中文摘要：

针对高光谱遥感图像分类中带标记训练样本较少、导致分类正确率偏低的问题,提出用于高光谱图像分类的空间约束半监督高斯过程方法.由于高光谱图像的特征空间满足流形分布假设,大量未标记样本可以使数据空间变得更加稠密,从而有助于更加准确地刻画局部空间特性,提高分类的精度和普适性.通过对高斯过程模型中的核函数施加空间近邻约束,建立未标记样本与带标记样本之间的空间联系.该半监督高斯过程分类器不仅可以提升高光谱遥感图像的分类性能,而且构造简单,实现方便.实验结果表明,在仅有少量带标记的训练样本情况下,半监督高斯过程分类方法对高光谱图像有较高的分类精度和稳定性.

英文摘要：

A new classification method based on spatial semi-supervised Gaussian processes （SSGP） was proposed to address the problem of low hyperspectral imagery classification performance caused by a small number of labeled training samples. As the feature space of a hyperspectral imagery satisfies the assump- tion of manifold distribution, a lot of unlabeled samples will make the feature space denser so that the local spatial character can be exploited more precisely and the classification accuracy and generality can be im- proved. In SSGP, the constraint of spatial neighborhood was imposed into the kernel function of Gaussian process, so the spatial correlations of labeled and unlabeled samples can be embedded in the kernel func- tion. SSGP not only raises the classification performance, but also is easy to build and realize. Experimen- tal results show that SSGP method is very good at classification of hyperspectral images in terms of classi- fication accuracy and stability in the case of small size of labeled training samples.