Share Email Print

Proceedings Paper

Hyperspectral image anomaly detecting based on kernel independent component analysis
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Hyperspectral image is a three-dimensional data cube which describes spatial information and spectral information of the scene. The anomaly detection technique can detect the targets which have difference between the image and the background without priori information. Kernel independent component analysis(KICA) is a method of mapping hyperspectral data into the kernel space for feature extraction. In this paper, the hyperspectral image is subjected to abnormal information detection based on KICA. First, we calculate the kernel matrix K in order to map the data to high-dimensional space for whitening and dimension reduction processing. Then we utilize the FastICA algorithm to extract the core independent component (KIC). Finally, the extracted independent components with the most abnormal information are analyzed by RX operator, kernel RX operator and abundance quantization method. Comparing with the simulation result and the detected result by RX method, the representation shows the algorithm based on KICA has better detection performance.

Paper Details

Date Published: 20 February 2018
PDF: 8 pages
Proc. SPIE 10697, Fourth Seminar on Novel Optoelectronic Detection Technology and Application, 1069710 (20 February 2018); doi: 10.1117/12.2309936
Show Author Affiliations
Shangzhen Song, Xidian Univ. (China)
Huixin Zhou, Xidian Univ. (China)
Hanlin Qin, Xidian Univ. (China)
Kun Qian, Xidian Univ. (China)
Kuanhong Cheng, Xidian Univ. (China)
Jin Qian, Xidian Univ. (China)

Published in SPIE Proceedings Vol. 10697:
Fourth Seminar on Novel Optoelectronic Detection Technology and Application
Weiqi Jin; Ye Li, Editor(s)

© SPIE. Terms of Use
Back to Top