This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Hierarchical Construction of Orientation and Velocity Selective Filters
March 1989 (vol. 11 no. 3)
pp. 315-325

As a step towards the early measurement of visual primitives, the authors outline design criteria for the extraction of orientation and velocity information, and present a variety of tools useful in the construction of simple linear filters. A hierarchical parallel-processing scheme is used in which nodes compute a weighted sum of inputs from within a small spatio-temporal neighborhood. The resulting scheme is easily analyzed and provides mechanisms sensitive to narrow ranges of both image velocity and orientation. The hierarchical approach in combination with separability in the first levels yields an efficient implementation.

[1] E. H. Adelson and J. R. Bergen, "Spatiotemporal energy models for the perception of motion,"J. Opt. Soc. Amer. A, vol. 2. pp. 284- 299, 1985.
[2] E. H. Adelson and J. R. Bergen, "The extraction of spatiotemporal energy in human and machine vision," inProc. IEEE Workshop Motion, Charleston, May 1986, pp. 151-156.
[3] S. T. Barnard and W. B. Thompson, "Disparity analysis of images,"IEEE Trans. Pattern Anal. Machine Intell., vol. 2, pp. 333-340. 1980.
[4] P. J. Burt, "Fast filter transforms for image processing,"Comput. Graphics Image Process., vol. 16, pp. 20-51, 1981.
[5] J. L. Crowley, "A representation for visual information," Ph.D. dissertation, Carnegie Mellon Univ., 1982; available as CMU Robotics Inst. Tech. Rep. CMU-RI-TR-82-7.
[6] J. D. Daugman, "Six formal properties of two-dimensional anisotropic visual filters: Structural principles and frequency/orientation selectivity,"IEEE Trans. Syst., Man, Cybern., vol. 13, pp. 882- 887, 1983.
[7] L. S. Dreachler and H. H. Nagel, "Volumetric model and 3D trajectory of a moving car derived from monocular TV frames of a street scene,"Comput. Graphics Image Process., vol. 20. pp. 199-228. 1982.
[8] D. J. Fleet, P. E. Hallett, and A. D. Jepson, "Spatiotemporal inseparability in early visual processing,"Biol. Cybern., vol. 52, pp. 153-164, 1985.
[9] D. J. Fleet and A. D. Jepson, "A cascaded filter approach to the construction of velocity selective mechanisms," Dep. Comput. Sci., Univ. Toronto, Tech. Rep. RBCV-TR-84-6, 1984.
[10] D. J. Fleet and A. D. Jepson, "Velocity extraction without form interpretation," inProc. IEEE Computer Vision Workshop: Representation and Control., Bellaire, Oct. 1985, pp. 179-185.
[11] D. J. Fleet and A. D. Jepson, "On the hierarchical construction of orientation and velocity selective filters." Univ. Toronto, Tech. Rep. RBCV-TR-85-8, 1985.
[12] G. H. Golub and C. F. van Loan,Matrix Computation. Baltimore, MD: Johns Hopkins University Press, 1983.
[13] D. J. Heeger, "Optical flow from spatiotemporal filters," inProc. IEEE Int. Conf. Computer Vision, London, June 1987, pp. 181-190.
[14] D. J. Heeger and A. P. Pentland. "Seeing structure through chaos," inProc. IEEE Workshop Motion: Representation and Analysis, Charleston, May 1986, pp. 131-136.
[15] B. K. P. Horn and B. G. Schunck, "Determining optic flow,"Artificial Intell., vol. 17. pp. 185-204. 1981.
[16] D. H. Hubel and T. N. Weisel, "Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex."J. Physiol., vol. 160, pp. 106-154, 1962.
[17] H. Knutsson and G. H. Grandlund, "Fourier domain design of line and edge detectors." inProc. 5th ICPR, Miami, 1980, pp. 45-47.
[18] D. Marr and E. C. Hildreth, "Theory of edge detection,"Proc. Roy. Soc. London., vol. B207, pp. 187-217, 1980.
[19] H. H. Nagel, "Displacement vectors derived from second-order intensity variations in image sequences,"Comput. Graphics, Image Process., vol. 21, pp. 85-117, 1983.
[20] A. Papoulis,Probability, Random Variables, and Stochastic Processes. New York: McGraw-Hill, 1965.
[21] L. R. Rabiner and B. Gold,Digital Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1975.
[22] J. Richter and S. Ullman, "A model for the temporal organization of X and Y type receptive fields in the primate retina,"Biol. Cybern., vol. 43, pp. 127-145, 1982.
[23] B. Schunck, "Image flow: Fundamentals and future research," inProc. CVPR, San Francisco, CA, June, 1985, pp. 561-571.
[24] D. Slepian, "Some comments on Fourier analysis, uncertainty and modeling,"Siam Rev., vol. 25, pp. 379-393, 1983.
[25] B. A. Watson, "Detection and recognition of simple spatial forms," inBiological and Machine Vision, O. Braddick and A. Sleigh, Eds. New York: Springer Verlag, 1983.
[26] B. A. Watson and A. J. Ahumada, "Model of human visual-motion sensing,"J. Opt. Soc. Amer. A, vol. 2, pp. 322-342, 1985.
[27] R. Young, "The Gaussian derivative model for biological vision,"Spatial Vision, to be published, 1987.
[28] S. W. Zucker, "Early orientation selection: Tangent fields and the dimensionality of their support,"Comput. Vision, Graphics, Image Process., vol. 32, pp. 74-103, 1985.

Index Terms:
image orientation; spatio-temporal linear filters; picture processing; motion analysis; visual primitives; design; hierarchical parallel-processing; image velocity; computerised picture processing; filtering and prediction theory; parallel processing
Citation:
D.J. Fleet, A.D. Jepson, "Hierarchical Construction of Orientation and Velocity Selective Filters," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 3, pp. 315-325, March 1989, doi:10.1109/34.21800
Usage of this product signifies your acceptance of the Terms of Use.