Hyperspectral Unmixing Using Deep Convolutional Autoencoders in a Supervised Scenario
Open Access
- 5 February 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 13 (19391404) , 567-576
Abstract
Abstract—Hyperspectral unmixing (HSU) is an essential technique that aims to address the mixed pixels problem in hyperspectral imagery via estimating the abundance of each endmember at every pixel given the endmembers. This paper introduces two approaches intending to solve the challenge of the mixed pixels using deep convolutional autoencoders (DCAEs), namely pixel-based DCAE, and cube-based DCAE. The former estimates abundances with the help of only spectral information, while the latter utilizes both spectral and spatial information which results in better unmixing performance. In the proposed frameworks, the weights of the decoder are set equal to the endmembers in order to address the issue in a supervised scenario. The proposed frameworks are also adapted to the VGG-Net that proved increasing depth with small convolution filters (3 ${\times}$ 3) leads to a considerable improvement. In other words, inspired by this idea, we utilize small and fixed kernels of size 3 in all layers of both proposed frameworks. The network is trained via the spectral information divergence objective function, and the dropout and regularization techniques are utilized to prevent overfitting. The superiority of the proposed frameworks is proven via conducting some experiments on both synthetic and real hyperspectral datasets and drawing a comparison with state-ofthe- art methods. Moreover, the quantitative and visual evaluation of the proposed frameworks indicate the necessity of integrating spatial information into the HSU.
Keywords
This publication has 34 references indexed in Scilit:
- Hyperspectral Unmixing With Spectral Variability Using a Perturbed Linear Mixing ModelIEEE Transactions on Signal Processing, 2015
- Deep learningNature, 2015
- Spectral Unmixing via Data-Guided SparsityIEEE Transactions on Image Processing, 2014
- Spectral Unmixing of Hyperspectral Imagery Using Multilayer NMFIEEE Geoscience and Remote Sensing Letters, 2014
- A Review of Nonlinear Hyperspectral Unmixing MethodsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Nonlinear Unmixing of Hyperspectral Images: Models and AlgorithmsIEEE Signal Processing Magazine, 2013
- Nonlinear Estimation of Material Abundances in Hyperspectral Images With $\ell_{1}$-Norm Spatial RegularizationIEEE Transactions on Geoscience and Remote Sensing, 2013
- A Quantitative and Comparative Analysis of Endmember Extraction Algorithms From Hyperspectral DataIEEE Transactions on Geoscience and Remote Sensing, 2004
- Spectral information divergence for hyperspectral image analysis2003
- N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data1999