Processing of Hyperion data set for detection of indicative minerals using a hybrid method in Dost-Bayli, Iran
- 19 September 2016
- journal article
- research article
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 37 (20) , 4923-4947
Abstract
In recent years hyperspectral remote sensing has played an important role in discovering of the earth surface and unmixing is an indispensable part of the hyperspectral data analysis. The most challenging stage in the spectral unmixing is determination of endmembers (EMs). Because of the absence of pure pixels, common methods based on pure pixel assumption do not yield accurate results. On the other hand, Hyperion hyperspectral data acquired by National Aeronautics and Space Administration (NASA)’s Earth Observing-1 (EO-1) system, is available widely but with a lower signal-to-noise ratio (SNR) in comparison to airborne spectrometers. Therefore, the methods with less sensitivity to noise amount will be more efficient in processing of the Hyperion data. Minimum Volume Constrained Nonnegative Matrix Factorization (MVC-NMF) algorithm is then an appropriate technique for EM detection in this case. It, however, has shortcomings in dealing with large data. To fix this problem the first module of Optical Real-time Adaptive Spectral Identification System (ORASIS) was applied for data reduction before running of the MVC-NMF algorithm. The modified technique was then investigated on a set of noisy synthetic data that the outcomes proved its functionality. The Hyperion image of Dost-Bayli area located in the Ardabil province in northwestern Iran, was then unmixed by the mentioned approach. To validate the accuracy of detected minerals, 20 surface samples were collected from the study area and analysed by X-ray diffraction (XRD) for detection of their mineralogical constituents and spectrometry to create a native spectral library. However, both native and United States Geological Survey (USGS) spectral libraries were applied in identification of estimated EMs. The signatures of the obtained EMs by hybrid method were appropriately similar to reference spectra. The mineral abundances maps were therefore generated by linear spectral unmixing (LSU), which have proper consistency with XRD results.Keywords
This publication has 18 references indexed in Scilit:
- Simplex volume analysis for finding endmembers in hyperspectral imagery2015
- Nonlinear Unmixing of Hyperspectral Images: Models and AlgorithmsIEEE Signal Processing Magazine, 2013
- Linear Mixture Analysis for Hyperspectral Imagery in the Presence of Less Prevalent MaterialsIEEE Transactions on Geoscience and Remote Sensing, 2012
- A Convex Analysis-Based Minimum-Volume Enclosing Simplex Algorithm for Hyperspectral UnmixingIEEE Transactions on Signal Processing, 2009
- Hyperspectral Subspace IdentificationIEEE Transactions on Geoscience and Remote Sensing, 2008
- Hyperspectral Data Exploitation2006
- Estimation of Number of Spectrally Distinct Signal Sources in Hyperspectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2004
- Processing hyperion and ali for forest classificationIEEE Transactions on Geoscience and Remote Sensing, 2003
- Comparison of airborne hyperspectral data and eo-1 hyperion for mineral mappingIEEE Transactions on Geoscience and Remote Sensing, 2003
- Analyzing hyperspectral data with independent component analysis1998