Abstract
A neural architecture is presented, aimed to describe the dynamic evolution of complex structures inside a video sequence. The proposed system is arranged as a tree of self-organizing maps. Leaf nodes are implemented by ARSOM networks as a way to code dynamic inputs, while classical SOM’s are used to implement the upper levels of the hierarchy. Depending on the application domain, inputs are made by suitable low level features extracted frame by frame of the sequence. Theoretical foundations of the architecture are reported along with a detailed outline of its structure, and encouraging experimental results.
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
A. Chella, M. Frixione, and S. Gaglio. A Cognitive Architecture for Artificial Vision. Artificial Intelligence, 89:73–111, 1997.
P. Frasconi, M. Gori, and A. Sperduti. A General Framework for Adaptive Processing of Data Structures. IEEE Trans. on Neural Networks, 9(5):768–786, September 1998.
M. Hermann, R. Der, and G. Balzuweit. Hierarchical Feature Maps and Nonlinear Component Analysis. In Proc. of ICNN’96, volume 2, pages 1390–1394, Texas, 1996.
T. Kohonen. The Self-Organizing Map. Proceedings of the IEEE, 78(9):1464–1480, September1990.
T. Kohonen, S. Kaski, K. Lagus, and T. Honkela. Very Large Two-Level SOM for the Browsing of Newsgroups. In Proc. of International Conference on Artificial Neural Networks, pages 269–274, Bochum, Germany, 1996.
P. Koikkalainen and E. Oja. Self-Organizing Hierarchical Feature Maps. In Proc. of International Joint Conference on Neural Networks, pages 279–284, San Diego, CA, 1990.
J. Laaksonen, M. Koskela, and E. Oja. PicSOM: Self-Organizing Maps for Content-Based Image Retrieval. In Proc. of International Joint Conference on Neural Networks, Washington D.C., USA, July 1999.
J. Lampinen and E. Oja. Self-Organizing Maps for Spatial and Temporal AR Models. In Proc. of the sixth SCIA Scandinavian Conference on Image Analysis, pages 120–127, Helsinky, Finland, 1990.
J. Lampinen and E. Oja. Clustering Properties of Hierarchical Self-Organizing Maps. J. Math. Imaging Vision, 2(3):261–271, 1992.
T.C. Lee and M. Peterson. Adaptive Vector Quantization Using a Self-Development Neural Network. IEEE J. Select Areas Commun., 8:1458–1471, 1990.
R. Mugnuolo, P. Magnani, E. Re, and S. Di Pippo. The SPIDER Manipulation System (SMS). The Italian Approach to Space Automation. Robotics and Autonomous Systems, 23(1–2), 1998.
G. Ongun and U. Halici. Fingerprint Classification through Self-Organizing Feature Map Modified to Treat Uncertainty. Proceedings of the IEEE, 84(10):1497–1512, October 1996.
A. Sperduti and A. Starita. Supervised Neural networks for the Classification of Structures. IEEE Trans. on Neural Networks, 8(3):714–735, May 1997.
P. N. Suganthan. Hierarchical Overlapped SOM’s for Pattern Classification. IEEE Trans. on Neural Networks, 10(1):193–196, January 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chella, A., Guarino, M.D., Pirrone, R. (2001). Description of Dynamic Structured Scenes by a SOM/ARSOM Hierarchy. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_143
Download citation
DOI: https://doi.org/10.1007/3-540-44668-0_143
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42486-4
Online ISBN: 978-3-540-44668-2
eBook Packages: Springer Book Archive