摘要
随着卫星遥感影像分辨率的不断提高,人们希望从遥感图像中获得更多有用的数据和信息,所以遥感影像的分类变得尤为重要。但是基于光谱特征的影像分类精度过低,不能满足生产的需要,所以研究利用其他辅助手段来提高遥感影像的分类成为未来发展的一个重要方向。本文研究了利用灰度共生矩阵提取纹理特征的方法并对利用纹理特征影像辅助光谱特征分类的方法进行了研究。实验结果表明,纹理特征辅助光谱特征分类能够提高遥感影像分类的准确性和精度。
With the development of high resolution remote sensing satellite image, people hoped that obtains more useful data and the information from the remote sensing images. So the classification of remote sensing images becomes especially important. But the accuracy based on the spectral feature of the remote images classification is too low and could not meet the needs of production. So using other means to assistant and to improve the classification of remote sensing images become an important development direction. The texture feature images are extracted by the gray level co - occurrence matrix and the classifications are carried out by combined the texture features with the spectral features is researched in this paper. The test results show that the assistant classification as the paper mentioned could increase the classification veracity and accuracy of remote sensing images.
出处
《测绘与空间地理信息》
2008年第6期82-85,共4页
Geomatics & Spatial Information Technology
关键词
遥感
辅助分类
纹理特征
灰度共生矩阵
Remote Sensing
assistant classification
texture feature
Gray Level Co - occurrence Matrix
