Share Email Print
cover

Proceedings Paper

An efficient approach for multi-temporal hyperspectral images interpretation based on high-order tensor
Author(s): S. Hemissi; I.R. Farah; K. Saheb Ettabaa; B. Solaiman
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The main purpose of this paper is to propose and to validate a new multi-temporal algorithm for hyperspectral endmembers extraction. The advanced approach is based on multi-linear algebra, spectral analysis and tensor data structure for each pixel. The detection of an endmember in the time series is done by the interpretation of the spatial-temporal signature in a multi-dimensional tonsorial space. Thus, the images could have different resolutions and could be coming from different dates. A multi-temporal synthetic and Hyperion series images were used to assess the effectiveness of the proposed algorithm. The obtained results show good performances with both permanent and temporal known features.

Paper Details

Date Published: 27 October 2011
PDF: 6 pages
Proc. SPIE 8180, Image and Signal Processing for Remote Sensing XVII, 81800J (27 October 2011); doi: 10.1117/12.898015
Show Author Affiliations
S. Hemissi, Ecole Nationale des Sciences de l'Informatique (Tunisia)
TELECOM Bretagne (France)
I.R. Farah, Ecole Nationale des Sciences de l'Informatique (Tunisia)
TELECOM Bretagne (France)
K. Saheb Ettabaa, Ecole Nationale des Sciences de l'Informatique (Tunisia)
TELECOM Bretagne (France)
B. Solaiman, TELECOM Bretagne (France)


Published in SPIE Proceedings Vol. 8180:
Image and Signal Processing for Remote Sensing XVII
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top