Abstract
In computer vision, the interpretation of optical flow (motion vector field calculated from images) and estimation of motion are important tasks. This study proposes a motion interpretation network which enables optical flow (OF) interpretation and describes motions on a plane through the use of a neural network with complex back propagation learning. Furthermore, an OF normalization network for optical flow normalization is proposed for the interpretation of diverse flow patterns, such as real image optical flow. Two types of output function of a neuron unit are examined. Using test patterns and real image optical flow, the generalization capacity of proposed network is investigated. And the ability is confirmed experimentally.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
B.K.P. Horn and B.G. Schunck: “Determining Optical Flow”, Artificial Intelligence, 17, pp. 185–203 (1981)
J.K. Aggarwal and N. Nandhakumar: “On the computation of motion from sequences of images — A review”, Proceedings of IEEE, 76, 8, pp. 917–935 (1988)
R.Y. Tsai and T.S. Huang: “Uniqueness and Estimation of Theree-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces”, IEEE Trans. Pattern Anal. & Mach. Intell., PAMI-6, No. 1, pp. 13–27 (1984)
G. Adiv: “Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects”, IEEE Trans. Pattern Anal. & Mach. Intell., PAMI-7, No.4, pp. 384–401 (1985)
M. Subbarao: “Interpretation of Image Flow: A Spatio-Temporal Approach”, IEEE Trans. Pattern Anal. & Mach. Intell., PAMI-11, No.3, pp. 266–278 (1989)
J. Hutchinson, C. Koch, J. Luo and C. Mead: “Computing Motion Using Analog and Binary Resistive Networks”, IEEE Computer, 21, 3, pp. 52–63 (1988)
K. Imai, K. Gouhara and Y. Hchikawa: “Detection of Position and Size Using Newral Network Learning”, Trans. Inst. of Elec., Inform., and Comm. Eng., Vol. J74-D-2, No.6, pp. 748–756 (1991) (in Japanese)
T. Nitta and T. Furuya: “A Complex Back Propagation Learning”, Trans. Information Proccesing Society of Japan, Vol. 32, No.10, pp. 1319–1329 (1991) (in Japanese)
T. Nitta, S. Akaho, Y. Akiyama and T. Furuya: “Structure of Weight Parameters and Decision Boundary in Complex Back-propagation Network”, Trans. Information Proccesing Society of Japan, Vol. 33, No. 11, pp. 1306–1313 (1992) (in Japanese)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Miyauchi, M., Seki, M., Watanabe, A., Miyauchi, A. (1993). Interpretation of optical flow through complex neural network. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_215
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_215
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive