An Abundance Estimation Method Based on Matrix Factorization for Hyperspectral Images
- 10.2991/asei-15.2015.8How to use a DOI?
- remote sensing imagery, hyperspectral unmixing, abundance estimation, matrix triangular factorization.
For hyperspectral remote sensing imagery, the observation of image pixel usually consists of more than one material, causing it to be a “mixed pixel”. In order to analyze the hyperspectral dataset, it is necessary to decompose the mixed pixels into a collection of substances’ spectra and their corresponding abundance proportions. However, hyperspectral dataset usually contains hundreds of spectral images, which brings rather large computational complexity. This paper presents a quick approach to estimate the abundances by exploiting matrix triangular factorization, which can rectify possible bias in the given spectral by utilizing the data’s geometric spatial information. This property is rather effective especially when no pure-pixel presents in the imagery. Experimental results on real hyperspectral data indicate that the proposed approach can obtain desirable results
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Wei Xia PY - 2015/05 DA - 2015/05 TI - An Abundance Estimation Method Based on Matrix Factorization for Hyperspectral Images BT - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation PB - Atlantis Press SP - 35 EP - 38 SN - 2352-5401 UR - https://doi.org/10.2991/asei-15.2015.8 DO - 10.2991/asei-15.2015.8 ID - Xia2015/05 ER -