CLASSIFICATION OF HIGH RESOLUTION OPTICAL AND SAR FUSION IMAGE USING FUZZY KNOWLEDGE AND OBJECT-ORIENTED PARADIGM

CLASSIFICATION OF HIGH RESOLUTION OPTICAL AND SAR FUSION IMAGE USING FUZZY KNOWLEDGE AND OBJECT-ORIENTED PARADIGM
复制标题

DOI：
--
复制
发表时间：
2010
期刊：
--
影响因子：
--
通讯作者：
J. Xia;Peijun Du;W. Cao
J. Xia;Peijun Du;W. Cao
中科院分区：
其他
文献类型：
--
作者：
J. Xia;Peijun Du;W. Cao

文献摘要

被引文献

相似文献

：采用IKONOS光学数据与cosmos - skymed SAR图像的融合图像作为分类器输入，在面向对象范式下进行土地覆盖分类。首先，采用Frost滤波方法去除SAR图像中的斑点噪声；采用IHS、PCA和小波变换三种常用的方法对高分辨率光学图像和SAR图像进行融合。与其他融合方法相比，采用基于小波变换的融合方案进行分类。基于人工解译和专家知识得到的光谱、空间和纹理特征建立模糊知识。最后，将该方法与其他传统分类方法进行了比较。
: The fusion image of IKONOS optical data and COSMO-SkyMed SAR image is used as the classifier inputs for land cover classification under an object-oriented paradigm. Firstly, Frost filter is selected to reduce speckle noises of SAR image. Three popular methods, including IHS, PCA and wavelet transform, are applied to fuse high resolution optical and SAR images. Comparing with other fusion methods, wavelet transform based fusion scheme is used for classification. Fuzzy knowledge is established based on the spectral, spatial and texture features derived from manual interpretation and expert knowledge. Finally, this proposed approach is compared with other traditional classification methods.