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 > 基于面向对象的鄱阳湖湿地枯水期地类分类研究 南方林业科学 2017 (3) 39-44
Position: Home > Articles > Study on classification of Poyang Lake wetland based on object oriented technology in low water period South China Forestry Science 2017 (3) 39-44

基于面向对象的鄱阳湖湿地枯水期地类分类研究

作  者：
刘俊;涂飞云;刘鹏;韩卫杰;游晓庆;黄晓凤
单  位：
上饶市林业科学研究所;江西省林业科学院
关键词：
鄱阳湖湿地;枯水期;多源数据;面向对象
摘  要：
典型湿地类型分类对于湿地生态环境保护和建设具有重要意义。以鄱阳湖湿地为研究区,利用2015年Landsat 8 OLI遥感影像数据,辅以数字高程模型(DEM)、归一化植被指数(NDVI)、归一化水体指数(NDWI)等数据,基于面向对象的基础上,综合运用阈值法、决策树法和分层分类等方法,对鄱阳湖湿地枯水期地类进行了解译和提取,并取得了较好的分类效果。研究结果表明:(1)辅以多种数据和先易后难的分层分类方法是有效提取地类信息的基础;(2)通过局部方差分析法对影像不同的分割尺度进行评价表明,分割尺度为50时,分割尺度最优;(3)面向对象方法的地类分类结果总体精度为86.5%,Kappa系数为0.84。以上结论表明基于中低分辨率遥感影像,采用多源数据和面向对象的分层分类方法,能够获得较高精度的湿地地类分布,为枯水期候鸟栖息地的研究和保护提供参考依据。
译  名：
Study on classification of Poyang Lake wetland based on object oriented technology in low water period
作  者：
Liu Jun;Tu Feiyun;Liu Peng;Han Weijie;You Xiaoqing;Huang Xiaofeng;Jiangxi Academy of Forestry;Shangrao City Forestry Research Institute;
关键词：
Poyang Lake wet;;low water period;;multi-source data;;object-oriented
摘  要：
The classification of typical wetland types is of great significance for wetland ecological environment protection and construction. Taking Poyang Lake wetland as the study area, the land types of Poyang Lake wetland in low water period were classified and extracted based on the multi-source data including the 2015 Landsat 8 OLI satellite remote sensing image data, digital elevation model(DEM), normalized difference vegetation index(NDVI), normalized difference water index(NDWI), the spatial distribution maps of land cover data using multi-methods, which integrated object-oriented, threshold classification, decision tree classification and hierarchical classification. The better classification results were obtained in this study. The results show that:(1) classification method combined with a variety of auxiliary data and from point to area is effective based information extraction;(2) the optimal segmentation scale was 50 when we evaluated the different image segmentation scale based on local variance analysis method;(3) based on object oriented the method of class classification,the overall accuracy is 86.5%, Kappa coefficient was 0.84. The results suggest that the low resolution remote sensing images based on the hierarchical classification method of multi-source data and object oriented, can obtain high accuracy of the distribution of wetland types, provide a reference for the research and protection of migratory bird habitat selection in low water period.

相似文章

导出引用
计量
文章访问数: 14
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