Endmember extraction algorithm for hyperspectral image based on PCA-SMACC

Chang Liu; Junwei Li; Guangping Wang

doi:10.1117/12.2054028

21 February 2014 Endmember extraction algorithm for hyperspectral image based on PCA-SMACC

Chang Liu, Junwei Li, Guangping Wang

Proceedings Volume 9142, Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics: Optical Imaging, Remote Sensing, and Laser-Matter Interaction 2013; 91421A (2014) https://doi.org/10.1117/12.2054028
Event: Selected Proceedings of the Photoelectronic Technology Committee Conferences held July-December 2013, 2013, SuZhou, China

Abstract

Due to the high hyperspectral data volume, high dimensionality and the data itself having great redundancy, the accuracy of Sequential Maximum Angle Convex Cone (SMACC) endmember extraction algorithm is low. In view of this, we proposed an endmember extraction algorithm based on PCA-SMACC. First ， it uses principal component analysis(PCA)algorithm to achieve the purpose of hyperspectral data dimensionality reduction. The method removes the data redundancy while maintains the validity of the data. Then it uses SMACC endmember extraction algorithm on the resulting principal component images. The experimental results show that PCA-SMACC algorithm can compensate for the lack of traditional algorithms. Compared with PPI and SMACC algorithms, PCA-SMACC has improved to some extent in the extraction accuracy and speed.

Citation Download Citation

Chang Liu, Junwei Li, and Guangping Wang "Endmember extraction algorithm for hyperspectral image based on PCA-SMACC", Proc. SPIE 9142, Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics: Optical Imaging, Remote Sensing, and Laser-Matter Interaction 2013, 91421A (21 February 2014); https://doi.org/10.1117/12.2054028

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