Hyperspectral remote sensing image classification based on random average band selection and an ensemble kernel extreme learning machine

Hyperspectral remote sensing technology can explore a lot of information about ground objects, and the information is not explored in multispectral technology. This study proposes a hyperspectral remote sensing image classification method. First, we preprocess the hyperspectral data to obtain the average spectral information of the pixels; the average spectral information contains spectral-spatial features. Second, the average spectral information is randomly band selected to obtain multiple different datasets. Third, based on ensemble learning and a kernel extreme learning machine, an ensemble kernel extreme learning machine is proposed. Finally, a hyperspectral remote sensing image classification model based on the ensemble kernel extreme learning machine is established. Experiments with two common hyperspectral remote sensing image datasets demonstrate the effectiveness of the proposed method.