基于地质统计学纹理特征的遥感影像分类方法研究

Remote Sensing Image Classification Method Based on Geostatistics Texture

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。

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 by means of test.At the same time,the paper discussed the size of computation window,computation direction and computation step according to the practical application.The results proved that the approach combining spectral features and textural measures based on the geostatistics texture to the classification of the remote sensing image may significantly improve the classification accuracy.