Target tracking with glint noise using an RBF neural network

Author

Yan, WeI ; Zhu, Zhaoda

Author_Institution

Dept. of Electron. Eng., Nanjing Univ. of Aeronaut. & Astronaut., China

Volume

1

fYear

1996

fDate

20-23 May 1996

Firstpage

239

Abstract

In this paper, the problem of target tracking with glint noise is considered. We apply a radial basis function (RBF) neural network to evaluate the nonlinear score function, which is used as the correction term in the state estimation of robust Kalman filter. Simulation results are presented to demonstrate the performance of the evaluation of the score function

Keywords

adaptive Kalman filters; adaptive estimation; adaptive signal detection; convolution; feedforward neural nets; radar cross-sections; radar detection; radar interference; radar signal processing; radar tracking; recursive estimation; state estimation; target tracking; unsupervised learning; Gaussian density function; adaptive estimation; convolution; glint noise; kernel functions; maneuvering target dynamics; non-Gaussian noise; nonlinear score function; radial basis function neural network; recursive algorithm; robust Kalman filter; simulation; state estimation; system model; target tracking; time series samples; unsupervised learning; Convolution; Degradation; Differential equations; Linear systems; Neural networks; Noise robustness; Probability density function; State estimation; Target tracking; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1996. NAECON 1996., Proceedings of the IEEE 1996 National

Conference_Location

Dayton, OH

ISSN

0547-3578

Print_ISBN

0-7803-3306-3

Type

conf

DOI

10.1109/NAECON.1996.517649

Filename

517649