Abstract
This paper describes a research activity devoted to verify the feasibility of a neural network approach for automatic detection of naval targets in radar imagery. The activity is part of a more ambitious industrial project concerning the use of advanced image processing techniques for improving the safety in maritime surveillance of harbour traffic. Having in mind this final application, the task of automatic target detection has to fulfil two main requirements: 1) quasi real time response, in the sense that each input radar image of about 1000 by 1000 pixels has to be analyzed in a time comparable with the sweep period of the acquisition system, i.e. three seconds; 2)very high accuracy, i.e. each ship in the scene must be surely detected: this means that the efficiency of the detection system should be not minus than 100%. These two applicative needs have to meet with the high degree of noise (clutter) characterizing the input radar data. In order to face up to the complexity of the exposed goal, the task has been decomposed in a set of sequential subtasks: noise elimination, preliminary object recognition and classified image reconstruction. Moreover, both neural and traditional tools have been used, designing a multi-modular hybrid system (a detailed discussion about the advantages of hybrid architecture can be found, for example, in (F. Folgelman Suolie, 1993)).
This work has been developed within a grant of the Programma Nazionale di Ricerca per la Bioelettronica assigned by the Italian Ministry of Scientifica and Technological Research to Elsag Bailey
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
Folgelman Soulie F., (1993), Multi-Modular Neural Network-Hybrid architectuires: a Review, Proc. of 1993 Int. Conf. on Neural Network, Nagoya, 2231–2236.
Hertz J.,Krogh A., Palmer R. G., (1991) Introduction to the Theory of Neural Computation. Redwood City, CA: Addison-Wesley.
Rumelhart D. E., Hinton G. E., Williams R. J., (1986) Learning internal representation by error propagation. in Parallel Distributed Processing. vol. 1, Rumelhart D. E., Mc-Oelland J. L. Cambridge: MIT Press.
Kohonen T., Self Organization and Associative Memory. (1987) 2nd edition Springer Verlag, Berlino.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag London Limited
About this paper
Cite this paper
Fiorentini, G., Pasquariello, G., Satalino, G., Spilotros, F. (1994). Hybrid System for Ship Detection in Radar Images. In: Marinaro, M., Morasso, P.G. (eds) ICANN ’94. ICANN 1994. Springer, London. https://doi.org/10.1007/978-1-4471-2097-1_64
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2097-1_64
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19887-1
Online ISBN: 978-1-4471-2097-1
eBook Packages: Springer Book Archive