Share Email Print
cover

Proceedings Paper

Endmember extraction algorithm for hyperspectral image based on PCA-SMACC
Author(s): Chang Liu; Junwei Li; Guangping Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 21 February 2014
PDF: 9 pages
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); doi: 10.1117/12.2054028
Show Author Affiliations
Chang Liu, Science and Technology on Optical Radiation Lab. (China)
Junwei Li, Science and Technology on Optical Radiation Lab. (China)
Guangping Wang, Science and Technology on Optical Radiation Lab. (China)


Published in SPIE Proceedings Vol. 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
Jorge Ojeda-Castaneda; Shensheng Han; Ping Jia; Jiancheng Fang; Dianyuan Fan; Liejia Qian; Yuqiu Gu; Xueqing Yan, Editor(s)

© SPIE. Terms of Use
Back to Top