep. CARTR560, 1991.
[15] D. J. Fleet and A. D. Jepson, "On the hierarchical construction of orientation and velocity selective filters," Univ. of Toronto, Tech. Rep. RBCVTR858, 1985.
[16] R. M. Haralick, "Statistical and structural approaches to texture,"Proc. IEEE, vol. 67, pp. 786804, 1979.
[17] E. Hildreth,The Measurement of Visual Motion, Cambridge, MA: MIT Press, 1983.
[18] D. J. Heeger, "A model for the extraction of image flow,"J. Opt. Soc. Am. A, vol. 4, pp. 14551471, 1988.
[19] R. A. Holub and M. MortonGibson, "Response of visual cortical neurons of the cat to moving sinusoidal gratings: Responsecontrast functions and spatiotemporal interactions,"J. Neurophysiol., vol. 46, pp. 12441259, 1981.
[20] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185203, 1981.
[21] R. S. Jasinschi, "Spacetime filtering, sampling and motion uncertainty," Carnegie Mellon Univ. Tech. Rep. CMURITR889, 1988.
[22] R. S. Jasinschi, "Spacetime sampling with motion uncertainty: Constraints on spacetime filtering," inProc. 2nd Int. Conf. Comput. Vision, IEEE Comput. Soc.(Washington, DC), 1988, pp. 428434.
[23] R. S. Jasinschi, "Toward a theory of apparent visual motion," inProc. Workshop Visual Motion, IEEE Computer Society(Washington, DC), 1989, pp. 139147.
[24] R. S. Jasinschi, "Energy filters, motion uncertainty, and motion sensitive cells in the visual cortex: A mathematical analysis,"Biol. Cybern., vol. 65, pp. 515523, 1991.
[25] R. S. Jasinschi, "The properties of spacetime sampling and the extraction of the optical flow: The effects of motion uncertainty,"J. Visual Commun. Image Representation, vol. 2, pp. 222229, 1991.
[26] R. S. Jasinschi, A. Rosenfeld, and K. Sumi, "Perceptual motion transparency: The role of geometrical information," submitted for publication, 1991.
[27] B. Julesz, "Textons, the elements of texture perception, and their interactions,"Nature, vol. 290, pp. 9197, 1981.
[28] A. Korte, "Kinematoskopische Untersuchungen,"Z. Psychol., vol. 72, pp. 193296, 1915.
[29] J. J. Kulikowskiet al., "Theory of spatial position and spatial frequency relations in the receptive fields of simple cells in the visual cortex,"Biol. Cybern., vol. 43, pp. 187198, 1982.
[30] J. Malik and P. Perona, "Preattentive texture discrimination with early vision mechanisms,"J. Opt. Soc. Am. A, vol. 7, pp. 923932, 1990.
[31] D. Marr,Vision. Cambridge, MA: MIT Press, 1981.
[32] K. Nakayama and G. H. Silverman, "Temporal and spatial characteristics of the upper displacement limit for motion in random dots,"Vision Res., vol. 24, pp. 293299, 1984.
[33] K. Nakayama, "Biological image motion processing: A review,"Vision Res., vol. 25, pp. 625660, 1985.
[34] W. Neuhaus, "Experimentelle Untersuchungen der Scheinbewegung,"Arch. Ges. Psychol., vol. 75, pp. 315418, 1930.
[35] M. Fahle and T. Poggio, "Visual hyperacuity: Spatiotemporal interpolation in human vision,"Proc. R. Soc. London. B, vol. 213, pp. 415477, 1981.
[36] T. Poggio, V. Torre, and C. Koch, "Computational vision and regularization theory,"Nature, vol. 317, pp. 314319, 1985.
[37] A. Verri and T. Poggio, "Against quantitative optical flow," inProc. First Int. Conf. Comput. Vision, IEEE Comput. Soc.(Washington, DC), 1987, pp. 171180.
[38] T. Poggio and F. Girosi, "A theory for approximation and learning," AI Memo 1140, MIT, July 1989.
[39] A. Rosenfeld, Ed.,Multiresolution Image Processing and Analysis. New York: SpringerVerlag, 1984.
[40] C. E. Shannon, "Communication in the presence of noise,"Proc. IRE, vol. 37, pp. 1021, 1949.
[41] W. M. Siebert,Circuits, Signals, and Systems. Cambridge, MA: MIT Press, 1986.
[42] A. Rosenfeld and M. Thurston, "Edge and curve detection for visual scene analysis,"IEEE Trans. Comput.vol. C20, pp. 562569, 1971.
[43] S. Ullman,The Interpretation of Visual Motion. Cambridge, MA: MIT Press, 1979.
[44] H. L. Van Trees,Detection, Estimation, and Modulation Theory, Vol. I. New York: Wiley, 1968.
[45] H. Voorhees and T. Poggio, "Computing texture boundaries from images,"Nature, vol. 333, pp. 364367, 1988.
[46] G. Wahba, "A cross validation Bayesian retrieval algorithm for nonlinear remote sensing experiments,"J. Comput. Physics, vol. 59, pp. 441455, 1985.
[47] G. Young and R. Chellappa, "Statistical analysis of inherent ambiguities in recovering 3D motion from a noisy flow field," Univ. of Maryland Tech. Rep. CARTR558, 1991.
[48] N. M. Grzywacz and A. L. Yuille, "A model for the estimate of local image velocity by cells in the visual cortex,"Proc. R. Soc. B, vol. 239, pp. 129161, 1990.