| 基于地质统计学纹理特征的遥感影像分类方法研究 |
| |
| 引用本文： | 李小涛,潘世兵,宋小宁. 基于地质统计学纹理特征的遥感影像分类方法研究[J]. 地理与地理信息科学, 2009, 25(2) |
| |
| 作者姓名： | 李小涛 潘世兵 宋小宁 |
| |
| 作者单位： | 中国水利水电科学研究院遥感中心,北京,100044;中国科学院研究生院资源与环境学院,北京,100049 |
| |
| 基金项目： | 地理空间信息工程国家测绘局重点实验室经费资助项目，国家自然科学基金 |
| |
| 摘 要： | 介绍地质统计学的原理与方法,论述了地质统计学应用于遥感影像描述及纹理提取的有效性,并将地质统计学变差函数得到的遥感影像纹理信息与其光谱信息相结合进行遥感影像分类试验,结果表明,辅以地质统计学纹理特征的遥感影像分类方法能够明显提高分类精度.
|
| 关 键 词： | 地质统计学 变差函数 纹理 遥感分类 |
Remote Sensing Image Classification Method Based on Geostatistics Texture |
| |
| LI Xiao-tao,PAN Shi-bing,SONG Xiao-ning. Remote Sensing Image Classification Method Based on Geostatistics Texture[J]. Geography and Geo-Information Science, 2009, 25(2) |
| |
| Authors: | LI Xiao-tao PAN Shi-bing SONG Xiao-ning |
| |
| Affiliation: | 1.Remote Sensing Center of China Institute of Water Resources and Hydropower;Beijing 100044;2.College of Resource and Environment;Graduate University of Chinese Academy of Sciences;Beijing 100049;China |
| |
| Abstract: | The remote sensing image texture information plays an important role in the image classification.Most of traditional classification methods are computational auto-classification based on the image spectral characteristics and ignore the spatial textures of image.Geostatistics,as a science treating the relationship of spatial data,could be applied to image classification.In this paper,the semi-variogram was used to extract textural information of remote sensing image,which was adopted to image classification... |
| |
| Keywords: | geostatistics variogram texture remote sensing classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
