A novel nonnegative matrix factorization method for hyperspectral unmixing

Nan Xu; Huadong Yang

doi:10.1117/12.2524186

6 May 2019 A novel nonnegative matrix factorization method for hyperspectral unmixing

Nan Xu, Huadong Yang

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 1106949 (2019) https://doi.org/10.1117/12.2524186
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

In this paper, we propose a new algorithm integrating pure pixel identification into nonnegative matrix factorization (NMF) model to decompose the mixed pixels existing in hyperspectral imagery. The proposed algorithm employs traditional endmember identification algorithm to search for the pure pixel candidates, and then the principal component analysis is performed on the homogenous pixels which consist of the pure pixel candidates and its neighborhoods to identify the endmembers existing in the real scene. Finally, the known-endmember-based NMF unmixing algorithm is used to generate the other unknown endmembers. The proposed algorithm retains the advantages of both pure pixel identification method and NMF. Experimental results based on simulated and real data sets demonstrate the superiority of the proposed algorithm with respect to other state-of-the-art approaches.

Citation Download Citation

Nan Xu and Huadong Yang "A novel nonnegative matrix factorization method for hyperspectral unmixing", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 1106949 (6 May 2019); https://doi.org/10.1117/12.2524186

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available