Nonuniform Image Motion Estimation from Noisy and Blurred Image Sequences

Abstract

This paper develops, presents, and evaluates a new iterative algorithm to estimate image motion from noisy-blurred image sequences. This algorithm seeks the maximum-likelihood estimate of image motion coefficients in an arbitrary transformed domain directly from noisy-blurred data. The range of the convergence parameters that control the speed of convergence is also presented. Simulation experiments demonstrate the validity of the motion estimator. Additional experiments investigate the algorithm's sensitivity to the extent of blur and noise. We also show the potential application of the estimated motion to image sequence restoration.

Key Words:

• Image motion estimation
• maximum-likelihood estimation
• steepest ascent algorithm
• image sequence restoration

Additional information

Notes on contributors

C.M. Fan

Chieh-Min Fan received his B.S. degree in geophysics from the National Central University, Chung-Li, Taiwan, R.O.C., in 1984, the M.S. degree in geophysics and the M.S. degree in electrical engineering, both from Michigan Technological University, Houghton, in 1989 and 1992, respectively, and the Ph.D. degree in electrical engineering from The Catholic University of America, Washington, DC, in 1998. He is currently with the U.S. Patent and Trademark Office, Arlington, VA. His research interests are in image motion estimation, image sequence filtering⁄restoration, digital communications, and seismic data processing.

N.M. Namazi

Nader M. Namazi received his bachelor's degree in electrical engineering from the Iran College of Science and Technology, Tehran, Iran, in 1977, and the M.S. and Ph.D. degrees in electrical engineering from the University of Missouri-Rolla in 1981 and 1985, respectively. Prom 1985 to 1992, he was with the Michigan Technological University, Houghton, where he was promoted to the rank of Associate Professor. Since 1992, he has been with the Catholic University of America, Washington, D.C., where he is currently an Associate Professor and Chairman of Electrical Engineering and Computer Science. He was the Editor-in-Chief of the International Journal of Modeling and Simulation from 1994 to 1996. He is the author of New Algorithms for variable Time Delay and Nonuniform Image Motion Estimation (Ablex, 1994). His research interests are in image motion detection and estimation, image sequence filtering⁄restoration, and digital communications. Dr. Namazi is a member of Eta Kappa Nu.