Summary
The neural extended Kalman filter is an adaptive state estimation routine that can be used in target-tracking systems to aid in the tracking through maneuvers. A neural network is trained using a Kalman filter training paradigm that is driven by the same residual as the state estimator and approximates the difference between the a priori model used in the prediction steps of the estimator and the actual target dynamics. An important benefit of the technique is its versatility because little if any a priori knowledge of the target dynamics is needed. This allows the neural extended Kalman filter to be used in a generic tracking system that will encounter various classes of targets. Here, the neural extended Kalman filter is applied simultaneously to three separate classes of targets each with different maneuver capabilities. The results show that the approach is well suited for use within a tracking system without prior knowledge of the targets’ characteristics.
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
Steinberg, A., Bowman, C., White, F.: Revisions to the JDL data fusion model. Proceedings of the SPIE Sensor Fusion: Architectures, Algorithms, and Applications III, 1999, 430–441
Llinas, J., Bowman, C., Rogova, G.L., Steinberg, A., Waltz, E., White, F.: Revisions and extensions to the JDL data fusion model II. Proceedings of Fusion 2004, Stockholm, Sweden, 2003, 1218–1230
Blackman, S., Popoli, R.: Design and analysis of modern tracking systems, Artech House, Norwood, MA, 1999
Best, R.A., Norton, J.P.: A new model and efficient tracker for a target with curvilinear motion. IEEE Transactions on Aerospace and Electronic Systems, Vol. 34, 1997, 1030–1037
Efe, M., Atherton, D.P.: Maneuvering target tracking with an adaptive Kalman filter. Proceedings of the 37th IEEE Conference on Decision and Control, 1998, 737–742
Kirubarajan, T., Bar-Shalom, Y.: Tracking evasive move-stop-move targets with a GMTI radar using a VS-IMM estimator. IEEE Transactions on Aerospace and Electronic Systems, Vol. 39(3), 2003, 1098–1103
Owen, M.W., Stubberud, A.R.: A neural extended Kalman filter multiple model tracker. Proceedings of OCEANS 2003 MTS/IEEE, 2003, 2111–2119
Jetto, L., Longhi, S., Venturini, G.: Development and experimental validation of an adaptive extended Kalman filter for the localization of mobile robots. IEEE Transactions on Robotics and Automation, Vol. 15(2), 1999, 219–229
Stubberud, S.C., Lobbia, R.N., Owen, M.: An adaptive extended Kalman filter using artificial neural networks. Proceedings of the 34th IEEE Conference on Decision and Control, 1995, 1852–1856
Stubberud, S.C., Lobbia, R.N., Owen, M: An adaptive extended Kalman filter using artificial neural networks. International Journal on Smart System Design, Vol. 1, 1998, 207–221
Singhal, S., Wu, L.: Training multilayer perceptrons with the extended Kalman algorithm. In: Touretsky, D.S. (ed.), Advances in Neural Processing Systems I, Morgan Kaufmann, Los Altos, CA (1989), 133–140
Stubberud, A.R., Wabgaonkar, H.M: Neural network techniques and applications to robust control. In: Leondes, C.T. (ed.), Advances in Control and Dynamic Systems (53), Academic, New York, 1992 427–522
Mack, G., Jain, V.: Speech parameter estimation by time-weighted-error Kalman filtering. IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 31(5), 1983, 1300–1303
Iglehart, S., Leondes, C.: Estimation of a dispersion parameter in discrete Kalman filtering. IEEE Transactions on Automatic Control, Vol. 19 (3), 1974, 262–263
Rhodes, I.B.: A tutorial introduction to estimation and filtering. IEEE Transactions on Automatic Control, Vol. AC-16 (6), (1971), 688–706
Brown, R.G.: Introduction to random signal analysis and Kalman filtering, Wiley, New York, 1983
Owen, M.W., Stubberud, A.R.: NEKF IMM tracking algorithm. (ed.) Drummond, O.: Proceedings of SPIE: Signal and Data Processing of Small targets 2003, Vol. 5204, San Diego, California, 2003
Shea, P.J., Zadra, T., Klamer, D., Frangione, E., Brouillard, R.: Improved state estimation through use of roads in ground tracking. Proceedings of SPIE: Signal and Data Processing of Small Targets, Orlando, FL, 2000
Brouillard, R., Stubberud, S.: A parallel approach to GMTI tracking. Proceedings of the Military Sensing Symposia: 2003 National Symposium on Sensor Data Fusion, San Diego, CA, 2003
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks, Vol. 2, 1989, 35–36
Alspach, D., Sorenson, H.: Nonlinear Bayesian estimation using Gaussian sum approximations. IEEE Transactions on Automatic Control, Vol. 17(4), 1972, 439–448
Brotherton, T., Johnson, T., Chadderdon, G.: Classification and novelty detection using linear models and a class dependent neural network. Proceedings of World Congress for Computational Intelligence (IJCNN), Anchorage, Alaska, 1998, 876–879
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kramer, K.A., Stubberud, S.C. (2008). Tracking of Multiple Target Types with a Single Neural Extended Kalman Filter. In: Chountas, P., Petrounias, I., Kacprzyk, J. (eds) Intelligent Techniques and Tools for Novel System Architectures. Studies in Computational Intelligence, vol 109. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77623-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-77623-9_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77621-5
Online ISBN: 978-3-540-77623-9
eBook Packages: EngineeringEngineering (R0)