Kalman filtering as a multilayer perceptron training algorithm for detecting changes in remotely sensed imagery

Author

Chibani, Youcef ; Nemmour, Hassiba

Author_Institution

Lab. de Traitement du Signal, Univ. des Sci. et de la Technol. Houari Boumedienne, Algiers, Algeria

Volume

6

fYear

2003

fDate

21-25 July 2003

Firstpage

4101

Abstract

The multilayer perceptron is usually trained by the backpropagation (BP) algorithm for computing the synaptic weights. In this paper, we investigate the use of Kalman filtering (KF) as a training algorithm for detecting changes in remotely sensed imagery. By using SPOT images and based on some evaluation criteria, the detailed comparison indicates that the KF algorithm is preferable compared to the BP algorithm in terms of convergence rate, stability and change detection accuracy.

Keywords

Kalman filters; backpropagation; geophysical techniques; geophysics computing; multilayer perceptrons; remote sensing; Kalman filtering; SPOT images; backpropagation algorithm; change detection; convergence rate; multilayer perceptron training algorithm; remotely sensed imagery; synaptic weights; Backpropagation algorithms; Change detection algorithms; Convergence; Equations; Filtering algorithms; Kalman filters; Mean square error methods; Multilayer perceptrons; Neural networks; Stability criteria;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International

Print_ISBN

0-7803-7929-2

Type

conf

DOI

10.1109/IGARSS.2003.1295375

Filename

1295375