SAM在Hyperion数据的土地利用分类中的应用——以平顶山新华区为例

A Study on the Application of SAM and Hyperion Data in Land Use Classification—— A Case Study of Xinhua District of Pingdingshan

利用SAM分类原理,以Hyperion高光谱遥感数据为数据源,对平顶山市新华区的部分地区进行了土地利用类型的分类提取,并利用混淆矩阵进行精度评价验证,总精度为95%,Kappa系数为0.8962.研究结果表明,高光谱数据的土地利用分类中,光谱角匹配技术是一种有效的分类方法,可以满足土地利用类型信息的分类需要.

In this paper, a study is conducted on the land use classification of Xinhua district of Pingdingshan, with SAM as the classification principle and the Hyperion hyperspectral remote sensing data as the data source. The confusion matrix is used for accuracy assessment. Results show that the overall accuracy is 95 % and the Kappa coefficient is 0. 8962. The researching results of this study indicate that in Hyperion data land use classification, spectral angle matching（SAM） is an effective classification technique and can be applied in clas- sifying information of different land use.