EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing
Authors:
- Savas OzkanSOSavas Ozkan
- Berk KayaBKBerk Kaya
- Gozde Bozdagi AkarGAGozde Bozdagi Akar
Preprint
Abstract
Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications. However, low spatial resolution is a critical limitation for previous sensors and the constituent materials of a scene can be mixed in different fractions due to their spatial interactions. Spectral unmixing is a technique that allows us to obtain the material spectral signatures and their fractions from hyperspectral data. In this paper, we propose a novel endmember extraction and hyperspectral unmixing scheme, so called \textit{EndNet}, that is based on a two-staged autoencoder network. This well-known structure is completely enhanced and restructured by introducing additional layers and a projection metric (i.e., spectral angle distance (SAD) instead of inner product) to achieve an optimum solution. Moreover, we present a novel loss function that is composed of a Kullback-Leibler divergence term with SAD similarity and additional penalty terms to improve the sparsity of the estimates. These modifications enable us to set the common properties of endmembers such as non-linearity and sparsity for autoencoder networks. Lastly, due to the stochastic-gradient based approach, the method is scalable for large-scale data and it can be accelerated on Graphical Processing Units (GPUs). To demonstrate the superiority of our proposed method, we conduct extensive experiments on several well-known datasets. The results confirm that the proposed method considerably improves the performance compared to the state-of-the-art techniques in literature.Keywords
All Related Versions
This publication has 53 references indexed in Scilit:
- Hyperspectral image nonlinear unmixing and reconstruction by ELM regression ensembleNeurocomputing, 2016
- Structured Sparse Method for Hyperspectral UnmixingISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Hydrothermal formation of Clay-Carbonate alteration assemblages in the Nili Fossae region of MarsEarth and Planetary Science Letters, 2010
- On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral imagesPattern Recognition, 2009
- Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchardsRemote Sensing of Environment, 2009
- A comparison of error metrics and constraints for multiple endmember spectral mixture analysis and spectral angle mapperRemote Sensing of Environment, 2004
- Multispectral and hyperspectral image analysis with convex conesIEEE Transactions on Geoscience and Remote Sensing, 1999
- Derivative Analysis of Hyperspectral DataRemote Sensing of Environment, 1998
- Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approachIEEE Transactions on Geoscience and Remote Sensing, 1994
- Bidirectional reflectance spectroscopy: 1. TheoryJournal of Geophysical Research, 1981