Engineering Transactions, 39, 2, pp. 139-161, 1991

Changes Detection in Two Images Using Walsh Functions and the Likelihood Test Method

M. Nieniewski
Electrotechnical Institute, Institute of Fundamental Technological Research, Warszawa
Poland

P.K. Pathak
Department of Mathematics and Statistics, University of New Mexico, Albuquerque
United States

The gray-value function in a local window is approximated by a series of the Walsh functions. Several terms of this series adequately model the gray-value function in the window, and the remaining variability can be attributed to noise. When comparing two images, one finds the coefficients of the Walsh functions for each consecutive position of the window in both images. Detection of the change between the corresponding windows is based on the maximum likelihood ratio testing, which consists in deciding between two hypotheses: Ho - there is no motion, versus H1 - there is motion. The results of change detection are presented for images of a natural scene, obtained by means of the CCD camera, as well as for simulated images subjected to the influence of Gaussian noise. The computer program described carries out the F-test for the maximum likelihood ratio. It is shown that such a program can be successfully used for change detection in image sequences.

Full Text: PDF
Copyright © Polish Academy of Sciences & Institute of Fundamental Technological Research (IPPT PAN).

References

D.H. BALLARD and C.M. BROWN, Computer vision, Prentice-Hall, Englewood Cliffs, NJ, 1982.

P. BOUTHEMY, A maximum likelihood framework for determining moving edges, IEEE Trans. Pattern Anal. Machine lntell., PAMI-11, 499-511, 1989.

C. CAFFORJO and F. ROCCA, Methods for measuring small displacements of television images, IEEE Trans. Inf. Theory, IT-22, 573-79, 1976.

G. DAHLQUIST and A. BJÖRCK, Numerical methods, Prentice-Ha.ll, Englewood Cliffs, NJ, 1974.

R.C. GONZALEZ and P. WINTZ, Digital image processing, Addison-Wesley, Reading, MA, 1977.

B.K.P. HORN, Robot vision, The MIT Press, Cambridge, MA, 1986.

B.K.P. HORN and B.G. SCHUNK, Determining optical flow, Artificial lntell., 17, 185-203, 1981.

Y.Z. HSU, H.H. NAGEL, G. REKERS, New likelihood test methods for change detection in image sequences, Comput. Vision Graphics Image Processing, 26, 73-106, 1984.

R. JAIN, Segmentation of moving observer frame sequences, Pattern Recogn. Letters, 1, 115-20, 1982.

D.T. LAWTON, Processing translational motion sequences, Comput. Vision Graphics Image Processing, 22, 116-44, 1983.

J.O. LIMB and J.A. MURPHY, Estimating the velocity of moving images in television signals, Comput. Graphics Image Processing, 4, 311-27, 1975.

S.A. MAHMOUD, M.S. AFIFI, R.J. GREEN, Recognition and velocity computation of large moving objects in images, IEEE Trans. Acoust. Speech Signal Proc., ASSP-36, 1790-91, 1988.

W. MICHAELIS, Möglichkeiten der Verschiebungsbestimmung bei der digitalen Auswertung von Bildfolgen, Wiss. Zeitschrift, TH Ilmenau, 34, H. 2, 95-106, 1988.

H.H. NAGEL, On change detection and displacement vector estimation in image sequences, Pattern Recogn. Letters, 1, 55-59, 1982.

M. NIENIEWSKI and P.K. PATHAK, Change detection in image sequences using Walsh functions and the likelihood test method, Proceedings of Internat. Conference on Signal Processing, 995-98, Beijing, October 22-26, 1990.

T.J. PATTERSON, D.M. CHABRIES, R.W. CHRISTIANSEN, Detection algorithms for image sequence analysis, IEEE Trans. Acoust. Speech Signal Proc., ASSP-37, 1454-58, 1989.

W.K. PRATT, Digital image processing, John Wiley, New York, NY, 1978.

S.A. RAJALA, A.N. RIDDLE, W.E. SNYDER, Application of the one-dimensional Fourier transform for tracking moving objects in noisy environments, Comput. Vision Graphics Image Processing, 21, 280-93, 1983.

A. ROSENFELD and A.C. KAK, Digital picture processing, Academic Press, Orlando, FL, 1982.

M.A. SHAH and R. JAIN, Detecting time-varying corners, Comput. Vision Graphics Image Processing, 28, 345-55, 1984.

M.R. SPIEGEL, Probability and statistics, McGraw-Hill, New York, NY, 1975.

M.S. ULSTAD, An algorithm for estimating small scale differences between two digital images, Pattern Recogn., 5, 323-33, 1973.

B. WICHMANN and D. HILL, Building a random-number generator, Byte, 12, 127-128, March 1987.

Y. YAKIMOVSKY, Boundary and object detection in real world images, J.Assoc. Comput. Machinery, 23, 599-618, 1976.

S. YALAMANCHILI, W.N. MARTIN, J.K. AGGARWAL, Extraction of moving object descriptions via differencing, Comput. Vision Graphics Image Processing, 18, 188-201, 1982.