A New Endmember Extraction Method Based on Least Squares

Abstract

Endmember extraction is frequently adopted to detect spectrally unique signatures of pure ground materials in hyperspectral imagery. These endmembers are the purest pixels in the HSI data cubes. Every pixel in a HSI data cube can be expressed as a linear combination of a finite number of endmembers. In this paper, we propose a novel method for endmember extraction by means of least squares. We perform minimum noise fraction to reduce the dimensionality of the data cube, initialize the endmembers by using automatic target generation process, compute the abundance map from the dimensionality reduced data cube and the initial endmembers, and calculate the final endmembers by using least squares. Our proposed method is comparable to and sometimes outperforms existing methods in term of spectral angle distance for all four testing data cubes for endmember extraction. In addition, our method is relatively fast as well because it only performs quite simple operations to find endmembers in the testing hyperspectral data cubes.