干旱区生态环境知识资源中心(Arid): 利用TM数据提取干旱区土地覆被信息的方法比较

Arid

	利用TM数据提取干旱区土地覆被信息的方法比较
其他题名	Study on the Methods of Deriving the Information of Land Cover in the Arid Areas by Using TM Data
	沙占江 1; 马海州 1; 李玲琴 2; 樊启顺 2; 黄华兵 1; 杨海镇 2; 曹广超 1
来源期刊	干旱区地理
ISSN	1000-6060
出版年	2005
卷号	28 期号:1 页码:59-64
中文摘要	以柴达木盆地香日德绿洲作为研究实验区,对该区域ETM遥感数据经过空间分辨率融合、主成分分析等方法进行空间信息增强及专题信息增强处理,组合最佳视觉背景图像,分别在不同背景图像上选择训练样本,利用最大似然法监督分类方法(MLC)、多空间尺度分层聚类(SSHC) 和基于知识的模糊聚类方法(KFC)等分类器,分别用各自训练样本初始化各类别信息特征值,形成类别特征值模式库,分别以此为基础对待分样本进行分类,对初分类的结果经过类别合并、碎斑滤除以及重新编码赋色等分类后处理,得到最终分类结果及分类精度评价结果.从所获数据可以得出如下结论:从总体精度和Kappa值可知,SSHC和KFC分类方法所获结果精度较高,总体精度比MLC分类结果约高于3%,SSHC之结果精度略高于KFC之结果;SSHC、KFC和MLC三种分类方法对该区域地表覆被信息的提取分类中,SSHC分类方法对耕地、石砾地、河滩和荒漠分类结果较好,KFC分类方法对耕地、沙地、河滩和荒漠分类结果较好,MLC分类方法对耕地、河滩和荒漠分类结果较好,三种分类方法对耕地、河滩和荒漠等三种地类的分类精度较高,用户精度都在80%以上,而对沙地和石砾地的分类结果其用户精度大都低于80%.
英文摘要	By taking the Xiangride Oasis as the study area, in this paper, the spatial information and the thematic information of land use and land cover in the study area are enhanced by using the ETM remote sensing data after inosculating the spatial resolving power and analyzing the principal components. The optimal color images are composed by using some processed band data, the training samples are selected from the background images. By using the maximum likelihood supervision classification (MLC), multi-spatial-scale hierarchical clustering algorithm (SSHC) and geographic-knowledge-based fuzzy clustering (KFC), the training samples are separately initialized to obtain the eigenvalues of all kinds information so as to develop the eigenvalue mode database. All pixels were classified by using the mode base to get the initial classified results, the finally classified results and classification precision are derived by post-processing including the clumping, riddling, elimination and recoding for the initial classified results. The conclusions are as follows: the classified accuracy of SSHC and KFC is 3% higher than that of MLC, and the classified accuracy of SSHC is slightly higher than that of KFC. In three methods for deriving the information of land use and land cover, SSHC is more ideal to class farmlands, gravel lands, flood lands and deserts, KFC is more ideal to class farmlands, sand lands, flood lands and deserts, and MLC is more ideal to class farmlands, flood lands and deserts. The accuracy of all three methods for classifying farmlands, flood lands and deserts is higher than 80%, but it is lower than 80% in classifying sand lands and gravel lands.
中文关键词	TM数据 ; 土地覆被 ; 遥感 ; 分类方法 ; 干旱区
英文关键词	LUCC TM data land use/cover LUCC remote sensing classifying method arid area
语种	中文
国家	中国
收录类别	CSCD
WOS类目	REMOTE SENSING ; AGRICULTURAL ECONOMICS POLICY
WOS研究方向	Remote Sensing ; Agriculture
CSCD记录号	CSCD:1905063
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/206131
作者单位	1.中国科学院青海盐湖研究, 西宁, 青海 810008, 中国; 2.青海师范大学地理与资源环境科学系, 西宁, 青海 810008, 中国
推荐引用方式 GB/T 7714	沙占江,马海州,李玲琴,等. 利用TM数据提取干旱区土地覆被信息的方法比较[J],2005,28(1):59-64.
APA	沙占江.,马海州.,李玲琴.,樊启顺.,黄华兵.,...&曹广超.(2005).利用TM数据提取干旱区土地覆被信息的方法比较.干旱区地理,28(1),59-64.
MLA	沙占江,et al."利用TM数据提取干旱区土地覆被信息的方法比较".干旱区地理 28.1(2005):59-64.