文章摘要
傅文杰,洪金益,朱谷昌.基于光谱相似尺度的支持向量机蚀变信息提取[J].地质与勘探,2006,(2):69-73
基于光谱相似尺度的支持向量机蚀变信息提取
EXTRACTING ALTERED AND MINERALIZED ROCK INFORMATION FROM REMOTE SENSING IMAGE BASED ON SUPPORT VECTOR MACHINES AND SPECTRAL SIMILARITY SCALE
投稿时间:2005-08-24  修订日期:2005-10-11
DOI:
中文关键词: 光谱相似尺度  支持向量机  矿化蚀变信息  遥感数据
英文关键词: spectral similarity scale, support vector machine, altered and mineralized rock information, remote sensing data
基金项目:国家科技攻关项目
傅文杰  洪金益  朱谷昌
[1]中南大学地学与环境工程学院,长沙410083 [2]莆田学院,莆田351100 [3]有色金属矿产地质调查中心,北京100814
摘要点击次数: 2858
全文下载次数: 1379
中文摘要:
      文章提出一种基于光谱相似尺度(spectral similarity scale-SSS)的支持向量机(support vector machines-SVM)遥感数据矿化蚀变信息提取的新方法.该方法选择青海两兰地区作为遥感矿化蚀变信息典型研究区,利用该区域的Landsat7ETM遥感影像结合地面实况调查数据,从图像上选取少量具有代表性的样本点的光谱作为参考光谱,利用SSS方法提取训练样本,然后应用SVM算法进行遥感矿化蚀变信息提取.试验结果经野外检查和验证,效果良好.
英文摘要:
      A new method for extracting mineralization information from remote sensing image based on support vector machines(SVM) and spectral similarity scale(SSS) is presented.Based on the Landsat 7 ETM data and ground truth data,Lianlan area in Qinghai Province is taken as a typical region to select training size of main rock types with the method of SSS.Then SVM algorithm was applied to extract mineralization information from remote sensing image.Practice has proved that such a method is effective in extracting mineralization information.
查看全文   查看/发表评论  下载PDF阅读器
关闭