Title :
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
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;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International
Print_ISBN :
0-7803-7536-X
DOI :
10.1109/IGARSS.2002.1024952