Abstract
This paper deals with the using of Artificial Neural Networks (ANN) for motion estimation. By means of simple neural structures it is possible to improve the reliability and accuracy of block matching algorithms (BMA) by a postprocessing of the similarity criterion. The ANN dimensions the appropriate structures. The fundamental idea and some first results will be described. The performance capability of the proposed method is shown for selected synthetic one- and real world two-dimensional measuring situations which are not solvable by means of conventional BMA.
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
Convertino, G.; et. al.: Hopfield: Neural Network for Motion Estimation and Interpretation. Proc. ICANN’ 94, Sorrento, Italy, 26–29 May 1994, Vol. 1, pp. 78–81.
Schnelting, O.; Seiffert, U.; Michaelis,B.: Bewegungsschätzung mit künstlichen neuronalen Netzen. 4. Dortunder Fuzzy-Tage’94 Dortmund, Germany.
Zaagman, W.H.; et. al.: On the Correlation Model: Performance of a Movement Detecting Neural Element in the Fly Visual System. Biological Cybernetics 31 (1978), pp. 163–178.
Poggio, T.; Reichart, W.: Considerations on Models of Movement Detection. Kybernetik 13 (1973), pp. 223–227.
Seiffert, U; Michaelis, B.: Estimating Motion Parameters from Image Sequences by Self-Organizing Maps. Proc. 39. IWK Ilmenau, 1994.
Musmann, H.-G.; Pirsch, P.; Grallert, H.-J.: Advances in Picture Coding. Proc. IEEE 73 (1985) No. 4, pp. 523–530.
Wiener, N.: The Extrapolation, Interpolation and Smoothing of Stationary Time Series. Wiley & Sons, New York, 1949.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag/Wien
About this paper
Cite this paper
Schnelting, O., Michaelis, B., Mecke, R. (1995). Artificial Neural Networks for Motion Estimation. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7535-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-7091-7535-4_37
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-82692-8
Online ISBN: 978-3-7091-7535-4
eBook Packages: Springer Book Archive