期刊名称：International Journal of Environmental Protection and Policy
印刷版ISSN：2330-7528
电子版ISSN：2330-7536
出版年度：2016
卷号：4
期号：3
页码：93-97
DOI：10.11648/j.ijepp.20160403.17
语种：English
出版社：Science Publishing Group
摘要：Remote sensing (RS) data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.
