Land-cover classification of multispectral imagery using a dynamic learning neural network

The results of the classification of SPOT high resolution visible multispectral imagery using a neural network are presented. The test site, located near Taoyuan in northern Taiwan, is in an agricultural area containing small ponds, bare and barren soils, vegetation, built-up land, and man-made buildings near the sea shore. The classififer is a dynamic learning neural network (DL) using the Kalman filter technique as its adaptation rule. The network's architecture consists of multi-layer perceptrons, i.e., feed-forward nets with one or more layers between the input and output nodes. Selected data sets from 512- by 512-pixel three-band images were used to train the neural nets to classify the different types of land cover. Both simulated and real images were used to test classification performance. -from Authors