Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Geospatial Information》 2017-10
Add to Favorite Get Latest Update

Research on Land Use Classification Precision of GF-1 Images in the Deep Incised Area of Qinghai-Tibet Plateau

SUN Xiaofei;  
Taking the deep incised area of Qinghai-Tibet plateau for example, this paper studied classification technique and methods in the deep incised area of GF-1 images. The paper used the maximum likelihood method, the neural network method and the support vector machine(SVM) classification method to classify the images, evaluated and analyzed the precision of three classification methods. The results show that(1)?the precision of classification by using GF-1 images is high, which meets the requirement of remote sensing monitoring of land use.(2)?The whole precision of SVM method is 91.67% and it's Kappa coefficient is 89.54%, which is more precise than the maximum likelihood method and the neural network method. In conclusion, SVM method is optimal one to classify land use in deep incised area by using GF-1 images.
【Fund】: 国家自然科学基金资助项目(41302282 41401659);; 全国边海防地区基础地质遥感调查资助项目(12120115063501);; 四川省科技厅应用基础资助项目(2015JY0145)
【CateGory Index】: F301.2;P237
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved