Application Study on Classification of Remote Sensed Imagery Using Improved RBF Neural Network

摘要：

In this paper, we had made some improves on RBF neural network used in the classification of remote sening imagery. During the structure of network being designed, RBF layer nodes and output layer nodes was both equal to the number of classes to be classified. We used the mean values of training samples as the initial center of RBF when using Kohonen algorithm to train RBF center, and made some mending to avoid memory overflow when computing the width of RBF. Experiment result showed that the classification accuracy of this improved RBF model was comparatively high, and it has practical application value.

关键词： Remote sening imagery RBF neural network Supervised classification

作者: Xiao-Bo Luo

作者单位: Sino-Korea Chongqing GIS Research Center, College of Computer Science and Technology,Chongqing University of Posts and Telecommunications, China

会议类型: 国际会议

会议名称: The 8th Asian Symposium on Geographic Information Systems from a Computer Science & Engineering Viewpoint(ASGIS 2010)(第八届亚洲地理信息系统国际学术研讨会)

会议地点: 重庆

会议语种:英文

页码: 74-77

在线出版日期: 2010-04-22（万方平台首次上网日期，不代表论文的发表时间）