Abstract
In this paper, a new approach to optical flow estimation in presence of multiple motions is presented. Firstly, motions are segmented on the basis of a frequency-based approach that groups spatio-temporal filter responses with continuity in its motion (each group will define a motion pattern). Then, the gradient constraint is applied to the output of each filter so that multiple estimations of the velocity at the same location may be obtained. For each “motion pattern”, the velocities at a given point are then combined using a probabilistic approach. The use of “motion patterns” allows multiple velocities to be represented, while the combination of estimations from different filters helps reduce the aperture problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Pingault, M., Bruno, E., Pellerin, D.: A robust multiscale b-spline function decomposition for estimating motion transparency. IEEE Transactions on Image Processing 12, 1416–1426 (2003)
Schunck, B.G.: Image flow segmentation and estimation by constraint line clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(10), 1010–1027 (1989)
Nagel, H., Enkelmann, W.: An investigation of smootness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 565–593 (1986)
Black, M.J., Anandan, P.: The robust estimation of multiple motion: parametric and piecewisesmooth flow fields. Computer Vision and Image Understanding 63(1), 75–104 (1996)
Heeger, D.J.: Model for the extraction of image flow. Journal of the Optical Society of America A 4(8), 1455–1571 (1987)
Nestares, O., Navarro, R.: Probabilistic estimation of optical flow in multiple band-pass directional channels. Image and Vision Computing 19(6), 339–351 (2001)
Chamorro-Martinez, J., Fdez-Valdivia, J., Martinez-Baena, J.: A spatiotemporal filtering approach to motion segmentation. In: Perales, F.J., Campilho, A.C., Pérez, N., Sanfeliu, A. (eds.) IbPRIA 2003. LNCS, vol. 2652, pp. 193–203. Springer, Heidelberg (2003)
Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. In: IEEE Proceedings of CVPR 1991, pp. 310–315 (1991)
Barron, J.L., Fleet, D.J., Beauchemin, S.: Performance of optical flow techniques. International Journal of Computer Vision 12(1), 43–77 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chamorro-Martínez, J., Martínez-Baena, J., Galán-Perales, E., Prados-Suárez, B. (2005). Dealing with Multiple Motions in Optical Flow Estimation. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds) Pattern Recognition and Image Analysis. IbPRIA 2005. Lecture Notes in Computer Science, vol 3522. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11492429_7
Download citation
DOI: https://doi.org/10.1007/11492429_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26153-7
Online ISBN: 978-3-540-32237-5
eBook Packages: Computer ScienceComputer Science (R0)