Abstract
Gradient-based algorithms for global motion estimation are effective in many image-processing tasks. However, when analytical estimation of derivatives of objective function is not possible, linear search based algorithms such as Powell perform better than the gradient-based ones. In this paper we propose global motion estimation algorithm that exploits linear search based algorithm, particularly Powell, instead of commonly used gradient-based one. We also introduce a new approach for extracting global motion parameters called Two Step Powell-based GME. Using this approach we further improve the Powell-based GME. The proposed Powell-based GME outperforms Gauss–Newton algorithm (gradient-based) in terms of PSNR. The proposed Two Step Powell GME algorithm outperforms Powell-based GME in terms of PSNR and computational time.
Similar content being viewed by others
References
Chi-Hsi S., Hsueh-Ming H., Lin D.W. (1999) Global motion parameter extraction and deformable block motion estimation. IEICE Trans. Inf. Syst. E82-D(8): 1210–1218
Tekalp A. (1995) Digital Video Processing. Prentice Hall, Englewood Cliffs
Smolic A., Sikora T., Ohm J-R. (1999) Long-term global motion estimation and its application for sprite coding, content description, and segmentation. IEEE Trans. Circuit System Video Technol. 9: 1227–1242
Grammalidis N., Beletsiotis D., Strintzis M. (2000) Sprite generation and coding in multiview image sequences. IEEE Trans. Circuits Syst. Video Technol. 10, 302–311
Szeliski R. Image Mosaicing for Tele-reality. Digital Equipment Corp., Cambridge Research Lab., TR94/2, Cambridge, MA (1994)
Dufaux F., Konrad J. (2000) Efficient, robust, and fast global motion estimation for video coding. IEEE Trans Image Process. 9(3): 497–501
Keller Y., Averbuch A. (2003) Fast gradient methods based on global motion estimation for video compression. IEEE Trans. Circuits Syst. Video Technol. 13(4): 300–309
Xiong Z., Chiang T., Zhang Y. Global motion compensation for low bitrate video coding. IEEE Trans. Consum. Electron. 45(1), (1999)
Averbuch A., Keller Y.: Fast motion estimation using bi-directional gradient methods. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2002, Orlando, USA, May 2002
Adby P.R., Dempster M.A.H. (1974) Introduction to Optimization Methods. Chapman and Hall, London
Argyriou V., Vlachos T.: Using gradient correlation for sub-pixel motion estimation of video sequences. IEEE Proc. ICASSP, vol. III, pp. 329–332, May 2004
Lucchese L.: Estimating Affine Transformations in the Frequency Domain. In: Proceedings of 2001 Int’l Conference on Image Processing (ICIP 2001), Thessaloniki, Greece, Sept. 2001, vol. II, pp. 909–912
Lucchese L. (2001) A frequency domain technique based on energy radial projections for robust estimation of global 2D affine transformations. Comput. Vis. Image Underst. 81, 72–116
Dane G., Nguyen T.: The effect of global motion parameter accuracies on the efficiency of video coding. IEEE International Conference on Image Processing, October, 2004
Burt P., Andelson E. (1993) Laplacian pyramid as a compact image code. IEEE Trans. Commun. 39(3): 141–150
Press W.H., Flannery B.P., Teukolsky S.A., Vetterling W.T. (1988) Numerical Recipes in C. Cambridge University Press, New York
Gill P.E., Murray W., Wright M.H.: Practical Optimization. Academic (1981)
Schwefel H.-P. (1995) Evolution and Optimum Seeking. Wiley, New York
Lourakis M.I.A., Argyros A.A.: Is Levenberg–Marquardt the Most Efficient Optimization Algorithm for Implementing Bundle Adjustment? 2005 IEEE International Conference on Computer Vision, ICCV’05, vol. 2, pp. 1526–1531, Beijing, China, Oct. 2005
Fletcher R. (2000) Practical Methods of Optimization. Wiley, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Greenberg, S., Kogan, D. Linear search applied to global motion estimation. Multimedia Systems 12, 493–504 (2007). https://doi.org/10.1007/s00530-006-0069-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-006-0069-2