计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (33): 244-248.

• 工程与应用 • 上一篇    

滨海湿地信息提取方法比较研究

慈 慧1,2,秦 勇1,2,杨 慧1,2,李国强3,酆格斐4   

  1. 1.中国矿业大学 资源与地球科学学院,江苏 徐州 221116
    2.煤层气资源与成藏过程教育部重点实验室,江苏 徐州 221116
    3.徐州师范大学 科文学院,江苏 徐州 221009
    4.徐州师范大学 语言研究所,江苏 徐州 221009
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-21 发布日期:2011-11-21

Study on extraction methods of coastal wetland information

CI Hui1,2,QIN Yong1,2,YANG Hui1,2,LI Guoqiang3,FENG Gefei4   

  1. 1.School of Mineral Resources and Earth Science,China University of Mining & Technology,Xuzhou,Jiangsu 221116,China
    2.Key Lab of CBM Resources and Pooling Process,Ministry of Education,Xuzhou,Jiangsu 221116,China
    3.College of Kewen,Xuzhou Normal University,Xuzhou,Jiangsu 221009,China
    4.Institute of Linguistics,Xuzhou Normal University,Xuzhou,Jiangsu 221009,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-21 Published:2011-11-21

摘要: 以江苏省典型滨海湿地为研究对象,利用2005年5月26日的Landsat7 ETM+图像数据,在湿地特征及其遥感图像表征分析的基础上,逐步提高湿地信息的提取精度,通过对多光谱遥感图像特征向量的分析,总结出一些湿地信息提取的规则和方法。在滨海湿地光谱特征分析的基础上,对研究区的图像进行了非监督分类,利用湿地的光谱相应特征、纹理特征、主成分变换、归一化差异水体指数等特征和相应的知识规则,得到用于优化分类的知识规则,采用分层分类的方法对非监督分类的结果进行了优化,从而使提取结果的精度较原来有了很大程度的提高。还利用给予数据挖掘的分层分类法进行分类比较,通过建立误差矩阵和对比各种分类方法的分类精度,总结出一套分类精度较高的针对该研究区的湿地信息提取方法。

关键词: 滨海湿地, 非监督分类, 知识规则, 信息提取

Abstract: The coastal wetlands in the northern part of Jiangsu province are taken as study object and the technology about the extraction of wetland is explored by using multi-features and multi-spectral Landsat7 ETM+ acquired on May 26,2005,in combination with the analysis upon the spectral feature of wetlands.Based on the analysis of the characteristics of spectrum about the wetland,unsupervised classification on the image of study area is conducted.By using the spectral feature of wetlands,texture,principal component analysis,NDWI and relative knowledge rules,the results of unsupervised classification are improved.By comparison,the classification accuracy of extraction by using unsupervised knowledge rules is very high.

Key words: coastal wetland, unsupervised classification, knowledge rules, information extraction