Various Deep Learning Methods for Hyperspectral Images

Hyperspectral imagery is widely used in remote sensing applications that take into account thousands of spectral channel compositions over a single scene. Hyperspectral imagery requires accurate models of learning to extract the hyperspectral features in an image. Due to the presence of its spatial and spectral resolution, the image learning model presents a core challenge due to its complicated nature of image frames. In order to assist it during the learning process, several attempts have been made to address its complicated nature. However, these methods failed to provide the hyperspectral imagery with a deeper understanding. Because of the presence of mixed pixels, limited training samples and redundant data, the utilization of deep learning techniques addresses the problems. The deep learning process addresses the complex image data relationship. In this paper, various deep learning methods are studied which are used for the learning of hyperspectral imagery. Initially, we present an overview on various deep learning methods for various image processing techniques. A system review is then carried out on various hyperspectral image learning models based on deep learning.