Author： Ji Luyan Geng Xiurui Yu Kai Zhao Yongchao
Publisher： Taylor & Francis Ltd
ISSN： 1366-5901
Source： International Journal of Remote Sensing, Vol.34, Iss.19, 2013-10, pp. : 6577-6586
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
In this study, we present a new non-negative matrix factorization (NMF) method using the pixel's barycentric coordinates for endmember extraction, named BC-NMF. Our method applies the geometrical property of simplex in the calculation of abundance fraction. That is, for any pixel in an image, its abundance fractions are its barycentric coordinates within the endmember coordinate system. Experiments using both simulated and real hyperspectral images show that BC-NMF can generate endmembers with higher accuracy and lower computational complexity than NMF.
Related content
Access to resources
Recommend
