摘要
选择青海湖流域内一个代表性区域为试验区,以TM数据和地形数据为主要数据源,在GeoEye-1高分辨率影像和土壤图的辅助下,采用最大似然监督分类方法,探讨了遥感技术在青海湖流域土壤分类中的可行性。使用主成分分析、缨帽变换、波段组合等图像处理技术,从TM图像中提取了多种图像特征,并结合高程、坡度及坡向等地形参数,共同生成分类特征数据集进行遥感分类。研究表明,基于遥感图像和地形数据提取的分类特征,有效地区分出试验区内9个土壤亚类和1个非土壤单元,总体分类精度达到了91.76%。
The aim of this study is to test the feasibility of soil classification based on remote sensing in a typical area of Qinghai Lake basin. The authors employed TM image and terrain data as main data sources, and used GeoEye- 1 high- resolution remote sensing images and soil map as auxiliary data sources. The TM image was processed to extract classification features by using a variety of image processing techniques, which included such means as principal component analysis, tasseled cap transformation, and band math. Supported by ArcGIS9.3 software, the authors detected several topographical features with DEM, such as elevation, slope and aspect. Then, the authors incorporated all classification features into a dataset, and used maximum likelihood classifier of supervision to classify the soil of the test area. The results suggest that the combination of remote sensing image with terrain data can distinguish nine soil subcategories and one non -soil unit. The overall classification accuracy can reach 91.76%.
出处
《国土资源遥感》
CSCD
北大核心
2014年第1期57-62,共6页
Remote Sensing for Land & Resources
基金
国家"十一五"科技支撑项目(编号:2007BAC30B05)资助
