Abstract
A theorem is proven which serves as the mathematical basis for the proposed global shift-vector extraction. This theorem states the identity of the difference vector between the centers of gravity (centroids) of two arbitrary nD density functions, with the centroid vector of their cross-correlation function. Consequently, the centroid of the cross-correlation function of consecutive manifestations of an arbitrarily transforming density function indicates its incremental shift vector. Advantages of this approach for implementations in massively parallel computing structures as well as applications, such as visual velocity estimation of nonrigid objects, are discussed.
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
A. Papoulis. Probability, Random Variables, and Stochastic Processes. McGraw-Hill, New York/NY, 1965.
H. Glünder. Correlative velocity estimation: visual motion analysis, independent of object form, in arrays of velocity-tuned bilocal detectors. J. Opt. Soc. Am. A 7: 255–263, 1990.
H. Glünder. EH-networks for motion and invariant form analyses. In: R. Eck-miller, G. Hartmann and G. Hauske (ed.) Parallel Processing in Neural Systems and Computers. Elsevier, Amsterdam, pp. 357–360, 1990.
D.E. Rumelhart, G.E. Hinton and J.L. McClelland. A general framework for parallel distributed processing. In: D.E.Rumelhart and J.L. McClelland (ed.) Parallel Distributed Processing 1. The MIT Press, Cambridge/MA, pp. 45–76, 1986.
B. Has s ens tein and W. Reichardt. Systemtheoretische Analyse der Zeit-, Reihenfolgen-und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus. Z. Naturforschg. llb: 513–524, 1956.
H. Glünder. A dualistic view of motion and invariant shape analysis. In: J.C. Simon (ed.) From Pixels to Features. Elsevier, Amsterdam, pp. 323–332, 1989.
M. Abeles. Local Cortical Circuits. Springer, Berlin, 1982.
T.J. Sejnowski. Neural populations revealed. Nature 332: 308, 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Glünder, H. (1991). Global Shift Analysis of Dynamic Density Functions by Structured ∑Π-Networks. In: Radig, B. (eds) Mustererkennung 1991. Informatik-Fachberichte, vol 290. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-08896-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-662-08896-8_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54597-2
Online ISBN: 978-3-662-08896-8
eBook Packages: Springer Book Archive