基于地统计学的图像纹理在岩性分类中的应用

被引:38
作者
黄颖端
李培军
李争晓
机构
[1] 北京大学遥感与地理信息系统研究所
[2] 普渡大学土木工程系 北京
[3] 北京
[4] 美国印第安纳州 IN-
基金
教育部留学回国人员科研启动基金;
关键词
纹理; 变差函数; 对数变差函数; 岩性分类;
D O I
暂无
中图分类号
P627 [遥感勘探];
学科分类号
1404 ;
摘要
纹理是遥感图像的重要特征,它揭示了图像中辐射亮度值空间变化的重要信息。本文运用地统计学中的对数变差函数计算图像纹理,并与图像的光谱信息结合,进行图像岩性分类,分析了不同大小窗口纹理信息对分类精度的影响。结果表明,运用地统计学原理进行图像分类,可大大提高图像的分类精度;采用较大窗口提取的纹理信息参与分类能使总体分类精度提高,但某些岩性类的分类精度有所下降,建议在实际应用中,根据具体情况选择窗口的大小。
引用
收藏
页码:45 / 49
页数:5
相关论文
共 14 条
[1]  
Semivariogram textural classification of JERS- 1 (Fuyo- 1) SAR data obtained over a flooded area of the Amazon rainforest. Miranda F P,Fonseca L E N,Carr J R. International Journal of Remote Sensing . 1998
[2]  
The semivariogram in comparison to the co-occurrence matrix for classification of image texture. Carr J R,Miranda F P. IEEE Transactions on Geoscience and Remote Sensing . 1998
[3]  
The integration of spectral and textural information using neural networks for land cover mapping in the Mediterranean. Berberoglu S,Lloyd C D,Atkinson P M,et al. Computers and Geosciences . 2000
[4]  
Computing geostatistical image texture for remotely sensed data classification. Chica-Olmo M,Abarca-Hernandez F. Computers and Geosciences . 2000
[5]  
Evaluation of geostatisical measures of radiometric spatial variability for lithologic discrimination in Landsat TM images. Abarca-Hernandez F,Chica-Olmo M. Photogrammetric Engineering and Remote Sensing . 1999
[6]  
Geostatistical description of texture on an aerial photograph for discriminating classes of land cover. Lark R M. International Journal of Remote Sensing . 1996
[7]  
Geostatistics for Natural Resources Evaluation. Goovaerts P. . 1997
[8]  
Texture feature for image classification. Haralick R M,Shanmugam K,Dinstein I. IEEE Transactions on Systems Man and Cybernetics . 1973
[9]  
GSLIB: geostatistical software library and users guide. Deutsch C V,Journel A G. . 1992
[10]  
Geostatistic & Remote Sensing. Curran P J,Atkinson P M. Progress in Physics . 1998