Abstract
In the usual optical flow detection, the gradient constraint, which expresses the relationship between the gradient of the image intensity and its motion, is combined with the least-squares criterion. From a statistical point of view, this means assuming that only the time derivative of the image intensity contains Gaussian noise. However, it is more reasonable to assume that all the derivatives are observed with Gaussian noise because they are equally computed from pixels containing noise and approximated by finite difference. In this paper, we study a new optical flow detection method based on the latter assumption. Since this method requires the knowledge about the covariance matrix of the noise, we also discuss a method for its estimation. Our experiments show that the proposed method can compute optical flow more accurately than the conventional method.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Anandan, P.: A computational framework and an algorithm for the measurement of visual motion. Int. J. Comput. Vis. 2 (1989) 283–310
Barron, J.L., Fleet. D.J., Beauchemin, S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12(1) (1994) 43–77
Horn, B.K.P., Schunk, B.G.: Determining optical flow. Artificial Intelligence 17 (1981) 185–203
Kanatani, K.: Statistical Optimization for Geometric Computation: Theory and Practice. Elsevier Science, Amsterdam (1996)
Kearney, J.K., Thompson, W.B., Boley, D.L.: Optical flow estimation: an error analysis of gradient-based methods with local optimization. IEEE Trans. Patt. Anal. Mach. Intell. 9(2) (1987) 229–244
Lucas, B, Kanade, T.: An iterative image registration technique with an application to stereo vision. Proc. 7th Int. Joint Conf. Artif. Intell., Vancouver Canada (1981) 674–679
Ohta, N.: Image movement detection with reliability indices. IEICE Trans. E74(10) (1991) 3379–3388
Press, H.P., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes in C. Cambridge University Press Cambridge (1988)
Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. Proc. Conf. Comput. Vis. Patt. Recog., Maui Hawaii (1991) 310–315
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ohta, N. (1997). Optical flow detection using a general noise model for gradient constraint. In: Sommer, G., Daniilidis, K., Pauli, J. (eds) Computer Analysis of Images and Patterns. CAIP 1997. Lecture Notes in Computer Science, vol 1296. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63460-6_177
Download citation
DOI: https://doi.org/10.1007/3-540-63460-6_177
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63460-7
Online ISBN: 978-3-540-69556-1
eBook Packages: Springer Book Archive