Convolutional Autoencoder for Blind Hyperspectral Image Unmixing
This work addresses the problem of decomposing mixed pixels in hyperspectral images for remote sensing applications, offering improved performance for practitioners in this field.
This paper proposes a novel convolutional autoencoder architecture for blind hyperspectral image unmixing. The method outperforms existing unmixing techniques in abundance estimation and achieves competitive results for endmember extraction, as measured by RMSE and SAD.
In the remote sensing context spectral unmixing is a technique to decompose a mixed pixel into two fundamental representatives: endmembers and abundances. In this paper, a novel architecture is proposed to perform blind unmixing on hyperspectral images. The proposed architecture consists of convolutional layers followed by an autoencoder. The encoder transforms the feature space produced through convolutional layers to a latent space representation. Then, from these latent characteristics the decoder reconstructs the roll-out image of the monochrome image which is at the input of the architecture; and each single-band image is fed sequentially. Experimental results on real hyperspectral data concludes that the proposed algorithm outperforms existing unmixing methods at abundance estimation and generates competitive results for endmember extraction with RMSE and SAD as the metrics, respectively.