遥感影像纹理分析方法研究  

STUDY ON TEXTURE ANALYSIS METHODS BASED OF REMOTE SENSING IMAGE

作　　者：梁国军[1] 彭明春[1] 王崇云[1] 

机构地区：[1]云南大学生态学与地植物学研究所,云南昆明650091

出　　处：《云南地理环境研究》2009年第1期93-98,共6页Yunnan Geographic Environment Research

摘　　要：影像纹理是遥感影像中的重要信息,原始的光谱信息加上纹理信息可以提高影像的精确性。作为提高影像分类精度的重要方法——纹理分析,合理有效地使用纹理分析方法至关重要。不同的纹理分析方法,不同程度的提高影像分类的精度。目前对影像进行纹理分析的方法主要有:统计方法、结构方法和谱方法3类。分别就3种方法的研究进展、应用情况进行了阐述,最后对影像纹理分析方法3种模式对比研究。The texture is one of the important features of remote sensing images, the original spectra information and texture information can improve the accuracy of the remote sensing images. It has played an important role in the classification of the remote sensing images, it is very vital to use the image texture analysis reasonably and effectively. The accuracy of the remote sensing images can be improved by different texture analysis methods. At present, there is a wide range of texture analysis techniques that are used for remote sensing images： statistical methods, structural methods and spectral methods. The paper discussed the research progress and application about the texture analysis methods. Finally, it analyzed the comparative study of remote sensing texture analysis methods in the recent years.

关 键 词：纹理 分析方法 遥感影像 

分 类 号：X87[环境科学与工程—环境工程]