Skip to Main Content
Classification is an important task in Hyperspectral data analysis. Hyperspectral images show strong correlations across spatial and spectral neighbors. Theoretically, classifier designed with a joint spectral and spatial correlations can improve classification performance than classifier which only utilize one of the correlations. Gaussian Processes(GPs) have been used for Hyperspectral imagery classification successfully by exploiting spectral correlation. Meanwhile,conditional random fields(CRFs) classify image regions by incorporating neighborhood Spatial interactions in the labels as well as the observed data. In this paper, we make a combination of GPs and CRFs and propose a novel GPCRF classifier to exploit spectral and spatial interactions in Hyperspectral remote sensing images. Experiments on the real-world Hyperspectral image attest to the accuracy and robust of the proposed method.