基于TM遥感影像的鄱阳湖湿地分类研究

对覆盖鄱阳湖湿地的LandsatTM遥感影像进行了计算机自动分类技术方法的实验研究,采用了先对遥感影像数据进行非监督分类,在非监督分类的基础上进行人工解译,确定其类别属性,然后将人工解译后的非监督分类的分类属性表经过光谱聚类处理转化成适用于监督分类的分类模板文件,再执行监督分类的方法,有效地提高了湿地遥感影像分类的精度。

Study on Classification of Poyang Lake Wetland Area Based on Landsat TM Image

The computer automatic classification method for Landsat TM image covering Poyang Lake wetland was studied.In the experiment firstly unsupervised classification was used to the remote sensing image,manual interpreting was made to determine the attributes,which were transformed to the file of classification cyclostyle,and then carried out supervised classification.It indicated that the classification precision of Poyang Lake wetland was improved through these means.