Abstract
In this paper different methods applied to the Automatic Target Recognition problem are studied. A database of High Range Resolution radar profiles of six kinds of aircrafts is used to study the performance of four classification methods: k-Nearest Neighbor method, Multilayer Perceptrons, Radial Basis Function Networks, and Support Vector Machines. Results obtained with these classifiers show a high correlation between two of the classes of targets that cause the majority of errors. We propose to split the task into two subtasks. A first one in which the classes of correlated targets are grouped in a single class, and a second one to distinguish between them. Different classifiers are studied to be applied to each subtask. Results demonstrate that Radial Basis Function Networks are very good classifiers for the main subtask, while Support Vector Machines are the best classification method, among the studied, to distinguish between the correlated targets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S. P. Jacobs, et al., “Automatic Target Recognition Using Sequences of High Resolution Radar Range Profiles,” IEEE Transactions on Aerospace and Electronic Systems 36(2), 364–381 (2000).
C. R. Smith and P. M. Goggans, “Radar Target Identification,” IEEE Antennas and Propagation Magazine 35(2), 27–37 (1993).
K. Fukunaga, Introduction to Statistical Pattern Recognition (Academic Press, Boston, 1990).
R. A. Mitchell and J. J. Westerkamp, “Robust Statistical Feature Based Aircraft Identification,” IEEE Transactions on Aerospace and Electronic Systems 35(3), 1077–1094 (1999).
D. E. Nelson and J. A. Starzyk, “Advance Feature Selection Methodology for Automatic Target Recognition,” in Proceedings of the 29 Southeastern Symposium on System Theory, 1997, pp. 24–28.
D. E. Nelson and J. A. Starzyk, “High Range Resolution Radar Signal Classification. A Partitioned Rough Set Approach,” in Proceedings of the 33 Southeastern Symposium on System Theory, 2001, pp. 21–24.
A. A. Kisienski, Y.-T. Lin, and L. J. White, “Low-frequency Approach to Target Identification,” in Proceedings of the IEEE, 1975, Vol. 63, pp. 1651–1659.
R. Van Der Heiden and F. C. A. Groen, “The Box-Cox Metric for Nearest Neighbour Classification Improvement,” Pattern Recognition 30(2), 273–279 (1997).
M. W. Roth, “Survey of Neural Network Technology for Automatic Target Recognition,” IEEE Transactions on Neural Networks 1(1), 28–43 (1990).
S. K. Rogers et al., “Neural Networks for Automatic Target Recognition,” Neural Networks 8(7/8), 1153–1184 (2000).
R. Gil-Pita, P. Jarabo-Amores, M. Rosa-Zurera, and F. Lopez-Ferreras, “Improving Neural Classifiers for ATR Using a Kernel Method for Generating Synthetic Training Sets,” in Proceedings of the 2002 IEEE Workshop on Neural Networks for Signal Processing, 2002, pp. 425–434.
R. Gil-Pita, P. Jarabo-Amores, R. Vicen-Bueno, and M. Rosa-Zurera, “Neural Solution for High Range Resolution Radar Classification,” Lecture Notes in Computer Science 2687, 559–566 (2003).
C. M. Bishop, Neural Networks for Pattern Recognition, (Oxford University Press, Inc., 1995).
F. Rosenblatt, Principles of Neurodynamics (Spartan Books, New York, 1962).
G. Cybenko, “Approximation by Superpositions of a Sigmoidal Function,” Mathematics of Control, Signals and Systems 2(4), 303–314 (1989).
M. T. Hagan and M. B. Menhaj, “Training Feedforward Networks with the Marquardt Algorithm,” IEEE Transactions on Neural Networks 5(6), 989–993 (1994).
S. Haykin, Neural Networks. A Comprehensive Foundation, 2nd ed. (Prentice-Hall, Inc., 1999).
F. Schwenker, H. A. Kestler, and G. Palm, “Three learning phases for radial-basis-function networks,” Neural Networks 14(4–5), 439–458 (2001).
V. Vapnik, et al., The Nature of Statistical Learning Theory (Springer-Verlag, New York, 1995).
Author information
Authors and Affiliations
Additional information
The text was submitted by the authors in English.
Roberto Gil Pita, born in 1978, obtained the degree of Telecomunication Engineer at Alcala University, 2001. Roberto Gil Pita is currently the Lecturer in Signal Theory and Communications Department, Polytechnical School, Alcala University (Spain). His research interests include signal processing and radar applications. Roberto Gil Pita has published ten journal papers, five book chapters, and nine conference contributions. He is an IEEE student member.
Manuel Utrilla Manso, born in 1972, obtained the degree of Telecomunication Engineer at Polythecnic University of Madrid, 1999. Manuel Utrilla Manso is currently the Lecturer in Signal Theory and Communications Department, Polytechnical School, Alcala University (Spain). His research interests include signal processing, and digital filters and applications. Manuel Utrilla Manso has published 3 journals papers, 5 book chapters, 23 conference contributions, and 1 book. He is an IEEE student member.
Manuel Rosa Zurera, born in 1968, obtained the degree of Telecomunication Engineer at Polythecnic University of Madrid, 1995. Manuel Rosa Zurera is currently the Associated Professor and Head of the Department in Signal Theory and Communications Department, Polytechnical School, Alcala University (Spain). His fields of research are signal processing, signal detection, and radar systems. Manuel Rosa Zurera has published 18 journal papers, 10 book chapters, 41 conference contributions, and 2 books. He is an IEEE member.
Raúl Vicen Bueno, born in 1977, obtained the degree of Telecomunication Engineer at Alcala University, 2002. Raul Vicen Bueno is currently the Lecturer in Signal Theory and Communications Department, Polytechnic School, Alcala University (Spain). His research interests include signal processing and radar applications. Raul Vicen Bueno has published six journal papers, three book chapters, four conference contributions, and one book.
Awards and prizes for achievements in research or applications
Second place in the “Liberalizacion de las Telecomunicaciones” awards, given by the “Colegio Oficial de Ingenieros Tecnicos de Telecomunicacion” (COITT) of Spain.
Maria Pilar Jarabo Amores, born in 1971, obtained the degree of Telecomunication Engineer at Polythecnical University of Madrid, 1997. Maria Pilar Jarabo Amores is currently the Lecturer in Signal Theory and Communications Department, Polytechnical School, Alcala University (Spain). Her research interests include signal processing, signal detection, and radar systems. Maria Pilar Jarabo Amores has published 11 journals papers, 8 book chapters, 21 conference contributions, and 2 books. She is an IEEE student member.
Francisco López Ferreras, born in 1948, obtained the degree of Telecommunication Engineer at Polythecnic University of Madrid, 1970. Francisco Lopez Ferreras is currently Associated Professor and Dean of the Signal Theory and Communications Department, Polytechnic School, Alcala University (Spain). His field of research is signal processing. Francisco Lopez Ferreras has published 23 journal papers, 16 book chapters, 88 conference contributions, and 10 books. He is an IEEE member.
Rights and permissions
About this article
Cite this article
Gil-Pita, R., Jarabo-Amores, P., Rosa-Zurera, M. et al. Divide and conquer approach to improve performance on ATR systems. Pattern Recognit. Image Anal. 17, 284–291 (2007). https://doi.org/10.1134/S1054661807020174
Received:
Issue Date:
DOI: https://doi.org/10.1134/S1054661807020174