TY  - JOUR
AU  - Canty, M. J.
TI  - Boosting a Fast Neural Network for Supervised Land Cover Classification
JO  - Computers & geosciences
VL  - 35
SN  - 0098-3004
CY  - Amsterdam [u.a.]
PB  - Elsevier Science
M1  - PreJuSER-5090
SP  - 1080 - 1295
PY  - 2009
N1  - Record converted from VDB: 12.11.2012
AB  - It is demonstrated that the use of an ensemble of neural networks for routine land cover classification of multispectral satellite data can lead to a significant improvement in classification accuracy. Specifically, the AdaBoost.M1 algorithm is applied to a sequence of three-layer, feed-forward neural networks. In order to overcome the drawback of long training time for each network in the ensemble, the networks are trained with an efficient Kalman filter algorithm. On the basis of statistical hypothesis tests, classification performance on multispectral imagery is compared with that of maximum likelihood and support vector machine classifiers. Good generalization accuracies are obtained with computation times of the order of I h or less. The algorithms involved are described in detail and a software implementation in the ENVI/IDL image analysis environment is provided. (C) 2009 Elsevier Ltd. All rights reserved.
KW  - J (WoSType)
LB  - PUB:(DE-HGF)16
UR  - <Go to ISI:>//WOS:000266544700022
DO  - DOI:10.1016/j.cageo.2008.07.004
UR  - https://juser.fz-juelich.de/record/5090
ER  -