Remote Sensing Classification for Wetland Based on Support Vector Machine
Remote sensing is an important way to realize wetland dynamic monitoring,and play an effective role of management and protection of the wetland.With Yellow River wetland in Heyang of Shaanxi province as the study area,support vector machines (SVM) method is applied to retrieve land use/land cover types,and compare the result with traditional supervised classification methods (Minimum Distance and Maximum Likelihood).The result shows that SVM classification method has higher classification accuracy and lower misclassification rate,the consistency of the classification result and original image are high,and it is efficient tools in wetlands classification.
NETL
NSTL
万方数据
维普
