Abstract
The Dynamic Pyramid is a tool for analyzing monocular moving image sequences. Its process for achieving correspondence between successive frames is based on the physical model of the elastic membrane, where the cost function consisting of the similarity between the frames and the deformation of the transformation vector field is minimized.
A new concept is developped in order to determine the iniatial local displacements. It includes isolated points like corners but also makes use of the one given component of the displacement at edges. For the local correlation the sign of the Laplacian is used. This is a fast and reliable method to determine the initial displacements. A new approach of region oriented continuity constraints is developped in order to allow semantic discontinuities e.g. due to occlusion.
To make a scaleinvariant analysis of image sequences possible, the membrane model is extended to the Dynamic Pyramid. It makes use of the fact that at the coarser levels of the pyramid even large distances come into the realm of local operators. The results of one level are good starting values of the next. Thus also there local operators can be applied.
This achieves a reliable mapping in combination with an efficient calculation. The result of the dynamic pyramid is a local motion vector field. From there segmentation of moving objects is simple and the basic information for further steps like 3D-reconstruction is given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literature
Bajcsy,R.; Lieberson,R.; Reivich,M. (1983) A Computerized System for the Elastic Matching of Deformed Radiographic Images to Idealized Atlas Images Journ. of Comp. Ass. Tomography 7 (4): 618–625
Broit,Ch. (1981) Optimal Registrations of Deformed Images Dissertation, Univ. of Pennsylvania, USA
Burt,P.J. (1984) The Pyramid as a Structure for Efficient Computation in Rosenfeld,A.(ed.),Multiresolution Image Processing and Analysis,Springer,Berlin
Dengler,J. (1985) Methoden und Algorithmen zur Analyse bewegter Realweltszenen im Hinblick auf ein Blindenhilfesystem Dissertation Univ. Heidelberg
Feynman,R. (1964) The Feynman Lectures on Physics Vol. II, Kар. 39. 29 Addison-Wesley, Reading, Mass., USA
Hildreth,E.C. (1984) The Computation of the Velocity Field Proceedings R. Soc. Lond. В 221, pp. 189–220
Horn,B.K.P.; Schunck,B.G. (1981) Determining Optical Flow Artificial Intelligence Vol. 17, pp. 185–204
Nagel,H.H.; Enkelmann,W. (1984) Towards the Estimation of Displacement Vector Fields by “Oriented Smoothness” Constraints. Proceedings 7th ICPR, pp. 6–8
Nishihara,H.K. (1984) PRISM: A Practical Real-Time Imaging Stereo Matcher MIT A.I. Memo No. 780, Cambridge, Mass., USA
Prager, J.M.; Arbib,M.A. (1983) Computing the Optic Flow: The MATCH-Algorithm and Prediction Соmр. Vision, Graph.,and Im.Proc. 24, pp. 271–304
Terzopoulos,D. (1983) Multilevel Computational Processes for Visual Surface Reconstruction Соmр. Vision, Graphics, and Im.Proc. 24, pp. 52–96
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1986 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dengler, J. (1986). Local motion estimation with the Dynamic Pyramid. In: Cantoni, V., Levialdi, S. (eds) Pyramidal Systems for Computer Vision. NATO ASI Series, vol 25. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-82940-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-82940-6_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-82942-0
Online ISBN: 978-3-642-82940-6
eBook Packages: Springer Book Archive