The use of an artificial neural network for detecting significant changes between remotely sensed images over regions of high variability

Author

Feldberg, Idan ; Netanyahu, Nathan S. ; Shoshany, Maxim ; Cohen, Yafit

Author_Institution

Dept. of Math. & Comput. Sci., Bar-Ilan Univ., Ramat-Gan, Israel

Volume

6

fYear

2001

fDate

2001

Firstpage

2704

Abstract

An artificial neural network (ANN) has been developed for the task of change detection in an area of high spatio-temporal heterogeneity along a climatic gradient between humid and and climate regions. Four recognition classes, "positive change", "negative change", "false change", and "no change" have been learned by a backpropagation ANN and then applied to Landsat images that were acquired over the study area in 1992 and 1997. A comparison with existing classification techniques indicates, in many instances, significantly improved performance due to the ANN developed

Keywords

backpropagation; geophysical signal processing; image classification; neural nets; remote sensing; Landsat images; arid regions; artificial neural network; backpropagation ANN; change detection; classification techniques; false change; high spatio-temporal heterogeneity region; high variability regions; humid regions; negative change; no change; positive change; recognition classes; remotely sensed images; Artificial neural networks; Backpropagation; Electronic mail; Mathematics; Monitoring; Neurons; Remote sensing; Satellites; Transfer functions; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-7031-7

Type

conf

DOI

10.1109/IGARSS.2001.978136

Filename

978136