Author(s): |
Haihong Liu, Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming, China, 650093 Shu Gan, Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming, China, 650093 Xiping Yuan, Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming, China, 650093 Hongwei Han, Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming, China, 650093 |
Abstract: |
Remote sensing classification method is to acquire land use/land cover the main method of classified data, supervised classification is based on spectral features, the phase space of characteristics and the characteristics of the commonly used method features are classified. Maximum Likelihood Classifier belong to the parameters classification method, is considered to be the highest classification accuracy of classification method. This paper applied maximum likelihood classification method to establish classification model, in TM432 images for the test. The results show that the method can effectively extract of urban construction land information, in classification template accurate, its classification accuracy can reach more than 90%.
|