中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于K-T变换和主成分变换的植被信息提取 中南林业科技大学学报 2014 (6) 81-84
Position: Home > Articles > Vegetation information extraction based on K-T transform and principal component transform Journal of Central South University of Forestry & Technology 2014 (6) 81-84

基于K-T变换和主成分变换的植被信息提取

作  者：
陈利;林辉
单  位：
中南林业科技大学林业遥感信息工程研究中心
关键词：
遥感;植被信息;WorldView-2;K-T变换;主成分变换
摘  要：
WorldView-2能够提供1个0.5 m全色波段和8个1.8 m分辨率的多光谱波段,为用户提供进行精确变化检测和制图的能力。本研究以深圳市植被为例,采用WorldView-2高分辨率遥感影像为数据源,进行缨帽变换及主成分分析处理,利用决策树分类模型进行提取。结果表明:WorldView-2影像经过缨帽变换及主成分分析处理后,能够明显增强影像的纹理信息,突出地物特征,并以各地物在经过缨帽变换及主成分分析处理之后的灰度值作为决策树分类的阈值,分类的总体精度、Kappa系数分别为89.26%、0.87,与以往的只利用波段的灰度值及植被指数等作为阈值相比,精度明显提高,方法也得到改善,得到了比较好的分类结果。
译  名：
Vegetation information extraction based on K-T transform and principal component transform
作  者：
CHEN Li;LIN Hui;Research Center of Forestry Remote Sensing & Information Engineering,Central South University of Forestry & Technology;
关键词：
remote sensing;;vegetation information;;Worldview-2;;K-T transform;;principal component transform
摘  要：
WorldView-2 can provide one band that the panchromatic band is 0.5 meters,and eight resolution multispectral bands that the panchromatic bands all are 1.8 meters,and have the ability for users to provide accurate change detection and mapping. With vegetation in Shenzhen city as an example,by adopting the Worldview-2 high resolution remote sensing images as data sources,the Tasseled Cap Transformation and Principal Components Analysis treatment for the vegetation information of Shenzhen city were conducted,further the data extraction was carried out by using decision tree classifi cation model. The results show that having been deal with Tasseled Cap Transformation and Principal Component Analysis,the image texture information was signifi cantly enhanced,the characteristics of ground objects were highlighted; by taking the gray values of all ground objects that were treated with Tasseled Cap Transformation and Principal Component Analysis as the decision tree classifi cation thresholds,the overall precision of plant classifi cation and the Kappa coeffi cient were calculated,being respectively 89.26% and 0.87,compared with the threshold only with previous bands of gray values and vegetation index,the new methods obviously improve the precision,the method is improved,better classifi cation results were obtained.

相似文章

导出引用
计量
文章访问数: 5
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46