Abstract
The blur in target images caused by camera bibration due to robot motion or hand shaking and by object(s) moving in the background scene is different to deal with in the computer vision system. In this paper, the authors study the relation model between motion and blur in the case of object motion existing in video image sequence, and work on a practical computation algorithm for both motion analysis and blur image restoration. Combining the general optical flow and stochastic process, the paper presents an approach by which the motion velocity can be calculated from blurred images. On the other hand, the blurred image can also be restored using the obtained motion information. For solving a problem with small motion limitation on the general optical flow computation, a multiresolution optical flow algorithm based on MAP estimation is proposed. For restoring the blurred image, an iteration algorithm and the obtained motion velocity are used. The experiment shows that the proposed approach for both motion velocity computation and blurred image restoration works well.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques.International Journal of Computer Vision, 1994, 12(1): 43–77.
Horn B K P, Robot Vision. MIT Press, Cambridge, MA, 1986.
Verri A, Poggio T. Motion field and flow: Qualitative properties AI Memo 917, MIT AI Lab., 1986.
Verri A, Poggio T. Against qualitative optical flow. InProc. 1st ICCV, London, 1987, pp.171–180.
Poggio T. Ill-posed problems and regularization analysis in early vision. AI Memo 773, MIT AI Lab., 1984.
Bertero M, Poggio T. Ill-posed problems in early vision. AI Memo 924, MIT AI Lab., 1987.
Jain R, Nagel H H. On the analysis of accumulation difference pictures from image sequences of real world scenes.IEEE Trans. PAMI, 1979, 1: 206–214.
Barman H, Haglund Let al. Estimation of velocity, acceleration and disparity in time sequences. InProc. IEEE Workshop on Visual Motion, Nassau Inn Princeton, New Jersey, Oct. 7–9, 1991, pp.44–51.
Barnard S T, Thompson W B. Disparity analysis of image.IEEE Trans. PAMI, 1980, 2: 333–340.
Horn B K P, Schunck B G. Determination of optical flow.AI, 1981, 17: 185–203
Kornrad J, Dubois E. Estimation of image motion fields. InProc. IGASSP’88, pp.1072–1074.
Koch C, Wang H Tet al. An adaptive multi-scale approach for estimating optical flow: Computational theory and physiological implementation. InProc. IEEE Workshop on Visual Motion, Nassau Inn Princeton, New Jersey, Oct. 7–9, 1991. pp.111–122.
Andrews H C, Hunt B R. Digital Image Restoration. Prentice-Hall, 1977.
Prost R, Goutte R. Deconvolution when the convolution kernel has no inverse.IEEE Trans. ASSP, 1977, 25(6): 542–549.
Schafer R W, Mersereau R M, Richards M A. Constrained iteration restoration algorithm. InProc. the IEEE 1981, 69(4): 432–450.
Geman S, Geman D. Stochastic relaxation, Gibbs distribution and Bayesian restoration of images.IEEE Trans. PAMI, 1984, 13: 721–741.
Gao Wen, Chen Xilin. Edge detection with stochastic approach. InProc. ACCV’93, Osaka, 1993.
Hopfield J J, Tank D W. Neural computation of decisions optimization problems.Biol. Cybern, 1985, 52: 141–152.
van Cittert P H. Zum einfluss der splatbreite auf die intensitatswerteilung in spektrallinien II.Z. für Physik, 1931, 69: 298–308.
Schnrr C. Determining optical flow for irregular domains by minimizing quadratic functions of a certain class.International Journal of Computer Vision, 1991, 6(1): 25–38.
Author information
Authors and Affiliations
Additional information
This work was supported in part by the Huo Ying-Dong Foundation, National Hi-Tech Program under contract 863-306-03-01, Outstanding Young Professor Foundation of State Education Commission, Outstanding Century-Crossing Scientist Foundation of State Education Commission.
Gao Wen received his first Ph.D. degree in computer science from Harbin Institute of Technology in 1988, and his second Ph.D. degree in electronics engineering from the University of Tokyo in 1991. In 1985, he joined the faculty of Department of Computer Science, Harbin Institute of Technology. He has been a Professor of computer science in Harbin Institute of Technology since 1991. Dr. Gao was a visiting scholar in the Institute of Medical Electronic Engineering, University of Tokyo from April 1991 to March 1992, a Visiting Professor in the Robotics Institute, Carnegie Mellon University from July 1993 to November 1993, a Visiting Professor in the MIT Artificial Intelligence Laboratory from May 1994 to July 1994, and from January 1995 to September 1995, he is an Honorary Professor in the City University of Hong Kong. His research centers on artificial intelligence, image understanding, pattern recognition, data compression, and multimodal interface.
Chen Xilin received his Ph.D. degree in computer science from Harbin Institute of Technology in 1994. He joined the faculty of Department of Computer Science, Harbin Institute of Technology in 1994. He has been an Associate Professor of computer science in Harbin Institute of Technology since July 1996. His research centers on artificial intelligence, computer vision, data compression and multimodal interface.
Rights and permissions
About this article
Cite this article
Gao, W., Chen, X. A stochastic approach for blurred image restoration and optical flow computation on field image sequence. J. of Comput. Sci. & Technol. 12, 385–399 (1997). https://doi.org/10.1007/BF02943171
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02943171