| 变差函数和神经网络结合的遥感影像分类方法研究 |
| |
| 引用本文： | 李小涛,李纪人,黄诗峰,宋小宁.变差函数和神经网络结合的遥感影像分类方法研究[J].国土资源遥感,2006,17(1):18-21. |
| |
| 作者姓名： | 李小涛 李纪人 黄诗峰 宋小宁 |
| |
| 作者单位： | 1. 中国水利水电科学研究院,北京,100044
2. 中国科学院研究生院资环学院,北京,100049 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 提出利用地统计学变差函数对遥感影像纹理信息进行提取，将变差函数得到的纹理信息与光谱信息相结合，运用神经网络进行分类的遥感影像分类方法。将该分类方法应用于试验区，并与最大似然法的分类结果进行对比分析，结果表明，该方法具有较高的分类精度。
|
| 关 键 词： | 地统计学 变差函数 神经网络 纹理 分类 |
| 文章编号： | 1001-070X(2006)01-0018-04 |
| 收稿时间： | 2005-10-10 |
| 修稿时间： | 2005-11-20 |
A REMOTE SENSING IMAGE CLASSIFICATION
METHOD BASED ON GEOSTATISTICS |
| |
| LI Xiao-tao,LI Ji-ren,HUANG Shi-feng,SONG Xiao-ning.A REMOTE SENSING IMAGE CLASSIFICATION
METHOD BASED ON GEOSTATISTICS[J].Remote Sensing for Land & Resources,2006,17(1):18-21. |
| |
| Authors: | LI Xiao-tao LI Ji-ren HUANG Shi-feng SONG Xiao-ning |
| |
| Institution: | 1. China Institute of Water Resources and Hydropower,Beijing 100044, China; 2. Graduate Univerity of Chinese Academy of Sciences, Beijing 100049, China |
| |
| Abstract: | Texture is the key character of remote sensing image.In this paper,the image texture was extracted by means of semivariogram.On such a basis,this study adopted the back propagation artificial neural network method to make classification by combining spectral feature with many sort of textures.The classification results were then compared with the results obtained by the maximum likelihood method.The results of the study have proved that the application of combined spectral features and textural measures based on the geostatistics and NN theory to the classification of the remote sensing image may improve the accuracy of image classification. |
| |
| Keywords: | Geostatistics Variation Artificial neural network Texture Classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《国土资源遥感》浏览原始摘要信息 |
| 点击此处可从《国土资源遥感》下载免费的PDF全文 |
