Deep spectral convolution network for hyperspectral image unmixing with spectral library

• Published in: Signal processing Vol. 176; p. 107672
• Main Authors: Qi, Lin, Li, Jie, Wang, Ying, Lei, Mingyu, Gao, Xinbo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2020
• Subjects: Deep learning; End-to-end model; Hyperspectral unmixing; Spectral convolution network; Spectral library; Deep learning; Hyperspectral unmixing; Spectral convolution network; Spectral library; End-to-end model
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2020.107672

•We propose a deep spectral convolution network with spectral library that can be applied for a series of HSIs after training.•We design a deeper network architecture to efficiently extract local spectral features and achieve better estimation results.•We construct a new loss function, which includes reconstruction error, abundance sparsity, and abundance cross-entropy. Spectral unmixing is an important task for hyperspectral remote sensing image processing, which infers the pure spectral signatures (endmembers) in hyperspectral image (HSI) and their corresponding fractions (abundances). Recently, deep learning has become a powerful tool for HSI analysis, such as HSI classification and HSI super-resolution. In this paper, we propose a new unmixing algorithm that uses the convolutional neural network (CNN) for hyperspectral data incorporating spectral library, which can be applied for a series of HSIs after training. The proposed deep spectral convolution network extracts features and then executes the estimating process from these extracted spectral characteristics to acquire the fractional abundances on a fixed spectral library. Meanwhile, considering the incorporation of spectral library, a deeper convolutional network has been adopted to achieve better results. Moreover, we construct a new loss function, which includes pixel reconstruction error, abundance sparsity, and abundance cross-entropy to train the aforementioned network in an end-to-end manner. Experiments on both simulated and real HSIs indicate the advantage of the proposed method, which can obviously enhance the abundance estimation accuracy.