An efficient neural classification chain of SAR and optical urban images

Citation
P. Gamba et B. Houshmand, An efficient neural classification chain of SAR and optical urban images, INT J REMOT, 22(8), 2001, pp. 1535-1553
Citations number
27
Categorie Soggetti
Earth Sciences
Journal title
INTERNATIONAL JOURNAL OF REMOTE SENSING
ISSN journal
01431161 → ACNP
Volume
22
Issue
8
Year of publication
2001
Pages
1535 - 1553
Database
ISI
SICI code
0143-1161(20010520)22:8<1535:AENCCO>2.0.ZU;2-Q
Abstract
In this paper a suitable neural classification algorithm, based on the use of Adaptive Resonance Theory (ART) networks, is applied to the fusion and c lassification of optical and SAR urban images. ART networks provide a flexi ble tool for classification, but are ruled by a large number of parameters. Therefore, the simplified ART2-A algorithm is used in this paper, and the neural approach is integrated into a classification chain where fuzzy clust ering for merging of classes is also considered. The interaction between th e two methods leads to encouraging results in less CPU time than classifica tion with fuzzy clustering alone or other classical approaches (ISODATA). E xamples of classification are provided using C-band total power AIRSAR data and optical images of Santa Monica, Los Angeles.