中文摘要：

针对遥感影像混合像元分解中的地物光谱不确定性问题，提出利用非参数模型来刻画地物光谱的概率分布，并基于贝叶斯方法得到地物面积比例的后验概率分布，最后利用无偏估计和最大似然估计来估算地物面积比例．通过Landsat遥感影像不透水层制图的实验表明，所提方法的分解精度高于传统的线性光谱分解算法和硬分类方法，证明了贝叶斯方法能够较好地解决地物光谱不确定的问题．

英文摘要：

To solve the problem of spectral uncertainty in spectral unmixing of remote sensing images, a non-parametric model is proposed to describe the probability distribution of land cover spectrum. A Bayesian method is used to derive a posteriori probability distribution of the proportion of land cover types. Proportions of land cover types are calculated using unbiased estimation and maximum likelihood estimation. Experiment is carried out to map the impervious surface using a Landsat image. The results show that the proposed Bayesian method has unmixing algorithms and the method of the spectral uncertainty problem. higher accuracy than conventional linear spectral hard classification, therefore is effective in solving