Abstract
We present a new method to simultaneously estimate optical flow fields and parameters of dynamic processes, violating the standard brightness change constraint equation. This technique constitutes a straightforward generalization of the standard brightness constancy assumption. Using TLS estimation the spatiotemporal brightness structure is analyzed in an entirely symmetric way with respect to the spatial and temporal coordinates. We directly incorporate nonlinear brightness changes based upon differential equations of the underlying processes.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Duc, B.: Feature design: applications to motion analysis and identity verification. PhD thesis, École Polytechnique Fédérale de Lausanne (1997)
Florae, L., W. Niessen, and M. Nielsen: The intrinsic structure of optical flow in-corporating measurement duality. Intl. J. Comp. Vis., 27 (3), (1998) 263–286
Hager, G. D., and P. N. Belhumeur: Efficient region tracking with parametric models of geometry and illumination. IEEE PAMI, 20(10), (1998) 1025–1039
Haußecker, H., and B. Jähne: A tensor approach for precise computation of dense displacement vector fields. In ‘Informatik aktuell’, Paulus, E., Wahl, F. M. (Hrsg.), Mustererkennung 1997, Springer-Verlag: Berlin, Heidelberg (1997) 199–208
Haußecker, H., and H. Spies: Motion. In ‘Handbook of Computer Vision and Applications’, Jahne, B., Haußecker, H., and Geißler, P. (Eds.), Academic Press, (1999)
Horn, B. K., and B. G. Schunk: Determining optical flow. AI, 17, (1999) 185–204
Jahne, B., H. Haußecker, H. Scharr, H. Spies, D. Schmundt, and U. Schurr: Study of dynamical processes with tensor-based spatiotemporal image processing techniques. Proc. ECCV ’98 (Vol. 2), Burkhardt, H., and Neumann, B. (Eds.), Springer-Verlag: Berlin, Heidelberg (1998) 322–335
Mühlich, M., and R. Mester: The role of Total Least Squares in motion analysis. Proc. ECCV ’98 (Vol. 2), Burkhardt, H., and Neumann, B. (Eds.), Springer-Verlag: Berlin, Heidelberg (1998) 305–321
Nagel, H.-H.: On a constraint equation for the estimation of displacement rates in image sequences. IEEE PAMI, 11 (1), (1989) 13–30
Nagel, H.-H., and A. Gehrke: Bildbereichsbasierte Verfolgung von Straßenfahrzeugen durch adaptive Schätzung und Segmentierung von Optischen-Flußfeldern. In ‘Informatik aktuell’, Levi, P., Ahlers, R.-J., May, F., Schanz, M. (Hrsg.), Mustererkennung 1998, Springer-Verlag: Berlin, Heidelberg (1998) 314–321
Negahdaripour, S.: Revised definition of optical flow: integration of radiometric and geometric clues for dynamic scene analysis. IEEE PAMI, 20 (9), (1998) 961–979
Ohta, N.: Optical flow detection using a general noise model. IEICE Trans. Inf. & Syst., Vol. E79-D, No. 7 July (1996) 951–957
Van Huffel, S., and S. Vandewalle: The Total Least Squares Problem: Computational aspects and analysis. SIAM, (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Haußecker, H., Garbe, C., Spies, H., Jähne, B. (1999). A Total Least Squares Framework for Low-Level Analysis of Dynamic Scenes and Processes. In: Förstner, W., Buhmann, J.M., Faber, A., Faber, P. (eds) Mustererkennung 1999. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60243-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-60243-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66381-2
Online ISBN: 978-3-642-60243-6
eBook Packages: Springer Book Archive