Spectral mixture analysis of hyperspectral data using Genetic Algorithm and Spectral Angle Constraint (GA-SAC)
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21586268,p. 1-4
Abstract
A Genetic Algorithm and Spectral Angle Constraint (GA-SAC) abundance estimation method is presented to improve the accuracy of abundance maps affected by illumination effects and sensor noise. As an improved version of the Spectral Angle Constraint (SAC), the GA-SAC was compared against several existing techniques. Preliminary results showed advantages of the proposed GA-SAC method from tests involving a simulated hyperspectral data set as well as for mapping mineral abundances using AVIRIS data over Cuprite, Nevada.Keywords
This publication has 7 references indexed in Scilit:
- A New Method to Change Illumination Effect Reduction Based on Spectral Angle Constraint for Hyperspectral Image UnmixingIEEE Geoscience and Remote Sensing Letters, 2011
- On Endmember Identification in Hyperspectral Images Without Pure Pixels: A Comparison of AlgorithmsJournal of Mathematical Imaging and Vision, 2011
- Comparison of fully constrained and weakly constrained unmixing through mine-tailing composition mappingCanadian Journal of Remote Sensing, 2008
- Hyperspectral Data Exploitation2006
- An algorithm for fully constrained abundance estimation in hyperspectral unmixing2005
- Does independent component analysis play a role in unmixing hyperspectral data?IEEE Transactions on Geoscience and Remote Sensing, 2005
- Some Comments on the Evaluation of Model PerformanceBulletin of the American Meteorological Society, 1982