SISLU-Net: Spatial Information-Assisted Spectral Information Learning Unmixing Network for Hyperspectral Images
Open Access
- 31 January 2023
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 15 (3), 817
- https://doi.org/10.3390/rs15030817
Abstract
Spectral unmixing is among one of the major hyperspectral image analysis tasks that aims to extract basic features (endmembers) at the subpixel level and estimate their corresponding proportions (fractional abundances). Recently, the rapid development of deep learning networks has provided us with a new method to solve the problem of spectral unmixing. In this paper, we propose a spatial-information-assisted spectral information learning unmixing network (SISLU-Net) for hyperspectral images. The SISLU-Net consists of two branches. The upper branch focuses on the extraction of spectral information. The input of the upper branch is a number of pixels randomly extracted from the hyperspectral image. The data are fed into the network as a random combination of different pixel blocks each time. The random combination of batches can boost the network to learn global spectral information. Another branch focuses on learning spatial information from the entire hyperspectral image and transmitting it to the upper branch through the shared weight strategy. This allows the network to take into account the spectral information and spatial information of HSI at the same time. In addition, according to the distribution characteristics of endmembers, we employ Wing loss to solve the problem of uneven distributions of endmembers. Experimental results on one synthetic and three real hyperspectral data sets show that SISLU-Net is effective and competitive compared with several state-of-the-art unmixing algorithms in terms of the spectral angle distance (SAD) of the endmembers and the root mean square error (RMSE) of the abundances.Keywords
Funding Information
- National Natural Science Foundation of China (61971233, 62076137, and 61901191)
- Shangdong Provincial Natural Science Foundation (ZR2020LZH005)
- China Postdoctoral Science Foundation (2022M713668)
This publication has 58 references indexed in Scilit:
- Nonlinear Hyperspectral Unmixing Using Nonlinearity Order Estimation and Polytope DecompositionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Minimum Volume Simplex Analysis: A Fast Algorithm for Linear Hyperspectral UnmixingIEEE Transactions on Geoscience and Remote Sensing, 2015
- A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote SensingIEEE Signal Processing Magazine, 2013
- Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based ApproachesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral imagesPattern Recognition, 2009
- Spatial and spectral resolution considerations for imaging coastal watersPublished by SPIE-Intl Soc Optical Eng ,2007
- Vertex component analysis: a fast algorithm to unmix hyperspectral dataIEEE Transactions on Geoscience and Remote Sensing, 2005
- Remote sensing for biodiversity science and conservationTrends in Ecology & Evolution, 2003
- Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2001
- N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral dataPublished by SPIE-Intl Soc Optical Eng ,1999