基于独立分量分析的遥感影像分类方法

Remote Image Classification Based on Independent Component Analysis

多光谱遥感影像反映了不同地物的光谱特征,其分类是遥感应用的基础。独立分量分析对未知的源信号的混合信号进行估计,可以获得相互独立的源信号的近似。独立分量分析利用了信号的高阶统计信息,对于多光谱遥感影像而言,其去除了波段影像之间的相关性,获得的波段影像是相互独立的。最后通过TM遥感影像数据的分类试验,验证了基于独立分量分析的线性光谱混合分析模型应用于多光谱遥感影像非监督分类的有效性。

The multi-spectral remote sensing images reflect the spectral features of diverse surface features, and their classification is the base of remote sensing applications. Independent Component Analysis （ICA） algorithm can estimate the independent source signals that are mixed by unknown mode, and the source signals are unknown, too. The ICA al- gorithm uses the high-order information of signals; to multi-spectral remote sensing images, ICA algorithm not only re- moves the correlation of images, but also obtains the new band images that are mutual independent. Experimental results with TM remote sensing images show that a linear spectral random mixture analysis model based on ICA is effective in multi-spectral remote sensing image classification.