Guided filter based Deep Recurrent Neural Networks for Hyperspectral Image Classification

Abstract

Hyperspectral image(HSI) classification has been a hot topic in the remote sensing community. A large number of methods have been proposed for HSI classification. However, most of them are based on the extraction of spectral feature, which leads to information loss. Moreover, they rarely consider the correlation among the spectrums. In this paper, we see spectral information as a sequential data which is relevant with each other. We introduce long short-term memory model, which is a typical recurrent neural network (RNN), to deal with HSI classification. In order to solve the problem of difficult to reach the steady state of the model, we proposed a novel guided filter based RNN model. Also, we proposed a method for modeling hyperspectral sequential data, which is very useful for future research work. The experimental results show that our proposed method can improve the classification performance as compared to other methods in two popular hyperspectral datasets.