Abstract
We present a new parallel approach for the computation of an optical flow field from a video image sequence. This approach incorporates the various local smoothness, spatial and temporal coherence constraints transparently by the application of fuzzy image processing techniques. Our Vector Coherence Mapping VCM approach accomplishes this by a weighted voting process in “local vector space,” where the weights provide high level guidance to the local voting process. Our results show that VCM is capable of extracting flow fields for video streams with global dominant fields (e.g. owing to camera pan or translation, moving camera and moving object(s), and multiple moving objects. Our results also show that VCM is able to operate under strong image noise and motion blur, and is not susceptible to boundary oversmoothing.
Preview
Unable to display preview. Download preview PDF.
References
J. L. Barron, D. J. Fleet, and S. S. Beauchemin, “Performance of optical flow techniques”, Int. Journal of Comp. Vision, vol. 12, pp. 43–77, 1994.
B. K. P. Horn and B. G. Schunck, “Determining optical flow”, Art. Intel., vol. 17, pp. 185–204, 1981.
J. Weber and J. Malik, “Robust computation of optical flow in a multi-scale differential framework”, in Proc. 4th ICCV, Berlin, Germany, May 11–14, 1993.
Massimo Tistarelli, “Computation of coherent optical flow by using multiple constraints”, in Proc. 5th ICCV, MIT, Cambridge, MA, June 20–23, 1995.
T. Yu Tian and M. Shah, “Recovering 3D motion of multiple objects using adaptive Hough transform”, in Proc. 5th ICCV, MIT, Cambridge, MA, June 20–23, 1995.
Q.X. Wu, “A correlation-relaxation-labeling framework for computing optical flow — Template matching from a new perspective”, PAMI, vol. 17, pp. 843–853, 1995.
P. Anandan, “A computational framework and an algorithm for the measurement of visual motion”, Int. Jou. of Comp. Vision, vol. 2, pp. 283–310, 1989.
A. Singh, Optic Flow Computation: A Unified Perspective, IEEE C.S.Press, 1992.
Ellen C. Hildreth, “Computations underlying the measurement of visual motion”, Art. Intel., vol. 23, pp. 309–354, 1984.
D. J. Fleet, Measurement of image Velocity, Kluwer Acad. Publ., Norwell, 1992.
Bernd Jahne, “Analytical studies of low-level motion estimators in space-time images using a unified filter concept”, in Proc. of the IEEE Conf. on CVPR, Seattle, Washington, June 21–23, 1994.
G. Adiv, “Determining three-dimensional motion and structure from optical flow generated by several moving objects”, PAMI, vol. 7, pp. 384–401, 1985.
Harpreet S. Sawhney, Serge Ayer, and Monika Gorkani, “Model-based 2D & 3D dominant motion estimation for mosaicing and video representation”, in Proc. 5th ICCV, MIT, Cambridge, MA, June 20–23, 1995.
Francis Quek, “Eyes in the interface”, Int. J. of Image and Vision Comp., vol. 13, pp. 511–525, Aug. 1995.
I.K. Sethi and R. Jain, “Finding trajectories of feature points in a monocular image sequence”, PAMI, vol. 9, pp. 56–73, Jan. 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Quek, F.K.H., Bryll, R.K. (1997). Vector coherence mapping: A parallelizable approach to image flow computation. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63931-4_266
Download citation
DOI: https://doi.org/10.1007/3-540-63931-4_266
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63931-2
Online ISBN: 978-3-540-69670-4
eBook Packages: Springer Book Archive