干旱区生态环境知识资源中心(Arid): 基于面向对象方法的遥感土壤盐渍化信息监测以渭干河库车河三角洲绿洲为例

Arid

	基于面向对象方法的遥感土壤盐渍化信息监测以渭干河库车河三角洲绿洲为例
其他题名	Remote Sensing Monitoring of Soil Salinization Based on Object-oriented MethodA Case Study in the Delta Oasis of Ugan and Kuqa Rivers
	阿依提拉·吾加布都拉; 塔西甫拉提·特依拜; 古丽加玛丽·吾不力
来源期刊	遥感技术与应用
ISSN	1004-0323
出版年	2010
卷号	25 期号:3 页码:373-378
中文摘要	遥感技术由于具有观测范围广、实时强等特点适合用来研究土壤盐渍化现象。利用遥感手段提取盐渍土信息已经取得了一定的成效。利用面向对象方法,以TM卫星图像数据和野外实地数据为数据源进行提取盐渍地信息。首先,对遥感影像进行预处理,预处理包括几何校正和辐射校正,然后对图像进行图像分割,图像分割使用了分割方法的多尺度分割法、特征选择、面向对象分类和分类图像进行精度评价。对面向对象方法和传统的基于像元分类(最大似然法和最小距离法)结果进行对比分析。结果表明:利用面向对象方法对TM遥感图像进行分类,能有效抑制"椒盐现象"的发生,分类精度比传统的分类方法更高,为盐渍地信息的自动提取提供了广阔的前景。
英文摘要	Precisely get the acurate information of soil salinization is very significant for both soil salinization monitoring and study of the dynamic changes of soil salinization.In this paper,saline soil information is extracted by using object-oriented method based on Landsat TM image data and field survey data.Firstly pre-processing on the remote sensing images has been carried out,including geometric correction and radiometric correction.Secondly the image segmentation has been processed on the remote sensing image using the method of multi-scale segmentation method,feature selection,object-oriented image classification and accuracy assessment of classification.The classification results of object-oriented methods and the traditional pixel-based classification such as maximum likelihood and minimum distance method were analized comparatively.The results showed that: the use of object-oriented method on the classification of TM image,not only reduce the "salt and pepper phenomenon" effectively,but also it has the higher classification accuracy than traditional classification methods,and will provide a broader prospect to the automatic extraction of saline soil information.
中文关键词	面向对象分类 ; 图像分割 ; 盐渍化信息提取 ; 渭干河库车河绿洲
英文关键词	Bbject-oriented classification method Image segmentation Saline soil information Delta Oasis of Ugan and Kuqa Rivers in xinjiang
语种	中文
国家	中国
收录类别	CSCD
WOS类目	REMOTE SENSING ; ENVIRONMENTAL SCIENCES
WOS研究方向	Remote Sensing ; Environmental Sciences & Ecology
CSCD记录号	CSCD:3905735
来源机构	新疆大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/225837
作者单位	新疆大学资源与环境科学学院, 绿洲生态教育部重点实验室, 乌鲁木齐, 新疆 830046, 中国
推荐引用方式 GB/T 7714	阿依提拉·吾加布都拉,塔西甫拉提·特依拜,古丽加玛丽·吾不力. 基于面向对象方法的遥感土壤盐渍化信息监测以渭干河库车河三角洲绿洲为例[J]. 新疆大学,2010,25(3):373-378.
APA	阿依提拉·吾加布都拉,塔西甫拉提·特依拜,&古丽加玛丽·吾不力.(2010).基于面向对象方法的遥感土壤盐渍化信息监测以渭干河库车河三角洲绿洲为例.遥感技术与应用,25(3),373-378.
MLA	阿依提拉·吾加布都拉,et al."基于面向对象方法的遥感土壤盐渍化信息监测以渭干河库车河三角洲绿洲为例".遥感技术与应用 25.3(2010):373-378.