Competitive artificial neural network for change-detection of land cover: an unsupervised approach

Author

Velloso, Maria Luiza F ; Simões, Margareth ; Carneiro, Thales A.

Author_Institution

Dept. of Electron. Eng., Univ. do Estado do Rio de Janeiro, Brazil

Volume

1

fYear

2002

fDate

2002

Firstpage

95

Abstract

This work investigates the potential of an unsupervised network classifier, the Centroid Neural Network (CNN), for land cover change detection in remotely sensed images. Experiments carried out to evaluate the algorithm include change detection in both approaches: pre-classification and post-classification. Results confirm the effectiveness of this technique.

Keywords

adaptive signal processing; geophysical signal processing; geophysical techniques; image sequences; neural nets; terrain mapping; Centroid Neural Network; algorithm; change detection; competitive artificial neural network; geophysical measurement technique; image processing; image sequence; land cover; land surface; multitemporal image processing; network classifier; neural net; post-classification; pre-classification; remote sensing; self-adaptive classifier; terrain mapping; unsupervised approach; Artificial neural networks; Cellular neural networks; Change detection algorithms; Clustering algorithms; Data engineering; Image processing; Neural networks; Remote monitoring; Remote sensing; Satellites;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International

Print_ISBN

0-7803-7536-X

Type

conf

DOI

10.1109/IGARSS.2002.1024952

Filename

1024952