Title :
A combined supervised and unsupervised approach to classification of multitemporal remote sensing images
Author :
Bruzzone, Lorenzo ; Prieto, Diego Fernandez
Author_Institution :
DICA, Trento Univ., Italy
Abstract :
A combined supervised and unsupervised approach to classification of multitemporal remote sensing images is presented. Such an approach performs the automatic classification of a remote sensing image for which training data are not available by exploiting the information derived from an image acquired in the same area at a previous time. Experiments, carried out on a multitemporal data set, point out the effectiveness of the proposed method
Keywords :
geophysical signal processing; geophysical techniques; image classification; remote sensing; terrain mapping; automatic classification; geophysical measurement technique; image classification; image sequence; land surface; multitemporal images; remote sensing; supervised approach; terrain mapping; unsupervised approach; Earth; Electronic mail; Information resources; Multispectral imaging; Pixel; Remote monitoring; Remote sensing; Robustness; Training data;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2000. Proceedings. IGARSS 2000. IEEE 2000 International
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-6359-0
DOI :
10.1109/IGARSS.2000.860455
